---
title: "Direct Voxel Grid Optimization — paper by Sun et al. (2021)"
description: "This paper (DVGO) shows that a radiance field can be learned from scratch in about a quarter of an… 72 references, cited by 77 papers here."
authors: ["Cheng Sun", "Min Sun", "Hwann-Tzong Chen"]
year: 2021
venue: "arXiv:2111.11215"
source: "https://arxiv.org/abs/2111.11215"
doi: "10.48550/arxiv.2111.11215"
arxiv: "2111.11215"
licence: "arXiv — non-exclusive license to distribute"
licence_url: "http://arxiv.org/licenses/nonexclusive-distrib/1.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/sun-2021-direct-voxel-grid-optimization-super/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/sun-2021-direct-voxel-grid-optimization-super/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/) / Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction

# Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction

**Authors:** Cheng Sun, [Min Sun](https://md.research.elamur.ai/free/en/authors/min-sun/) and Hwann-Tzong Chen · **Year:** 2021 · **Venue:** [arXiv:2111.11215](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/) ([IEEE Computer Society Conference on Computer Vision and Pattern Recognition 2021](https://md.research.elamur.ai/free/en/venues/ieee-computer-society-conference-on-computer-vision-and-pattern-recognition/2021/)) · **Publisher:** [Institute of Electrical and Electronics Engineers](https://md.research.elamur.ai/free/en/publishers/institute-of-electrical-and-electronics-engineers/) · **Licence:** [arXiv — non-exclusive license to distribute](http://arxiv.org/licenses/nonexclusive-distrib/1.0/)

**Links:** [Publisher's page](https://arxiv.org/abs/2111.11215) · [PDF](https://arxiv.org/pdf/2111.11215) · [DOI 10.48550/arxiv.2111.11215](https://doi.org/10.48550/arxiv.2111.11215) · [arXiv 2111.11215](https://arxiv.org/abs/2111.11215) · [OpenAlex](https://openalex.org/W3215589927)

**Citations:** 939 citations (OpenAlex, 2026-10-14) · [77](https://md.research.elamur.ai/free/en/papers/sun-2021-direct-voxel-grid-optimization-super/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
NeRF-style novel view synthesis gives high-quality renderings from posed photographs, but fitting a single scene usually takes hours or days of GPU time. This paper (DVGO) shows that a radiance field can be learned from scratch in about a quarter of an hour on one GPU while reaching NeRF-level quality. Instead of hiding geometry inside an MLP, the authors store volume density directly in a dense voxel grid. Color comes from a second grid of features, decoded by a small MLP. Two ingredients make this explicit approach work. First, raw grid values are interpolated trilinearly and only then passed through the activation, which lets a single cell express a sharp surface, so a coarse grid is enough. Second, the optimization is regularized so it does not fill empty space with "cloud": densities start near zero, and voxels seen by few cameras get smaller learning rates. Training proceeds from coarse geometry to fine detail. On five inward-facing benchmarks the method matches or beats NeRF, making per-scene reconstruction practical.

## Key points
- Training time drops from about 10–20 hours (NeRF) to about 15 minutes on a single NVIDIA RTX 2080 Ti, roughly two orders of magnitude faster. Rendering is about 45× faster than NeRF.
- On the Lego scene the model reaches 23.64 PSNR after 2.33 min, 32.72 after 5.07 min and 34.22 after 13.72 min.
- A density grid of about 160³ voxels is enough. Earlier voxel-based methods needed 512³–1300³ for comparable quality.
- No cross-scene pretraining, external MVS depth, or conversion from a pre-trained NeRF is required. Each scene is optimized directly.
- The pipeline has four parts:
  - automatic search for a tight bounding box;
  - free-space skipping;
  - a coarse geometry stage;
  - a fine stage for detail and view-dependent effects.
- Code is released as DirectVoxGO.

## Interesting ideas
- **Activate after interpolating, not before.** Interpolating raw (pre-activation) values and applying the nonlinearity afterwards gives much sharper boundaries than interpolating already-activated outputs. This trick applies to any discretized field or lookup table that feeds a nonlinearity.
- **Scale learning rates by evidence.** Parameters supported by few observations (here, voxels visible from few views) receive smaller learning rates, so they do not overfit a handful of samples. The same principle could help any sparse, explicitly parameterized model where coverage is uneven.
- **Initialize to "empty".** Starting densities near zero keeps the solution from being biased toward regions close to the cameras. Choosing a neutral initial state is a cheap way to steer an explicit optimization away from degenerate solutions.
- **Explicit structure where it matters, small networks elsewhere.** A plain grid handles geometry for speed, while a feature grid plus a shallow MLP handles the harder appearance modeling. This hybrid balances speed and expressiveness without a deep network.
