We introduce differentiable indirection – a novel learned primitive that...
We propose a physically-motivated deep learning framework to solve a gen...
Most indoor 3D scene reconstruction methods focus on recovering 3D geome...
Real-world applications require a robot operating in the physical world ...
Indoor scenes exhibit significant appearance variations due to myriad
in...
We present a method to edit complex indoor lighting from a single image ...
Recently neural volumetric representations such as neural reflectance fi...
Large-scale photorealistic datasets of indoor scenes, with ground truth
...
Recovering the 3D shape of transparent objects using a small number of
u...
We propose a deep inverse rendering framework for indoor scenes. From a
...
We propose a material acquisition approach to recover the spatially-vary...