Fast Inverse Rendering by Unified Voxelization of Scene Representation

Shuang Wu, Songlin Tang, Guangming Lu, Jianzhuang Liu, Wenjie Pei

Primary Area: representation learning for computer vision, audio, language, and other modalities

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Keywords: Inverse Rendering, Neural Rendering, Explicit Scene Representation Learning, Volumetric Representation

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

TL;DR: We propose a fast inverse rendering method by explicit voxelization of scenes, which allows for efficient modeling of geometry, materials and illumination jointly, thereby reducing the optimization time significantly ( from hours to 18 minutes).

Abstract: Typical inverse rendering methods focus on learning implicit neural scene representations by modeling the geometry, materials and illumination separately, which entails significant computations for optimization. In this work we design a Unified Voxelization framework for explicit learning of scene representations, dubbed UniVoxel, which allows for efficient modeling of the geometry, materials and illumination, thereby accelerating the inverse rendering substantially. To be specific, we propose to encode a scene into a latent volumetric representation, based on which the geometry, materials and illumination can be readily learned via lightweight neural networks in a unified manner. Particularly, we leverage Spherical Gaussians to represent the incident light radiance, which enables the seamless integration of modeling illumination into the unified voxelization framework. Extensive experiments on multiple benchmarks covering diverse scenes demonstrate that UniVoxel boosts the optimization efficiency significantly compared to other inverse rendering methods, reducing the per-scene training time from hours to 18 minutes, while achieving favorable reconstruction quality. Code will be released.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2483