- **Coarse-to-fine with a tight bounding box.** First locating the region of interest and allocating resolution only inside it saves memory and compute. This design generalizes to many reconstruction or search problems.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [National Tsing Hua University](https://md.research.elamur.ai/free/en/universities/national-tsing-hua-university/) — University, Hsinchu, Taiwan · 10 works · 1,850 citations
- [Asus](https://md.research.elamur.ai/free/en/companies/asus/) — Company, Taipei, Taiwan · 3 works · 2,674 citations

📚 Shelves (5): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [👁️ Computer Vision and Pattern Recognition](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-vision-and-pattern-recognition/) · 3,486 works · [⚙️ Engineering](https://md.research.elamur.ai/free/en/shelves/engineering/) · 188 works · [🖥️ Computer Graphics and Computer-Aided Design](https://md.research.elamur.ai/free/en/shelves/computer-science/computer-graphics-and-computer-aided-design/) · 16 works · [⚙️ Computational Mechanics](https://md.research.elamur.ai/free/en/shelves/engineering/computational-mechanics/) · 5 works

## Cite

Cite as: Cheng Sun, Min Sun and Hwann-Tzong Chen. 2021. Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction. arXiv:2111.11215.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@misc{sun2021direct,
  title = {{Direct Voxel Grid Optimization: Super-fast Convergence for Radiance Fields Reconstruction}},
  author = {Cheng Sun, Min Sun and Hwann-Tzong Chen},
  year = {2021},
  doi = {10.48550/arxiv.2111.11215},
  eprint = {2111.11215},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.48550/arxiv.2111.11215}
}
```

- [← previous GPT Understands, Too](https://md.research.elamur.ai/free/en/papers/liu-2021-gpt-understands-too/)
- [next → Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://md.research.elamur.ai/free/en/papers/rudin-2021-interpretable-machine-learning-fundamental/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/)

## References

72 references, 1 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Jonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman, Ricardo Martin-Brualla, and Pratul P. Srinivasan. Mip-nerf: A multiscale representation for anti-aliasing neural radiance fields. In ICCV, 2021. 1, 3, 4, 6, 7, 9, 11, 12, 13 [find](https://scholar.google.com/scholar?q=Jonathan+T%2E+Barron%2C+Ben+Mildenhall%2C+Matthew+Tancik%2C+Peter+Hedman%2C+Ricardo+Martin%2DBrualla%2C+and+Pratul+P%2E+Srinivasan%2E+Mip%2Dnerf%3A+A+multiscale+representation+for+anti%2Daliasing+neural+radiance+fields%2E+In+I)
2. Sai Bi, Zexiang Xu, Pratul P. Srinivasan, Ben Mildenhall, Kalyan Sunkavalli, Milos Hasan, Yannick Hold-Geoffroy, David J. Kriegman, and Ravi Ramamoorthi. Neural reflectance fields for appearance acquisition. arxiv CS.CV 2106.01970, 2020. 2 [find](https://scholar.google.com/scholar?q=Sai+Bi%2C+Zexiang+Xu%2C+Pratul+P%2E+Srinivasan%2C+Ben+Mildenhall%2C+Kalyan+Sunkavalli%2C+Milos+Hasan%2C+Yannick+Hold%2DGeoffroy%2C+David+J%2E+Kriegman%2C+and+Ravi+Ramamoorthi%2E+Neural+reflectance+fields+for+appearance+acqui)
3. Mark Boss, Raphael Braun, Varun Jampani, Jonathan T. Barron, Ce Liu, and Hendrik P. A. Lensch. Nerd: Neural reflectance decomposition from image collections. In ICCV, 2021. 2 [find](https://scholar.google.com/scholar?q=Mark+Boss%2C+Raphael+Braun%2C+Varun+Jampani%2C+Jonathan+T%2E+Barron%2C+Ce+Liu%2C+and+Hendrik+P%2E+A%2E+Lensch%2E+Nerd%3A+Neural+reflectance+decomposition+from+image+collections%2E+In+ICCV%2C+2021%2E+2)
4. Chris Buehler, Michael Bosse, Leonard McMillan, Steven J. Gortler, and Michael F. Cohen. Unstructured lumigraph rendering. In SIGGRAPH, 2001. 2 [find](https://scholar.google.com/scholar?q=Chris+Buehler%2C+Michael+Bosse%2C+Leonard+McMillan%2C+Steven+J%2E+Gortler%2C+and+Michael+F%2E+Cohen%2E+Unstructured+lumigraph+rendering%2E+In+SIGGRAPH%2C+2001%2E+2)
5. Eric R. Chan, Marco Monteiro, Petr Kellnhofer, Jiajun Wu, and Gordon Wetzstein. Pi-gan: Periodic implicit generative adversarial networks for 3d-aware image synthesis. In CVPR, 2021. 2 [find](https://scholar.google.com/scholar?q=Eric+R%2E+Chan%2C+Marco+Monteiro%2C+Petr+Kellnhofer%2C+Jiajun+Wu%2C+and+Gordon+Wetzstein%2E+Pi%2Dgan%3A+Periodic+implicit+generative+adversarial+networks+for+3d%2Daware+image+synthesis%2E+In+CVPR%2C+2021%2E+2)
