7 papers
GraspGen-X: Cross-Embodiment 6-DOF Diffusion-based Grasping
Beining Han, Yu-Wei Chao, Erwin Coumans +5
We study cross-embodiment 6-DOF robot grasping. Unlike prior works, we require the model not only to generalize to novel objects / scenes but also to novel gripper morphologies and…
What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?
David Yan, Alexander Raistrick, Jia Deng
Synthetic datasets are a crucial ingredient for training stereo matching networks, but the question of what makes a stereo dataset effective remains underexplored. We investigate t…
Toward A Better Understanding of Monocular Depth Evaluation
Siyang Wu, Jack Nugent, Willow Yang +1
Monocular depth estimation is an important task with rapid progress, but how to evaluate it is not fully resolved, as evidenced by a lack of standardization in existing literature…
Procedural Generation of Articulated Simulation-Ready Assets
Abhishek Joshi, Beining Han, Jack Nugent +12
We introduce Infinigen-Articulated, a toolkit for generating realistic, procedurally generated articulated assets for robotics simulation. We include procedural generators for 18 c…
Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations
Jack Nugent, Siyang Wu, Zeyu Ma +7
Recent years have witnessed substantial progress on monocular depth estimation, particularly as measured by the success of large models on standard benchmarks. However, performance…
Zero-shot Sim2Real Transfer for Magnet-Based Tactile Sensor on Insertion Tasks
Beining Han, Abhishek Joshi, Jia Deng
Tactile sensing is an important sensing modality for robot manipulation. Among different types of tactile sensors, magnet-based sensors, like u-skin, balance well between high dura…