CoDe-NeRF: Neural Rendering via Dynamic Coefficient Decomposition

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xing, Wenpeng, Chen, Jie, Yang, Zaifeng, Zhao, Tiancheng, Li, Gaolei, Lin, Changting, Guo, Yike, Han, Meng
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918120677965824
author Xing, Wenpeng
Chen, Jie
Yang, Zaifeng
Zhao, Tiancheng
Li, Gaolei
Lin, Changting
Guo, Yike
Han, Meng
author_facet Xing, Wenpeng
Chen, Jie
Yang, Zaifeng
Zhao, Tiancheng
Li, Gaolei
Lin, Changting
Guo, Yike
Han, Meng
contents Neural Radiance Fields (NeRF) have shown impressive performance in novel view synthesis, but challenges remain in rendering scenes with complex specular reflections and highlights. Existing approaches may produce blurry reflections due to entanglement between lighting and material properties, or encounter optimization instability when relying on physically-based inverse rendering. In this work, we present a neural rendering framework based on dynamic coefficient decomposition, aiming to improve the modeling of view-dependent appearance. Our approach decomposes complex appearance into a shared, static neural basis that encodes intrinsic material properties, and a set of dynamic coefficients generated by a Coefficient Network conditioned on view and illumination. A Dynamic Radiance Integrator then combines these components to synthesize the final radiance. Experimental results on several challenging benchmarks suggest that our method can produce sharper and more realistic specular highlights compared to existing techniques. We hope that this decomposition paradigm can provide a flexible and effective direction for modeling complex appearance in neural scene representations.
format Preprint
id arxiv_https___arxiv_org_abs_2508_06632
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CoDe-NeRF: Neural Rendering via Dynamic Coefficient Decomposition
Xing, Wenpeng
Chen, Jie
Yang, Zaifeng
Zhao, Tiancheng
Li, Gaolei
Lin, Changting
Guo, Yike
Han, Meng
Computer Vision and Pattern Recognition
Artificial Intelligence
Neural Radiance Fields (NeRF) have shown impressive performance in novel view synthesis, but challenges remain in rendering scenes with complex specular reflections and highlights. Existing approaches may produce blurry reflections due to entanglement between lighting and material properties, or encounter optimization instability when relying on physically-based inverse rendering. In this work, we present a neural rendering framework based on dynamic coefficient decomposition, aiming to improve the modeling of view-dependent appearance. Our approach decomposes complex appearance into a shared, static neural basis that encodes intrinsic material properties, and a set of dynamic coefficients generated by a Coefficient Network conditioned on view and illumination. A Dynamic Radiance Integrator then combines these components to synthesize the final radiance. Experimental results on several challenging benchmarks suggest that our method can produce sharper and more realistic specular highlights compared to existing techniques. We hope that this decomposition paradigm can provide a flexible and effective direction for modeling complex appearance in neural scene representations.
title CoDe-NeRF: Neural Rendering via Dynamic Coefficient Decomposition
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2508.06632