DeepAI AI Chat
Log In Sign Up

A Neural Rendering Framework for Free-Viewpoint Relighting

by   Zhang Chen, et al.

We present a novel Relightable Neural Renderer (RNR) for simultaneous view synthesis and relighting using multi-view image inputs. Existing neural rendering (NR) does not explicitly model the physical rendering process and hence has limited capabilities on relighting. RNR instead models image formation in terms of environment lighting, object intrinsic attributes, and the light transport function (LTF), each corresponding to a learnable component. In particular, the incorporation of a physically based rendering process not only enables relighting but also improves the quality of novel view synthesis. Comprehensive experiments on synthetic and real data show that RNR provides a practical and effective solution for conducting free-viewpoint relighting.


page 1

page 3

page 6

page 7

page 8


Appearance Editing with Free-viewpoint Neural Rendering

We present a neural rendering framework for simultaneous view synthesis ...

Improving NeRF Quality by Progressive Camera Placement for Unrestricted Navigation in Complex Environments

Neural Radiance Fields, or NeRFs, have drastically improved novel view s...

IGNOR: Image-guided Neural Object Rendering

We propose a new learning-based novel view synthesis approach for scanne...

SteerNeRF: Accelerating NeRF Rendering via Smooth Viewpoint Trajectory

Neural Radiance Fields (NeRF) have demonstrated superior novel view synt...

Non-Linear Phase-Shifting of Haar Wavelets for Run-Time All-Frequency Lighting

This paper focuses on real-time all-frequency image-based rendering usin...

Viewpoint Selection for Photographing Architectures

This paper studies the problem of how to choose good viewpoints for taki...

Code Repositories


Our work presents a novel neural rendering approach that can efficiently reconstruct geometric and neural radiance fields for view synthesis.

view repo


A Neural Rendering Framework for Free-Viewpoint Relighting (CVPR 2020)

view repo