Uni-IR: Ambiguity-Reduced Inverse Rendering through a Unified Framework for Glossy Objects

Wenhang Ge

Keywords: Inverse rendering, physically based rendering

Abstract:

Inverse rendering aims to decompose the an image into geometry, materials, and lighting.
Recently, Neural Radiance Fields (NeRF) based inverse rendering has significantly advanced, bridging the gap between NeRF-based models and conventional rendering engines.
Existing methods typically adopt a two-stage optimization approach, beginning with volume rendering for geometry reconstruction, followed by physically based rendering (PBR) for materials and lighting estimation.
However, the inherent ambiguity between materials and lighting during PBR and the suboptimal nature of geometry reconstruction by volume rendering only compromise the outcomes.
To address these challenges, we introduce Uni-IR, a unified framework that imposes mutual constraints to alleviate ambiguity by integrating volume rendering and physically based rendering.
Specifically, we employ a physically-based volume rendering (PBVR) approach that incorporates PBR concepts into volume rendering, directly facilitating connections with materials and lighting, in addition to geometry. Both rendering methods are utilized during optimization, imposing mutual constraints and optimizing geometry, materials, and lighting synergistically. Employing a meticulously crafted unified representation for both lighting and materials, Uni-IR achieves high-quality geometry reconstruction, materials and lighting estimation across various object types.

Primary Area: applications to 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.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

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: 2332