9 papers
Learning Expressive Priors for Generalization and Uncertainty Estimation in Neural Networks
Dominik Schnaus, Jongseok Lee, Daniel Cremers +1
In this work, we propose a novel prior learning method for advancing generalization and uncertainty estimation in deep neural networks. The key idea is to exploit scalable and stru…
SPIRIT: Perceptive Shared Autonomy for Robust Robotic Manipulation under Deep Learning Uncertainty
Jongseok Lee, Ribin Balachandran, Harsimran Singh +6
Deep learning (DL) has enabled impressive advances in robotic perception, yet its limited robustness and lack of interpretability hinder reliable deployment in safety critical appl…
Evaluating Latent Generative Paradigms for High-Fidelity 3D Shape Completion from a Single Depth Image
Matthias Humt, Ulrich Hillenbrand, Rudolph Triebel
While generative models have seen significant adoption across a wide range of data modalities, including 3D data, a consensus on which model is best suited for which task has yet t…
Human-Interpretable Uncertainty Explanations for Point Cloud Registration
Johannes A. Gaus, Loris Schneider, Yitian Shi +3
In this paper, we address the point cloud registration problem, where well-known methods like ICP fail under uncertainty arising from sensor noise, pose-estimation errors, and part…
FFHFlow: Diverse and Uncertainty-Aware Dexterous Grasp Generation via Flow Variational Inference
Qian Feng, Jianxiang Feng, Zhaopeng Chen +2
Synthesizing diverse, uncertainty-aware grasps for multi-fingered hands from partial observations remains a critical challenge in robot learning. Prior generative methods struggle…
Conditional Latent Diffusion Models for Zero-Shot Instance Segmentation
Maximilian Ulmer, Wout Boerdijk, Rudolph Triebel +1
This paper presents OC-DiT, a novel class of diffusion models designed for object-centric prediction, and applies it to zero-shot instance segmentation. We propose a conditional la…