6. Anpei Chen, Zexiang Xu, Fuqiang Zhao, Xiaoshuai Zhang, Fanbo Xiang, Jingyi Yu, and Hao Su. Mvsnerf: Fast generalizable radiance field reconstruction from multi-view stereo. In ICCV, 2021. 1, 3, 7 [find](https://scholar.google.com/scholar?q=Anpei+Chen%2C+Zexiang+Xu%2C+Fuqiang+Zhao%2C+Xiaoshuai+Zhang%2C+Fanbo+Xiang%2C+Jingyi+Yu%2C+and+Hao+Su%2E+Mvsnerf%3A+Fast+generalizable+radiance+field+reconstruction+from+multi%2Dview+stereo%2E+In+ICCV%2C+2021%2E+1%2C+3%2C+7)
7. Abe Davis, Marc Levoy, and Frédo Durand. Unstructured light fields. Comput. Graph. Forum, 2012. 2 [find](https://scholar.google.com/scholar?q=Abe+Davis%2C+Marc+Levoy%2C+and+Fre%CC%81do+Durand%2E+Unstructured+light+fields%2E+Comput%2E+Graph%2E+Forum%2C+2012%2E+2)
8. Paul E. Debevec, Camillo J. Taylor, and Jitendra Malik. Modeling and rendering architecture from photographs: A hybrid geometry- and image-based approach. In SIGGRAPH, 1996. 2 [find](https://scholar.google.com/scholar?q=Paul+E%2E+Debevec%2C+Camillo+J%2E+Taylor%2C+and+Jitendra+Malik%2E+Modeling+and+rendering+architecture+from+photographs%3A+A+hybrid+geometry%2D+and+image%2Dbased+approach%2E+In+SIGGRAPH%2C+1996%2E+2)
9. Boyang Deng, Jonathan T. Barron, and Pratul P. Srinivasan. JaxNeRF: an efficient JAX implementation of NeRF, 2020. 6, 7, 11, 13, 17 [find](https://scholar.google.com/scholar?q=Boyang+Deng%2C+Jonathan+T%2E+Barron%2C+and+Pratul+P%2E+Srinivasan%2E+JaxNeRF%3A+an+efficient+JAX+implementation+of+NeRF%2C+2020%2E+6%2C+7%2C+11%2C+13%2C+17)
10. Kangle Deng, Andrew Liu, Jun-Yan Zhu, and Deva Ramanan. Depth-supervised nerf: Fewer views and faster training for free. arxiv CS.CV 2107.02791, 2021. 1, 3 [find](https://scholar.google.com/scholar?q=Kangle+Deng%2C+Andrew+Liu%2C+Jun%2DYan+Zhu%2C+and+Deva+Ramanan%2E+Depth%2Dsupervised+nerf%3A+Fewer+views+and+faster+training+for+free%2E+arxiv+CS%2ECV+2107%2E02791%2C+2021%2E+1%2C+3)
11. Helisa Dhamo, Keisuke Tateno, Iro Laina, Nassir Navab, and Federico Tombari. Peeking behind objects: Layered depth prediction from a single image. Pattern Recognit. Lett., 2019. 2 [find](https://scholar.google.com/scholar?q=Helisa+Dhamo%2C+Keisuke+Tateno%2C+Iro+Laina%2C+Nassir+Navab%2C+and+Federico+Tombari%2E+Peeking+behind+objects%3A+Layered+depth+prediction+from+a+single+image%2E+Pattern+Recognit%2E+Lett%2E%2C+2019%2E+2)
12. John Flynn, Michael Broxton, Paul E. Debevec, Matthew DuVall, Graham Fyffe, Ryan S. Overbeck, Noah Snavely, and Richard Tucker. Deepview: View synthesis with learned gradient descent. In CVPR, 2019. 2 [find](https://scholar.google.com/scholar?q=John+Flynn%2C+Michael+Broxton%2C+Paul+E%2E+Debevec%2C+Matthew+DuVall%2C+Graham+Fyffe%2C+Ryan+S%2E+Overbeck%2C+Noah+Snavely%2C+and+Richard+Tucker%2E+Deepview%3A+View+synthesis+with+learned+gradient+descent%2E+In+CVPR%2C+2019%2E+2)
13. Guy Gafni, Justus Thies, Michael Zollhöfer, and Matthias Nießner. Dynamic neural radiance fields for monocular 4d facial avatar reconstruction. In CVPR, 2021. 2 [find](https://scholar.google.com/scholar?q=Guy+Gafni%2C+Justus+Thies%2C+Michael+Zollho%CC%88fer%2C+and+Matthias+Nie%C3%9Fner%2E+Dynamic+neural+radiance+fields+for+monocular+4d+facial+avatar+reconstruction%2E+In+CVPR%2C+2021%2E+2)
14. Chen Gao, Ayush Saraf, Johannes Kopf, and Jia-Bin Huang. Dynamic view synthesis from dynamic monocular video. In ICCV, 2021. 2 [find](https://scholar.google.com/scholar?q=Chen+Gao%2C+Ayush+Saraf%2C+Johannes+Kopf%2C+and+Jia%2DBin+Huang%2E+Dynamic+view+synthesis+from+dynamic+monocular+video%2E+In+ICCV%2C+2021%2E+2)
15. Stephan J. Garbin, Marek Kowalski, Matthew Johnson, Jamie Shotton, and Julien P. C. Valentin. Fastnerf: High-fidelity neural rendering at 200fps. In ICCV, 2021. 1, 2, 3, 7, 13 [find](https://scholar.google.com/scholar?q=Stephan+J%2E+Garbin%2C+Marek+Kowalski%2C+Matthew+Johnson%2C+Jamie+Shotton%2C+and+Julien+P%2E+C%2E+Valentin%2E+Fastnerf%3A+High%2Dfidelity+neural+rendering+at+200fps%2E+In+ICCV%2C+2021%2E+1%2C+2%2C+3%2C+7%2C+13)
16. Steven J. Gortler, Radek Grzeszczuk, Richard Szeliski, and Michael F. Cohen. The lumigraph. In SIGGRAPH, 1996. 2 [find](https://scholar.google.com/scholar?q=Steven+J%2E+Gortler%2C+Radek+Grzeszczuk%2C+Richard+Szeliski%2C+and+Michael+F%2E+Cohen%2E+The+lumigraph%2E+In+SIGGRAPH%2C+1996%2E+2)
17. Tong He, John P. Collomosse, Hailin Jin, and Stefano Soatto. Deepvoxels++: Enhancing the fidelity of novel view synthesis from 3d voxel embeddings. In Hiroshi Ishikawa, Cheng-Lin Liu, Tomás Pajdla, and Jianbo Shi, editors, ACCV, 2020. 2, 18 [find](https://scholar.google.com/scholar?q=Tong+He%2C+John+P%2E+Collomosse%2C+Hailin+Jin%2C+and+Stefano+Soatto%2E+Deepvoxels%2B%2B%3A+Enhancing+the+fidelity+of+novel+view+synthesis+from+3d+voxel+embeddings%2E+In+Hiroshi+Ishikawa%2C+Cheng%2DLin+Liu%2C+Toma%CC%81s+Pajdla%2C+a)
