Search Results for author:
Found 15 papers, 5 papers with code
PhysPart: Physically Plausible Part Completion for Interactable Objects
We also demonstrate our applications in 3D printing, robot manipulation, and sequential part generation, showing our strength in realistic tasks with the demand for high physical plausibility.
RAM: Retrieval-Based Affordance Transfer for Generalizable Zero-Shot Robotic Manipulation
First, RAM extracts unified affordance at scale from diverse sources of demonstrations including robotic data, human-object interaction (HOI) data, and custom data to construct a comprehensive affordance memory.
EquiBot: SIM(3)-Equivariant Diffusion Policy for Generalizable and Data Efficient Learning
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 in robot learning.
Zero-Shot Image Feature Consensus with Deep Functional Maps
We demonstrate that our technique yields correspondences that are not only smoother but also more accurate, with the possibility of better reflecting the knowledge embedded in the large-scale vision models that we are studying.
Denoising Vision Transformers
In the second stage, we train a lightweight transformer block to predict clean features from raw ViT outputs, leveraging the derived estimates of the clean features as supervision.
SAGE: Bridging Semantic and Actionable Parts for GEneralizable Manipulation of Articulated Objects
More concretely, given an articulated object, we first observe all the semantic parts on it, conditioned on which an instruction interpreter proposes possible action programs that concretize the natural language instruction.
Rethinking Directional Integration in Neural Radiance Fields
To that end, we introduce a modification to the NeRF rendering equation which is as simple as a few lines of code change for any NeRF variations, while greatly improving the rendering quality of view-dependent effects.
Make a Donut: Hierarchical EMD-Space Planning for Zero-Shot Deformable Manipulation with Tools
Remarkably, our model demonstrates robust generalization capabilities to novel and previously unencountered complex tasks without any preliminary demonstrations.
SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
Central to SparseDFF is a feature refinement network, optimized with a contrastive loss between views and a point-pruning mechanism for feature continuity.
NAP: Neural 3D Articulation Prior
We propose Neural 3D Articulation Prior (NAP), the first 3D deep generative model to synthesize 3D articulated object models.
EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision
First, we introduce equivariant shape representations to this problem to eliminate the complexity induced by the variation in object configuration.
NeRDi: Single-View NeRF Synthesis with Language-Guided Diffusion as General Image Priors
Formulating single-view reconstruction as an image-conditioned 3D generation problem, we optimize the NeRF representations by minimizing a diffusion loss on its arbitrary view renderings with a pretrained image diffusion model under the input-view constraint.
Breaking the Symmetry: Resolving Symmetry Ambiguities in Equivariant Neural Networks
We present OAVNN: Orientation Aware Vector Neuron Network, an extension of the Vector Neuron Network.
Vector Neurons: A General Framework for SO(3)-Equivariant Networks
Invariance and equivariance to the rotation group have been widely discussed in the 3D deep learning community for pointclouds.
Alternating ConvLSTM: Learning Force Propagation with Alternate State Updates
Experimental results show that Alt-ConvLSTM efficiently models the material kinetic features and greatly outperforms vanilla ConvLSTM with only the single state update.
