We present a spatial and angular Gaussian based representation and a triple splatting
process, for real-time, high-quality novel lighting-and-view synthesis from multi-view point-lit …

We present ZeroComp, an effective zero-shot 3D object compositing approach that does not
require paired composite-scene images during training. Our method leverages ControlNet to …

Understanding and modeling lighting effects are fundamental tasks in computer vision and
graphics. Classic physically-based rendering (PBR) accurately simulates the light transport …

Reconstructing the geometry and appearance of objects from photographs taken in different
environments is difficult as the illumination and therefore the object appearance vary across …

Recent image-to-video generation methods have demonstrated success in enabling control
over one or two visual elements, such as camera trajectory or object motion. However, these …

Recent work has shown that diffusion models can be used as powerful neural rendering
engines that can be leveraged for inserting virtual objects into images. Unlike typical physics …

We introduce LumiNet, a novel architecture that leverages generative models and latent
intrinsic representations for effective lighting transfer. Given a source image and a target …

In this paper, we propose a novel end-to-end relightable neural inverse rendering system
that achieves high-quality reconstruction of geometry and material properties, thus enabling …

Image-based relighting of indoor rooms creates an immersive virtual understanding of the
space, which is useful for interior design, virtual staging, and real estate. Relighting indoor …

Multi-source face relighting is a key challenge in computer vision due to its applications in
virtual reality, face recognition, and image editing, yet existing methods struggle with lighting …