18. Peter Hedman, Pratul P. Srinivasan, Ben Mildenhall, Jonathan T. Barron, and Paul E. Debevec. Baking neural radiance fields for real-time view synthesis. In ICCV, 2021. 1, 2, 3, 5, 7, 10, 13 [find](https://scholar.google.com/scholar?q=Peter+Hedman%2C+Pratul+P%2E+Srinivasan%2C+Ben+Mildenhall%2C+Jonathan+T%2E+Barron%2C+and+Paul+E%2E+Debevec%2E+Baking+neural+radiance+fields+for+real%2Dtime+view+synthesis%2E+In+ICCV%2C+2021%2E+1%2C+2%2C+3%2C+5%2C+7%2C+10%2C+13)
19. Yoonwoo Jeong, Seokjun Ahn, Christopher Choy, Animashree Anandkumar, Minsu Cho, and Jaesik Park. Self-calibrating neural radiance fields. In ICCV, 2021. 2 [find](https://scholar.google.com/scholar?q=Yoonwoo+Jeong%2C+Seokjun+Ahn%2C+Christopher+Choy%2C+Animashree+Anandkumar%2C+Minsu+Cho%2C+and+Jaesik+Park%2E+Self%2Dcalibrating+neural+radiance+fields%2E+In+ICCV%2C+2021%2E+2)
20. Diederik P. Kingma and Jimmy Ba. [Adam: A method for stochastic optimization](https://md.research.elamur.ai/free/en/papers/kingma-2014-adam-method-stochastic-optimization/). In ICLR, 2015. 6
21. Arno Knapitsch, Jaesik Park, Qian-Yi Zhou, and Vladlen Koltun. Tanks and temples: benchmarking large-scale scene reconstruction. ACM Trans. Graph., 2017. 6, 11, 12, 17 [find](https://scholar.google.com/scholar?q=Arno+Knapitsch%2C+Jaesik+Park%2C+Qian%2DYi+Zhou%2C+and+Vladlen+Koltun%2E+Tanks+and+temples%3A+benchmarking+large%2Dscale+scene+reconstruction%2E+ACM+Trans%2E+Graph%2E%2C+2017%2E+6%2C+11%2C+12%2C+17)
22. Adam R. Kosiorek, Heiko Strathmann, Daniel Zoran, Pol Moreno, Rosalia Schneider, Sona Mokrá, and Danilo Jimenez Rezende. Nerf-vae: A geometry aware 3d scene generative model. In ICML, 2021. 2 [find](https://scholar.google.com/scholar?q=Adam+R%2E+Kosiorek%2C+Heiko+Strathmann%2C+Daniel+Zoran%2C+Pol+Moreno%2C+Rosalia+Schneider%2C+Sona+Mokra%CC%81%2C+and+Danilo+Jimenez+Rezende%2E+Nerf%2Dvae%3A+A+geometry+aware+3d+scene+generative+model%2E+In+ICML%2C+2021%2E+2)
23. Anat Levin and Frédo Durand. Linear view synthesis using a dimensionality gap light field prior. In CVPR, 2010. 2 [find](https://scholar.google.com/scholar?q=Anat+Levin+and+Fre%CC%81do+Durand%2E+Linear+view+synthesis+using+a+dimensionality+gap+light+field+prior%2E+In+CVPR%2C+2010%2E+2)
24. Marc Levoy and Pat Hanrahan. Light field rendering. In SIGGRAPH, 1996. 2 [find](https://scholar.google.com/scholar?q=Marc+Levoy+and+Pat+Hanrahan%2E+Light+field+rendering%2E+In+SIGGRAPH%2C+1996%2E+2)
25. Zhengqi Li, Simon Niklaus, Noah Snavely, and Oliver Wang. Neural scene flow fields for space-time view synthesis of dynamic scenes. In CVPR, 2021. 2 [find](https://scholar.google.com/scholar?q=Zhengqi+Li%2C+Simon+Niklaus%2C+Noah+Snavely%2C+and+Oliver+Wang%2E+Neural+scene+flow+fields+for+space%2Dtime+view+synthesis+of+dynamic+scenes%2E+In+CVPR%2C+2021%2E+2)
26. Zhengqi Li, Wenqi Xian, Abe Davis, and Noah Snavely. Crowdsampling the plenoptic function. In ECCV, 2020. 2 [find](https://scholar.google.com/scholar?q=Zhengqi+Li%2C+Wenqi+Xian%2C+Abe+Davis%2C+and+Noah+Snavely%2E+Crowdsampling+the+plenoptic+function%2E+In+ECCV%2C+2020%2E+2)
27. Chen-Hsuan Lin, Wei-Chiu Ma, Antonio Torralba, and Simon Lucey. BARF: bundle-adjusting neural radiance fields. In ICCV, 2021. 2 [find](https://scholar.google.com/scholar?q=Chen%2DHsuan+Lin%2C+Wei%2DChiu+Ma%2C+Antonio+Torralba%2C+and+Simon+Lucey%2E+BARF%3A+bundle%2Dadjusting+neural+radiance+fields%2E+In+ICCV%2C+2021%2E+2)
28. Yen-Chen Lin, Pete Florence, Jonathan T. Barron, Alberto Rodriguez, Phillip Isola, and Tsung-Yi Lin. inerf: Inverting neural radiance fields for pose estimation. In IROS, 2021. 2 [find](https://scholar.google.com/scholar?q=Yen%2DChen+Lin%2C+Pete+Florence%2C+Jonathan+T%2E+Barron%2C+Alberto+Rodriguez%2C+Phillip+Isola%2C+and+Tsung%2DYi+Lin%2E+inerf%3A+Inverting+neural+radiance+fields+for+pose+estimation%2E+In+IROS%2C+2021%2E+2)
29. David B. Lindell, Julien N. P. Martel, and Gordon Wetzstein. Autoint: Automatic integration for fast neural volume rendering. In CVPR, 2021. 1, 7, 13 [find](https://scholar.google.com/scholar?q=David+B%2E+Lindell%2C+Julien+N%2E+P%2E+Martel%2C+and+Gordon+Wetzstein%2E+Autoint%3A+Automatic+integration+for+fast+neural+volume+rendering%2E+In+CVPR%2C+2021%2E+1%2C+7%2C+13)
