As a common image editing operation, image composition aims to combine the foreground
from one image and another background image, resulting in a composite image. However …

The fidelity of relighting is bounded by both geometry and appearance representations. For
geometry both mesh and volumetric approaches have difficulty modeling intricate structures …

Given a portrait image of a person and an environment map of the target lighting, portrait
relighting aims to re-illuminate the person in the image as if the person appeared in an …

Image matting refers to extracting precise alpha matte from natural images, and it plays a
critical role in various downstream applications, such as image editing. Despite being an ill …

The two-hand interaction is one of the most challenging signals to analyze due to the self-
similarity, complicated articulations, and occlusions of hands. Although several datasets …

High-quality HDRIs (High Dynamic Range Images), typically HDR panoramas, are one of
the most popular ways to create photorealistic lighting and 360-degree reflections of 3D …

Human relighting is a highly desirable yet challenging task. Existing works either require
expensive one-light-at-a-time (OLAT) captured data using light stage or cannot freely …

We present a new lighting estimation and editing framework to generate high-dynamic-
range (HDR) indoor panorama lighting from a single limited field-of-view (LFOV) image …

This paper tackles the problem of creating relightable and animatable neural avatars from
sparse-view (or monocular) videos of dynamic humans under unknown illumination …

Recent work on radiance fields and volumetric inverse rendering (eg, NeRFs) has provided
excellent results in building data-driven models of real scenes for novel view synthesis with …