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

In this work, we address the problem of jointly estimating albedo, normals, depth and 3D
spatially-varying lighting from a single image. Most existing methods formulate the task as …

Smoke has semi-transparency property leading to highly complicated mixture of background
and smoke. Sparse or small smoke is visually inconspicuous, and its boundary is often …

We explore the zero-shot setting for day-night domain adaptation. The traditional domain
adaptation setting is to train on one domain and adapt to the target domain by exploiting …

Scene appearance changes drastically throughout the day. Existing semantic segmentation
methods mainly focus on well-lit daytime scenarios and are not well designed to cope with …

Intrinsic decomposition is a fundamental mid-level vision problem that plays a crucial role in
various inverse rendering and computational photography pipelines. Generating highly …

Intrinsic image decomposition is the process of recovering the image formation components
(reflectance and shading) from an image. Previous methods employ either explicit priors to …

Image synthesis designed for machine learning applications provides the means to
efficiently generate large quantities of training data while controlling the generation process …

Most prior semantic segmentation methods have been developed for day-time scenes, while
typically underperforming in night-time scenes due to insufficient and complicated lighting …

Intrinsic image decomposition, ie, decomposing a natural image into a reflectance image
and a shading image, is used in many augmented reality applications for achieving better …