30. Lingjie Liu, Jiatao Gu, Kyaw Zaw Lin, Tat-Seng Chua, and Christian Theobalt. Neural sparse voxel fields. In NeurIPS, 2020. 1, 2, 3, 5, 6, 7, 11, 12, 13, 15, 16, 17 [find](https://scholar.google.com/scholar?q=Lingjie+Liu%2C+Jiatao+Gu%2C+Kyaw+Zaw+Lin%2C+Tat%2DSeng+Chua%2C+and+Christian+Theobalt%2E+Neural+sparse+voxel+fields%2E+In+NeurIPS%2C+2020%2E+1%2C+2%2C+3%2C+5%2C+6%2C+7%2C+11%2C+12%2C+13%2C+15%2C+16%2C+17)
31. Yuan Liu, Sida Peng, Lingjie Liu, Qianqian Wang, Peng Wang, Christian Theobalt, Xiaowei Zhou, and Wenping Wang. Neural rays for occlusion-aware image-based rendering. arxiv CS.CV 2107.13421, 2021. 1, 3, 7, 10 [find](https://scholar.google.com/scholar?q=Yuan+Liu%2C+Sida+Peng%2C+Lingjie+Liu%2C+Qianqian+Wang%2C+Peng+Wang%2C+Christian+Theobalt%2C+Xiaowei+Zhou%2C+and+Wenping+Wang%2E+Neural+rays+for+occlusion%2Daware+image%2Dbased+rendering%2E+arxiv+CS%2ECV+2107%2E13421%2C+2021%2E+1%2C+)
32. Stephen Lombardi, Tomas Simon, Jason M. Saragih, Gabriel Schwartz, Andreas M. Lehrmann, and Yaser Sheikh. Neural volumes: learning dynamic renderable volumes from images. ACM Trans. Graph., 2019. 2, 7, 13, 15, 16, 17, 18 [find](https://scholar.google.com/scholar?q=Stephen+Lombardi%2C+Tomas+Simon%2C+Jason+M%2E+Saragih%2C+Gabriel+Schwartz%2C+Andreas+M%2E+Lehrmann%2C+and+Yaser+Sheikh%2E+Neural+volumes%3A+learning+dynamic+renderable+volumes+from+images%2E+ACM+Trans%2E+Graph%2E%2C+2019%2E+2%2C+7)
33. Ricardo Martin-Brualla, Noha Radwan, Mehdi S. M. Sajjadi, Jonathan T. Barron, Alexey Dosovitskiy, and Daniel Duckworth. Nerf in the wild: Neural radiance fields for unconstrained photo collections. In CVPR, 2021. 2 [find](https://scholar.google.com/scholar?q=Ricardo+Martin%2DBrualla%2C+Noha+Radwan%2C+Mehdi+S%2E+M%2E+Sajjadi%2C+Jonathan+T%2E+Barron%2C+Alexey+Dosovitskiy%2C+and+Daniel+Duckworth%2E+Nerf+in+the+wild%3A+Neural+radiance+fields+for+unconstrained+photo+collections%2E+In)
34. Nelson L. Max. Optical models for direct volume rendering. IEEE Trans. Vis. Comput. Graph., 1995. 3 [find](https://scholar.google.com/scholar?q=Nelson+L%2E+Max%2E+Optical+models+for+direct+volume+rendering%2E+IEEE+Trans%2E+Vis%2E+Comput%2E+Graph%2E%2C+1995%2E+3)
35. Quan Meng, Anpei Chen, Haimin Luo, Minye Wu, Hao Su, Lan Xu, Xuming He, and Jingyi Yu. Gnerf: Gan-based neural radiance field without posed camera. In ICCV, 2021. 2 [find](https://scholar.google.com/scholar?q=Quan+Meng%2C+Anpei+Chen%2C+Haimin+Luo%2C+Minye+Wu%2C+Hao+Su%2C+Lan+Xu%2C+Xuming+He%2C+and+Jingyi+Yu%2E+Gnerf%3A+Gan%2Dbased+neural+radiance+field+without+posed+camera%2E+In+ICCV%2C+2021%2E+2)
36. Ben Mildenhall, Pratul P. Srinivasan, Rodrigo Ortiz Cayon, Nima Khademi Kalantari, Ravi Ramamoorthi, Ren Ng, and Abhishek Kar. Local light field fusion: practical view synthesis with prescriptive sampling guidelines. ACM Trans. Graph., 2019. 2, 18 [find](https://scholar.google.com/scholar?q=Ben+Mildenhall%2C+Pratul+P%2E+Srinivasan%2C+Rodrigo+Ortiz+Cayon%2C+Nima+Khademi+Kalantari%2C+Ravi+Ramamoorthi%2C+Ren+Ng%2C+and+Abhishek+Kar%2E+Local+light+field+fusion%3A+practical+view+synthesis+with+prescriptive+samp)
37. Ben Mildenhall, Pratul P. Srinivasan, Matthew Tancik, Jonathan T. Barron, Ravi Ramamoorthi, and Ren Ng. Nerf: Representing scenes as neural radiance fields for view synthesis. In ECCV, 2020. 1, 2, 3, 5, 6, 7, 9, 11, 12, 13, 14, 15, 16, 17, 18 [find](https://scholar.google.com/scholar?q=Ben+Mildenhall%2C+Pratul+P%2E+Srinivasan%2C+Matthew+Tancik%2C+Jonathan+T%2E+Barron%2C+Ravi+Ramamoorthi%2C+and+Ren+Ng%2E+Nerf%3A+Representing+scenes+as+neural+radiance+fields+for+view+synthesis%2E+In+ECCV%2C+2020%2E+1%2C+2%2C+3%2C+)
38. Atsuhiro Noguchi, Xiao Sun, Stephen Lin, and Tatsuya Harada. Neural articulated radiance field. In ICCV, 2021. 2 [find](https://scholar.google.com/scholar?q=Atsuhiro+Noguchi%2C+Xiao+Sun%2C+Stephen+Lin%2C+and+Tatsuya+Harada%2E+Neural+articulated+radiance+field%2E+In+ICCV%2C+2021%2E+2)
39. Michael Oechsle, Songyou Peng, and Andreas Geiger. UNISURF: unifying neural implicit surfaces and radiance fields for multi-view reconstruction. In ICCV, 2021. 9 [find](https://scholar.google.com/scholar?q=Michael+Oechsle%2C+Songyou+Peng%2C+and+Andreas+Geiger%2E+UNISURF%3A+unifying+neural+implicit+surfaces+and+radiance+fields+for+multi%2Dview+reconstruction%2E+In+ICCV%2C+2021%2E+9)
40. Keunhong Park, Utkarsh Sinha, Jonathan T. Barron, Sofien Bouaziz, Dan B. Goldman, Steven M. Seitz, and Ricardo Martin-Brualla. Deformable neural radiance fields. In ICCV, 2021. 2 [find](https://scholar.google.com/scholar?q=Keunhong+Park%2C+Utkarsh+Sinha%2C+Jonathan+T%2E+Barron%2C+Sofien+Bouaziz%2C+Dan+B%2E+Goldman%2C+Steven+M%2E+Seitz%2C+and+Ricardo+Martin%2DBrualla%2E+Deformable+neural+radiance+fields%2E+In+ICCV%2C+2021%2E+2)
