Diffusion models have emerged as the best approach for generative modeli...
We introduce 3inGAN, an unconditional 3D generative model trained from 2...
Scalable generation of furniture layouts is essential for many applicati...
Triangle meshes remain the most popular data representation for surface
...
We investigate the problem of training generative models on a very spars...
Computer-aided design (CAD) is the most widely used modeling approach fo...
We propose an unsupervised segmentation framework for StyleGAN generated...
Recent years have seen a proliferation of new digital products for the
e...
We present a method for reconstructing triangle meshes from point clouds...
Humans regularly interact with their surrounding objects. Such interacti...
We investigate the problem of learning to generate 3D parametric surface...
High-quality, diverse, and photorealistic images can now be generated by...
We present RELATE, a model that learns to generate physically plausible
...
We present BlockGAN, an image generative model that learns object-aware ...
Learning to encode differences in the geometry and (topological) structu...
The ability to generate novel, diverse, and realistic 3D shapes along wi...
We develop PlatonicGAN to discover 3D structure of an object class from ...
In this paper, we address the recent controversy between Lipschitz
regul...
While learning models of intuitive physics is an increasingly active are...
Urban facade segmentation from automatically acquired imagery, in contra...
While the basic laws of Newtonian mechanics are well understood, explain...
Discovering 3D arrangements of objects from single indoor images is impo...
While the basic laws of Newtonian mechanics are well understood, explain...
The paper addresses the following problem: given a set of man-made shape...
We consider the problem of establishing dense correspondences within a s...
Humans describe images in terms of nouns and adjectives while algorithms...