Programs are an increasingly popular representation for visual data, exp...
Representing a 3D shape with a set of primitives can aid perception of
s...
Language is one of the primary means by which we describe the 3D world a...
We present ShapeCrafter, a neural network for recursive text-conditioned...
3D models of manufactured objects are important for populating virtual w...
We present SHRED, a method for 3D SHape REgion Decomposition. SHRED take...
Question answering (QA) is a fundamental means to facilitate assessment ...
Despite its benefits for children's skill development and parent-child
b...
The shape of many objects in the built environment is dictated by their
...
Realistic 3D indoor scene datasets have enabled significant recent progr...
We present the Shape Part Slot Machine, a new method for assembling nove...
Manipulating an articulated object requires perceiving itskinematic
hier...
Many learning-based 3D shape semantic segmentation methods assign labels...
A popular way to create detailed yet easily controllable 3D shapes is vi...
In computer-aided design (CAD), the ability to "reverse engineer" the
mo...
Reconstructing object geometry and material from multiple views typicall...
Inferring programs which generate 2D and 3D shapes is important for reve...
Manually authoring 3D shapes is difficult and time consuming; generative...
We present a new, fast and flexible pipeline for indoor scene synthesis ...
Unsupervised image-to-image translation techniques are able to map local...
We introduce ScanComplete, a novel data-driven approach for taking an
in...
Neural autoregressive models are explicit density estimators that achiev...
We introduce a model that learns to convert simple hand drawings into
gr...
Probabilistic programming languages (PPLs) are a powerful modeling tool,...
Probabilistic inference algorithms such as Sequential Monte Carlo (SMC)
...
Lightweight, source-to-source transformation approaches to implementing ...