41. Keunhong Park, Utkarsh Sinha, Peter Hedman, Jonathan T. Barron, Sofien Bouaziz, Dan B. Goldman, Ricardo Martin-Brualla, and Steven M. Seitz. Hypernerf: A higher-dimensional representation for topologically varying neural radiance fields. arxiv CS.CV 2106.13228, 2021. 2 [find](https://scholar.google.com/scholar?q=Keunhong+Park%2C+Utkarsh+Sinha%2C+Peter+Hedman%2C+Jonathan+T%2E+Barron%2C+Sofien+Bouaziz%2C+Dan+B%2E+Goldman%2C+Ricardo+Martin%2DBrualla%2C+and+Steven+M%2E+Seitz%2E+Hypernerf%3A+A+higher%2Ddimensional+representation+for+topologi)
42. Albert Pumarola, Enric Corona, Gerard Pons-Moll, and Francesc Moreno-Noguer. D-nerf: Neural radiance fields for dynamic scenes. In CVPR, 2021. 2 [find](https://scholar.google.com/scholar?q=Albert+Pumarola%2C+Enric+Corona%2C+Gerard+Pons%2DMoll%2C+and+Francesc+Moreno%2DNoguer%2E+D%2Dnerf%3A+Neural+radiance+fields+for+dynamic+scenes%2E+In+CVPR%2C+2021%2E+2)
43. Daniel Rebain, Wei Jiang, Soroosh Yazdani, Ke Li, Kwang Moo Yi, and Andrea Tagliasacchi. Derf: Decomposed radiance fields. In CVPR, 2021. 1 [find](https://scholar.google.com/scholar?q=Daniel+Rebain%2C+Wei+Jiang%2C+Soroosh+Yazdani%2C+Ke+Li%2C+Kwang+Moo+Yi%2C+and+Andrea+Tagliasacchi%2E+Derf%3A+Decomposed+radiance+fields%2E+In+CVPR%2C+2021%2E+1)
44. Christian Reiser, Songyou Peng, Yiyi Liao, and Andreas Geiger. Kilonerf: Speeding up neural radiance fields with thousands of tiny mlps. In ICCV, 2021. 1, 3, 7, 13, 15, 16, 17 [find](https://scholar.google.com/scholar?q=Christian+Reiser%2C+Songyou+Peng%2C+Yiyi+Liao%2C+and+Andreas+Geiger%2E+Kilonerf%3A+Speeding+up+neural+radiance+fields+with+thousands+of+tiny+mlps%2E+In+ICCV%2C+2021%2E+1%2C+3%2C+7%2C+13%2C+15%2C+16%2C+17)
45. Katja Schwarz, Yiyi Liao, Michael Niemeyer, and Andreas Geiger. GRAF: generative radiance fields for 3d-aware image synthesis. In NeurIPS, 2020. 2 [find](https://scholar.google.com/scholar?q=Katja+Schwarz%2C+Yiyi+Liao%2C+Michael+Niemeyer%2C+and+Andreas+Geiger%2E+GRAF%3A+generative+radiance+fields+for+3d%2Daware+image+synthesis%2E+In+NeurIPS%2C+2020%2E+2)
46. Jonathan Shade, Steven J. Gortler, Li-wei He, and Richard Szeliski. Layered depth images. In SIGGRAPH, 1998. 2 [find](https://scholar.google.com/scholar?q=Jonathan+Shade%2C+Steven+J%2E+Gortler%2C+Li%2Dwei+He%2C+and+Richard+Szeliski%2E+Layered+depth+images%2E+In+SIGGRAPH%2C+1998%2E+2)
47. Lixin Shi, Haitham Hassanieh, Abe Davis, Dina Katabi, and Frédo Durand. Light field reconstruction using sparsity in the continuous fourier domain. ACM Trans. Graph., 2014. 2 [find](https://scholar.google.com/scholar?q=Lixin+Shi%2C+Haitham+Hassanieh%2C+Abe+Davis%2C+Dina+Katabi%2C+and+Fre%CC%81do+Durand%2E+Light+field+reconstruction+using+sparsity+in+the+continuous+fourier+domain%2E+ACM+Trans%2E+Graph%2E%2C+2014%2E+2)
48. Meng-Li Shih, Shih-Yang Su, Johannes Kopf, and Jia-Bin Huang. 3d photography using context-aware layered depth inpainting. In CVPR, 2020. 2 [find](https://scholar.google.com/scholar?q=Meng%2DLi+Shih%2C+Shih%2DYang+Su%2C+Johannes+Kopf%2C+and+Jia%2DBin+Huang%2E+3d+photography+using+context%2Daware+layered+depth+inpainting%2E+In+CVPR%2C+2020%2E+2)
49. Vincent Sitzmann, Justus Thies, Felix Heide, Matthias Nießner, Gordon Wetzstein, and Michael Zollhöfer. Deepvoxels: Learning persistent 3d feature embeddings. In CVPR, 2019. 2, 6, 11, 12, 18 [find](https://scholar.google.com/scholar?q=Vincent+Sitzmann%2C+Justus+Thies%2C+Felix+Heide%2C+Matthias+Nie%C3%9Fner%2C+Gordon+Wetzstein%2C+and+Michael+Zollho%CC%88fer%2E+Deepvoxels%3A+Learning+persistent+3d+feature+embeddings%2E+In+CVPR%2C+2019%2E+2%2C+6%2C+11%2C+12%2C+18)
50. Vincent Sitzmann, Michael Zollhöfer, and Gordon Wetzstein. Scene representation networks: Continuous 3d-structure-aware neural scene representations. In NeurIPS, 2019. 7, 13, 15, 16, 17, 18 [find](https://scholar.google.com/scholar?q=Vincent+Sitzmann%2C+Michael+Zollho%CC%88fer%2C+and+Gordon+Wetzstein%2E+Scene+representation+networks%3A+Continuous+3d%2Dstructure%2Daware+neural+scene+representations%2E+In+NeurIPS%2C+2019%2E+7%2C+13%2C+15%2C+16%2C+17%2C+18)
51. Pratul P. Srinivasan, Boyang Deng, Xiuming Zhang, Matthew Tancik, Ben Mildenhall, and Jonathan T. Barron. Nerv: Neural reflectance and visibility fields for relighting and view synthesis. In CVPR, 2021. 2 [find](https://scholar.google.com/scholar?q=Pratul+P%2E+Srinivasan%2C+Boyang+Deng%2C+Xiuming+Zhang%2C+Matthew+Tancik%2C+Ben+Mildenhall%2C+and+Jonathan+T%2E+Barron%2E+Nerv%3A+Neural+reflectance+and+visibility+fields+for+relighting+and+view+synthesis%2E+In+CVPR%2C+202)
