Summary of Illuminerf: 3d Relighting Without Inverse Rendering, by Xiaoming Zhao et al.
IllumiNeRF: 3D Relighting Without Inverse Rendering
by Xiaoming Zhao, Pratul P. Srinivasan, Dor Verbin, Keunhong Park, Ricardo Martin Brualla, Philipp Henzler
First submitted to arxiv on: 10 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Graphics (cs.GR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed method for relightable view synthesis uses a simpler approach than existing inverse rendering methods. It involves first relighting each input image using an image diffusion model conditioned on target environment lighting and estimated object geometry, and then reconstructing a Neural Radiance Field (NeRF) with these relit images to render novel views under the target lighting. The method achieves state-of-the-art results on multiple relighting benchmarks. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper proposes a new way to create 3D models from pictures taken in different lighting conditions. Instead of trying to figure out what’s inside each picture, it first makes each picture look like it was taken with the same lighting as the target image. Then, it uses these “relit” images to build a 3D model that can be used to create new views under any lighting condition. |
Keywords
» Artificial intelligence » Diffusion model
