Reconstruction and intrinsic decomposition of scenes from captured imagery would enable
many applications such as relighting and virtual object insertion. Recent NeRF based …

We present a learning-based method for synthesizingnovel views of complex scenes using
only unstructured collections of in-the-wild photographs. We build on Neural Radiance …

Existing inverse rendering combined with neural rendering methods can only perform
editable novel view synthesis on object-specific scenes, while we present intrinsic neural …

Recent work has made significant progress on using implicit functions, as a continuous
representation for 3D rigid object shape reconstruction. However, much less effort has been …

We introduce Stanford-ORB, a new real-world 3D Object inverse Rendering Benchmark.
Recent advances in inverse rendering have enabled a wide range of real-world applications …

This paper presents a novel method for exerting fine-grained lighting control during text-
driven diffusion-based image generation. While existing diffusion models already have the …

Relighting radiance fields is severely underconstrained for multi‐view data, which is most
often captured under a single illumination condition; It is especially hard for full scenes …

Estimating the reflectance layer from a single image is a challenging task. It becomes more
challenging when the input image contains shadows or specular highlights, which often …

A light stage uses a series of calibrated cameras and lights to capture a subject's facial
appearance under varying illumination and viewpoint. This captured information is crucial …

Abstract We present Video Autoencoder for learning disentangled representations of 3D
structure and camera pose from videos in a self-supervised manner. Relying on temporal …