52. Pratul P. Srinivasan, Richard Tucker, Jonathan T. Barron, Ravi Ramamoorthi, Ren Ng, and Noah Snavely. Pushing the boundaries of view extrapolation with multiplane images. In CVPR, 2019. 2 [find](https://scholar.google.com/scholar?q=Pratul+P%2E+Srinivasan%2C+Richard+Tucker%2C+Jonathan+T%2E+Barron%2C+Ravi+Ramamoorthi%2C+Ren+Ng%2C+and+Noah+Snavely%2E+Pushing+the+boundaries+of+view+extrapolation+with+multiplane+images%2E+In+CVPR%2C+2019%2E+2)
53. Matthew Tancik, Ben Mildenhall, Terrance Wang, Divi Schmidt, Pratul P. Srinivasan, Jonathan T. Barron, and Ren Ng. Learned initializations for optimizing coordinate-based neural representations. In CVPR, 2021. 2 [find](https://scholar.google.com/scholar?q=Matthew+Tancik%2C+Ben+Mildenhall%2C+Terrance+Wang%2C+Divi+Schmidt%2C+Pratul+P%2E+Srinivasan%2C+Jonathan+T%2E+Barron%2C+and+Ren+Ng%2E+Learned+initializations+for+optimizing+coordinate%2Dbased+neural+representations%2E+In+CV)
54. Matthew Tancik, Pratul P. Srinivasan, Ben Mildenhall, Sara Fridovich-Keil, Nithin Raghavan, Utkarsh Singhal, Ravi Ramamoorthi, Jonathan T. Barron, and Ren Ng. Fourier features let networks learn high frequency functions in low dimensional domains. In NeurIPS, 2020. 3 [find](https://scholar.google.com/scholar?q=Matthew+Tancik%2C+Pratul+P%2E+Srinivasan%2C+Ben+Mildenhall%2C+Sara+Fridovich%2DKeil%2C+Nithin+Raghavan%2C+Utkarsh+Singhal%2C+Ravi+Ramamoorthi%2C+Jonathan+T%2E+Barron%2C+and+Ren+Ng%2E+Fourier+features+let+networks+learn+high+)
55. Justus Thies, Michael Zollhöfer, and Matthias Nießner. Deferred neural rendering: image synthesis using neural textures. ACM Trans. Graph., 2019. 2 [find](https://scholar.google.com/scholar?q=Justus+Thies%2C+Michael+Zollho%CC%88fer%2C+and+Matthias+Nie%C3%9Fner%2E+Deferred+neural+rendering%3A+image+synthesis+using+neural+textures%2E+ACM+Trans%2E+Graph%2E%2C+2019%2E+2)
56. Edgar Tretschk, Ayush Tewari, Vladislav Golyanik, Michael Zollhöfer, Christoph Lassner, and Christian Theobalt. Non-rigid neural radiance fields: Reconstruction and novel view synthesis of a deforming scene from monocular video. In ICCV, 2021. 2 [find](https://scholar.google.com/scholar?q=Edgar+Tretschk%2C+Ayush+Tewari%2C+Vladislav+Golyanik%2C+Michael+Zollho%CC%88fer%2C+Christoph+Lassner%2C+and+Christian+Theobalt%2E+Non%2Drigid+neural+radiance+fields%3A+Reconstruction+and+novel+view+synthesis+of+a+deformin)
57. Richard Tucker and Noah Snavely. Single-view view synthesis with multiplane images. In CVPR, 2020. 2 [find](https://scholar.google.com/scholar?q=Richard+Tucker+and+Noah+Snavely%2E+Single%2Dview+view+synthesis+with+multiplane+images%2E+In+CVPR%2C+2020%2E+2)
58. Shubham Tulsiani, Richard Tucker, and Noah Snavely. Layer-structured 3d scene inference via view synthesis. In ECCV, 2018. 2 [find](https://scholar.google.com/scholar?q=Shubham+Tulsiani%2C+Richard+Tucker%2C+and+Noah+Snavely%2E+Layer%2Dstructured+3d+scene+inference+via+view+synthesis%2E+In+ECCV%2C+2018%2E+2)
59. Michael Waechter, Nils Moehrle, and Michael Goesele. Let there be color! large-scale texturing of 3d reconstructions. In ECCV, 2014. 2 [find](https://scholar.google.com/scholar?q=Michael+Waechter%2C+Nils+Moehrle%2C+and+Michael+Goesele%2E+Let+there+be+color%21+large%2Dscale+texturing+of+3d+reconstructions%2E+In+ECCV%2C+2014%2E+2)
60. Qianqian Wang, Zhicheng Wang, Kyle Genova, Pratul P. Srinivasan, Howard Zhou, Jonathan T. Barron, Ricardo Martin-Brualla, Noah Snavely, and Thomas A. Funkhouser. Ibrnet: Learning multi-view image-based rendering. In CVPR, 2021. 1, 3, 7, 18 [find](https://scholar.google.com/scholar?q=Qianqian+Wang%2C+Zhicheng+Wang%2C+Kyle+Genova%2C+Pratul+P%2E+Srinivasan%2C+Howard+Zhou%2C+Jonathan+T%2E+Barron%2C+Ricardo+Martin%2DBrualla%2C+Noah+Snavely%2C+and+Thomas+A%2E+Funkhouser%2E+Ibrnet%3A+Learning+multi%2Dview+image%2Dbase)
61. Zhou Wang, Alan C. Bovik, Hamid R. Sheikh, and Eero P. Simoncelli. Image quality assessment: from error visibility to structural similarity. IEEE TIP, 2004. 6 [find](https://scholar.google.com/scholar?q=Zhou+Wang%2C+Alan+C%2E+Bovik%2C+Hamid+R%2E+Sheikh%2C+and+Eero+P%2E+Simoncelli%2E+Image+quality+assessment%3A+from+error+visibility+to+structural+similarity%2E+IEEE+TIP%2C+2004%2E+6)
