1.2k citations · 1.3k across the 24 of their papers we have counts for
7 papers · 1 filter
Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields
Rohith Agaram, Shaurya Dewan, Rahul Sajnani +3
Coordinate-based implicit neural networks, or neural fields, have emerged as useful representations of shape and appearance in 3D computer vision. Despite advances, however, it rem…
CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language
Aditya Sanghi, Rao Fu, Vivian Liu +5
Recent works have demonstrated that natural language can be used to generate and edit 3D shapes. However, these methods generate shapes with limited fidelity and diversity. We intr…
ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model
Rao Fu, Xiao Zhan, Yiwen Chen +2
We present ShapeCrafter, a neural network for recursive text-conditioned 3D shape generation. Existing methods to generate text-conditioned 3D shapes consume an entire text prompt…
Unsupervised Kinematic Motion Detection for Part-segmented 3D Shape Collections
Xianghao Xu, Yifan Ruan, Srinath Sridhar +1
3D models of manufactured objects are important for populating virtual worlds and for synthetic data generation for vision and robotics. To be most useful, such objects should be a…
NeuralODF: Learning Omnidirectional Distance Fields for 3D Shape Representation
Trevor Houchens, Cheng-You Lu, Shivam Duggal +2
In visual computing, 3D geometry is represented in many different forms including meshes, point clouds, voxel grids, level sets, and depth images. Each representation is suited for…
Learning Body-Aware 3D Shape Generative Models
Bryce Blinn, Alexander Ding, R. Kenny Jones +3
The shape of many objects in the built environment is dictated by their relationships to the human body: how will a person interact with this object? Existing data-driven generativ…
ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes
Rahul Sajnani, Adrien Poulenard, Jivitesh Jain +3
Progress in 3D object understanding has relied on manually canonicalized shape datasets that contain instances with consistent position and orientation (3D pose). This has made it…