Authoring high-quality digital materials is key to realism in 3D renderi...
Programs are an increasingly popular representation for visual data, exp...
Node graph systems are used ubiquitously for material design in computer...
Representing a 3D shape with a set of primitives can aid perception of
s...
Diffusion models have shown great promise for image generation, beating ...
Diffusion models currently achieve state-of-the-art performance for both...
Finding an unsupervised decomposition of an image into individual object...
Neural representations are popular for representing shapes, as they can ...
Graph-based procedural materials are ubiquitous in content production
in...
Procedural material graphs are a compact, parameteric, and
resolution-in...
Despite the ubiquitousness of materials maps in modern rendering pipelin...
Recent methods (e.g. MaterialGAN) have used unconditional GANs to genera...
Scalable generation of furniture layouts is essential for many applicati...
This work is concerned with a representation of shapes that disentangles...
We present the Shape Part Slot Machine, a new method for assembling nove...
Triangle meshes remain the most popular data representation for surface
...
Computer-aided design (CAD) is the most widely used modeling approach fo...
A popular way to create detailed yet easily controllable 3D shapes is vi...
We present a method for reconstructing triangle meshes from point clouds...
We propose a new generative model for layout generation. We generate lay...
Patterns, which are collections of elements arranged in regular or
near-...
Manually authoring 3D shapes is difficult and time consuming; generative...
We investigate the problem of learning to generate 3D parametric surface...
A key step in any scanning-based asset creation workflow is to convert
u...
Learning to encode differences in the geometry and (topological) structu...
The ability to generate novel, diverse, and realistic 3D shapes along wi...
Point clouds obtained with 3D scanners or by image-based reconstruction
...
A long-standing challenge in scene analysis is the recovery of scene
arr...
Coarse building mass models are now routinely generated at scales rangin...
In this paper, we propose a deep-learning based approach for estimating ...
In the context of scene understanding, a variety of methods exists to
es...
As humans, we regularly interpret images based on the relations between ...