62. Zirui Wang, Shangzhe Wu, Weidi Xie, Min Chen, and Victor Adrian Prisacariu. Nerf-: Neural radiance fields without known camera parameters. arxiv CS.CV 2102.07064, 2021. 2 [find](https://scholar.google.com/scholar?q=Zirui+Wang%2C+Shangzhe+Wu%2C+Weidi+Xie%2C+Min+Chen%2C+and+Victor+Adrian+Prisacariu%2E+Nerf%2D%3A+Neural+radiance+fields+without+known+camera+parameters%2E+arxiv+CS%2ECV+2102%2E07064%2C+2021%2E+2)
63. Suttisak Wizadwongsa, Pakkapon Phongthawee, Jiraphon Yenphraphai, and Supasorn Suwajanakorn. Nex: Real-time view synthesis with neural basis expansion. In CVPR, 2021. 2, 3, 10 [find](https://scholar.google.com/scholar?q=Suttisak+Wizadwongsa%2C+Pakkapon+Phongthawee%2C+Jiraphon+Yenphraphai%2C+and+Supasorn+Suwajanakorn%2E+Nex%3A+Real%2Dtime+view+synthesis+with+neural+basis+expansion%2E+In+CVPR%2C+2021%2E+2%2C+3%2C+10)
64. Daniel N. Wood, Daniel I. Azuma, Ken Aldinger, Brian Curless, Tom Duchamp, David Salesin, and Werner Stuetzle. Surface light fields for 3d photography. In SIGGRAPH, 2000. 2 [find](https://scholar.google.com/scholar?q=Daniel+N%2E+Wood%2C+Daniel+I%2E+Azuma%2C+Ken+Aldinger%2C+Brian+Curless%2C+Tom+Duchamp%2C+David+Salesin%2C+and+Werner+Stuetzle%2E+Surface+light+fields+for+3d+photography%2E+In+SIGGRAPH%2C+2000%2E+2)
65. Wenqi Xian, Jia-Bin Huang, Johannes Kopf, and Changil Kim. Space-time neural irradiance fields for free-viewpoint video. In CVPR, 2021. 2 [find](https://scholar.google.com/scholar?q=Wenqi+Xian%2C+Jia%2DBin+Huang%2C+Johannes+Kopf%2C+and+Changil+Kim%2E+Space%2Dtime+neural+irradiance+fields+for+free%2Dviewpoint+video%2E+In+CVPR%2C+2021%2E+2)
66. Yao Yao, Zixin Luo, Shiwei Li, Jingyang Zhang, Yufan Ren, Lei Zhou, Tian Fang, and Long Quan. Blendedmvs: A large-scale dataset for generalized multi-view stereo networks. In CVPR, 2020. 6, 11, 12, 16 [find](https://scholar.google.com/scholar?q=Yao+Yao%2C+Zixin+Luo%2C+Shiwei+Li%2C+Jingyang+Zhang%2C+Yufan+Ren%2C+Lei+Zhou%2C+Tian+Fang%2C+and+Long+Quan%2E+Blendedmvs%3A+A+large%2Dscale+dataset+for+generalized+multi%2Dview+stereo+networks%2E+In+CVPR%2C+2020%2E+6%2C+11%2C+12%2C+16)
67. Alex Yu, Ruilong Li, Matthew Tancik, Hao Li, Ren Ng, and Angjoo Kanazawa. Plenoctrees for real-time rendering of neural radiance fields. In ICCV, 2021. 1, 2, 3, 5, 7, 10, 11, 13, 17 [find](https://scholar.google.com/scholar?q=Alex+Yu%2C+Ruilong+Li%2C+Matthew+Tancik%2C+Hao+Li%2C+Ren+Ng%2C+and+Angjoo+Kanazawa%2E+Plenoctrees+for+real%2Dtime+rendering+of+neural+radiance+fields%2E+In+ICCV%2C+2021%2E+1%2C+2%2C+3%2C+5%2C+7%2C+10%2C+11%2C+13%2C+17)
68. Alex Yu, Vickie Ye, Matthew Tancik, and Angjoo Kanazawa. pixelnerf: Neural radiance fields from one or few images. In CVPR, 2021. 3 [find](https://scholar.google.com/scholar?q=Alex+Yu%2C+Vickie+Ye%2C+Matthew+Tancik%2C+and+Angjoo+Kanazawa%2E+pixelnerf%3A+Neural+radiance+fields+from+one+or+few+images%2E+In+CVPR%2C+2021%2E+3)
69. Kai Zhang, Gernot Riegler, Noah Snavely, and Vladlen Koltun. Nerf++: Analyzing and improving neural radiance fields. arxiv CS.CV 2010.07492, 2020. 3 [find](https://scholar.google.com/scholar?q=Kai+Zhang%2C+Gernot+Riegler%2C+Noah+Snavely%2C+and+Vladlen+Koltun%2E+Nerf%2B%2B%3A+Analyzing+and+improving+neural+radiance+fields%2E+arxiv+CS%2ECV+2010%2E07492%2C+2020%2E+3)
70. Richard Zhang, Phillip Isola, Alexei A. Efros, Eli Shechtman, and Oliver Wang. The unreasonable effectiveness of deep features as a perceptual metric. In CVPR, 2018. 6 [find](https://scholar.google.com/scholar?q=Richard+Zhang%2C+Phillip+Isola%2C+Alexei+A%2E+Efros%2C+Eli+Shechtman%2C+and+Oliver+Wang%2E+The+unreasonable+effectiveness+of+deep+features+as+a+perceptual+metric%2E+In+CVPR%2C+2018%2E+6)
71. Xiuming Zhang, Pratul P. Srinivasan, Boyang Deng, Paul E. Debevec, William T. Freeman, and Jonathan T. Barron. Nerfactor: Neural factorization of shape and reflectance under an unknown illumination. arxiv CS.CV 2106.01970, 2021. 2 [find](https://scholar.google.com/scholar?q=Xiuming+Zhang%2C+Pratul+P%2E+Srinivasan%2C+Boyang+Deng%2C+Paul+E%2E+Debevec%2C+William+T%2E+Freeman%2C+and+Jonathan+T%2E+Barron%2E+Nerfactor%3A+Neural+factorization+of+shape+and+reflectance+under+an+unknown+illumination%2E+a)
72. Tinghui Zhou, Richard Tucker, John Flynn, Graham Fyffe, and Noah Snavely. Stereo magnification: learning view synthesis using multiplane images. ACM Trans. Graph., 2018. 2 [find](https://scholar.google.com/scholar?q=Tinghui+Zhou%2C+Richard+Tucker%2C+John+Flynn%2C+Graham+Fyffe%2C+and+Noah+Snavely%2E+Stereo+magnification%3A+learning+view+synthesis+using+multiplane+images%2E+ACM+Trans%2E+Graph%2E%2C+2018%2E+2)

*Updated 2 November 2026*