Log In Sign Up

NeRD: Neural Reflectance Decomposition from Image Collections

by   Mark Boss, et al.

Decomposing a scene into its shape, reflectance, and illumination is a challenging but essential problem in computer vision and graphics. This problem is inherently more challenging when the illumination is not a single light source under laboratory conditions but is instead an unconstrained environmental illumination. Though recent work has shown that implicit representations can be used to model the radiance field of an object, these techniques only enable view synthesis and not relighting. Additionally, evaluating these radiance fields is resource and time-intensive. By decomposing a scene into explicit representations, any rendering framework can be leveraged to generate novel views under any illumination in real-time. NeRD is a method that achieves this decomposition by introducing physically-based rendering to neural radiance fields. Even challenging non-Lambertian reflectances, complex geometry, and unknown illumination can be decomposed into high-quality models. The datasets and code is available on the project page:


page 1

page 6

page 7

page 8

page 10

page 11

page 16

page 17


Neural-PIL: Neural Pre-Integrated Lighting for Reflectance Decomposition

Decomposing a scene into its shape, reflectance and illumination is a fu...

SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections

Inverse rendering of an object under entirely unknown capture conditions...

Neural Radiance Transfer Fields for Relightable Novel-view Synthesis with Global Illumination

Given a set of images of a scene, the re-rendering of this scene from no...

IntrinsicNeRF: Learning Intrinsic Neural Radiance Fields for Editable Novel View Synthesis

We present intrinsic neural radiance fields, dubbed IntrinsicNeRF, that ...

DeRF: Decomposed Radiance Fields

With the advent of Neural Radiance Fields (NeRF), neural networks can no...

Fast Training of Neural Lumigraph Representations using Meta Learning

Novel view synthesis is a long-standing problem in machine learning and ...

Scene Inference for Object Illumination Editing

The seamless illumination integration between a foreground object and a ...