6 citations · 32 across the 25 of their papers we have counts for
25 papers
Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution
Zixin Jessie Chen, Zhuo Chen, Archer Wang +4
Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as r…
DeepShapeMatchingKit: Accelerated Functional Map Solver and Shape Matching Pipelines Revisited
Yizheng Xie, Lennart Bastian, Congyue Deng +3
Deep functional maps, leveraging learned feature extractors and spectral correspondence solvers, are fundamental to non-rigid 3D shape matching. Based on an analysis of open-source…
RINO: Rotation-Invariant Non-Rigid Correspondences
Maolin Gao, Shao Jie Hu-Chen, Congyue Deng +3
Dense 3D shape correspondence remains a central challenge in computer vision and graphics as many deep learning approaches still rely on intermediate geometric features or handcraf…
Rodrigues Network for Learning Robot Actions
Jialiang Zhang, Haoran Geng, Yang You +4
Understanding and predicting articulated actions is important in robot learning. However, common architectures such as MLPs and Transformers lack inductive biases that reflect the…
Denoising Hamiltonian Network for Physical Reasoning
Congyue Deng, Brandon Y. Feng, Cecilia Garraffo +5
Machine learning frameworks for physical problems must capture and enforce physical constraints that preserve the structure of dynamical systems. Many existing approaches achieve t…
Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning
Yang You, Yixin Li, Congyue Deng +2
Vision foundation models, particularly the ViT family, have revolutionized image understanding by providing rich semantic features. However, despite their success in 2D comprehensi…
Neural Attention Field: Emerging Point Relevance in 3D Scenes for One-Shot Dexterous Grasping
Qianxu Wang, Congyue Deng, Tyler Ga Wei Lum +5
One-shot transfer of dexterous grasps to novel scenes with object and context variations has been a challenging problem. While distilled feature fields from large vision models hav…
D3RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation
Songlin Wei, Haoran Geng, Jiayi Chen +6
Depth sensing is an important problem for 3D vision-based robotics. Yet, a real-world active stereo or ToF depth camera often produces noisy and incomplete depth which bottlenecks…
PhysPart: Physically Plausible Part Completion for Interactable Objects
Rundong Luo, Haoran Geng, Congyue Deng +5
Interactable objects are ubiquitous in our daily lives. Recent advances in 3D generative models make it possible to automate the modeling of these objects, benefiting a range of ap…
RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation
Yuxuan Kuang, Junjie Ye, Haoran Geng +5
This work proposes a retrieve-and-transfer framework for zero-shot robotic manipulation, dubbed RAM, featuring generalizability across various objects, environments, and embodiment…
EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning
Jingyun Yang, Zi-ang Cao, Congyue Deng +3
Building effective imitation learning methods that enable robots to learn from limited data and still generalize across diverse real-world environments is a long-standing problem i…
Zero-Shot Image Feature Consensus with Deep Functional Maps
Xinle Cheng, Congyue Deng, Adam Harley +2
Correspondences emerge from large-scale vision models trained for generative and discriminative tasks. This has been revealed and benchmarked by computing correspondence maps betwe…
SAGE: Bridging Semantic and Actionable Parts for GEneralizable Manipulation of Articulated Objects
Haoran Geng, Songlin Wei, Congyue Deng +3
To interact with daily-life articulated objects of diverse structures and functionalities, understanding the object parts plays a central role in both user instruction comprehensio…
Rethinking Directional Integration in Neural Radiance Fields
Congyue Deng, Jiawei Yang, Leonidas Guibas +1
Recent works use the Neural radiance field (NeRF) to perform multi-view 3D reconstruction, providing a significant leap in rendering photorealistic scenes. However, despite its eff…
Make a Donut: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools
Yang You, Bokui Shen, Congyue Deng +4
Deformable object manipulation stands as one of the most captivating yet formidable challenges in robotics. While previous techniques have predominantly relied on learning latent d…
SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
Qianxu Wang, Haotong Zhang, Congyue Deng +4
Humans demonstrate remarkable skill in transferring manipulation abilities across objects of varying shapes, poses, and appearances, a capability rooted in their understanding of s…
EquivAct: SIM(3)-Equivariant Visuomotor Policies beyond Rigid Object Manipulation
Jingyun Yang, Congyue Deng, Jimmy Wu +3
If a robot masters folding a kitchen towel, we would expect it to master folding a large beach towel. However, existing policy learning methods that rely on data augmentation still…
Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance
Congyue Deng, Jiahui Lei, Bokui Shen +2
Equivariance has gained strong interest as a desirable network property that inherently ensures robust generalization. However, when dealing with complex systems such as articulate…
NAP: Neural 3D Articulation Prior
Jiahui Lei, Congyue Deng, Bokui Shen +2
We propose Neural 3D Articulation Prior (NAP), the first 3D deep generative model to synthesize 3D articulated object models. Despite the extensive research on generating 3D object…
EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision
Jiahui Lei, Congyue Deng, Karl Schmeckpeper +2
We introduce Equivariant Neural Field Expectation Maximization (EFEM), a simple, effective, and robust geometric algorithm that can segment objects in 3D scenes without annotations…
NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
Congyue Deng, Chiyu "Max'' Jiang, Charles R. Qi +4
2D-to-3D reconstruction is an ill-posed problem, yet humans are good at solving this problem due to their prior knowledge of the 3D world developed over years. Driven by this obser…
Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks
Sidhika Balachandar, Adrien Poulenard, Congyue Deng +1
Equivariant networks have been adopted in many 3-D learning areas. Here we identify a fundamental limitation of these networks: their ambiguity to symmetries. Equivariant networks…
Orientation-Aware Graph Neural Networks for Protein Structure Representation Learning
Jiahan Li, Shitong Luo, Congyue Deng +5
By folding into particular 3D structures, proteins play a key role in living beings. To learn meaningful representation from a protein structure for downstream tasks, not only the…
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
Congyue Deng, Or Litany, Yueqi Duan +3
Invariance and equivariance to the rotation group have been widely discussed in the 3D deep learning community for pointclouds. Yet most proposed methods either use complex mathema…