paper-with-me

홈 › Papers

Stem-OB: Generalizable Visual Imitation Learning with Stem-Like Convergent Observation through Diffusion Inversion

2024-11-07 · Kaizhe Hu, Zihang Rui, Yao He, Yuyao Liu, Pu Hua, Huazhe Xu

Visual imitation learning methods demonstrate strong performance, yet they lack generalization when faced with visual input perturbations, including variations in lighting and textures, impeding their real-world application. We propose Stem-OB that utilizes pretrained image diffusion models to suppress low-level visual differences while maintaining high-level scene structures. This image inversion process is akin to transforming the observation into a shared representation, from which other observations stem, with extraneous details removed. Stem-OB contrasts with data-augmentation approaches as it is robust to various unspecified appearance changes without the need for additional training. Our method is a simple yet highly effective plug-and-play solution. Empirical results confirm the effectiveness of our approach in simulated tasks and show an exceptionally significant improvement in real-world applications, with an average increase of 22.2% in success rates compared to the best baseline. See https://hukz18.github.io/Stem-Ob/ for more info.

📄 PDF Abstract BibTeX arXiv:2411.04919

Code (1)

hukz18/Stem-Ob-Code 공식 구현 pytorch

Tasks

Data AugmentationImitation Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Task-Relevant and Irrelevant Region-Aware Augmentation for Generalizable Vision-Based Imitation Learning in Agricultural Manipulation

2026-03-05 · Shun Hattori, Hikaru Sasaki, Takumi Hachimine, Yusuke Mizutani 외 arxiv

Vision-based imitation learning has shown promise for robotic manipulation; however, its generalization remains limited in practical agricultural tasks. This limitation stems from scarce demonstration data and substantia…

OmniHarness: Harnessing Generalizable Visual Generation via Symbolic Policy Learning

2026-09-13 · Xu Xu, Jinxiu Liu, Zhangbo Qiao, Jiaxing Lu 외 hf

Unified multimodal large language models (MLLMs) and multi-agent systems have advanced visual generation. However, three limitations remain. (1) Existing methods often distill task-specific experience with limited genera…

Enhancing Generalizable 6D Pose Tracking of an In-Hand Object with Tactile Sensing

2022-10-08 · Yun Liu, Xiaomeng Xu, Weihang Chen, Haocheng Yuan 외

When manipulating an object to accomplish complex tasks, humans rely on both vision and touch to keep track of the object's 6D pose. However, most existing object pose tracking systems in robotics rely exclusively on vis…

hand-object poseObjectPose Tracking

VLBiMan: Vision-Language Anchored One-Shot Demonstration Enables Generalizable Bimanual Robotic Manipulation

2025-09-26 · Huayi Zhou, Kui Jia arxiv

Achieving generalizable bimanual manipulation requires systems that can learn efficiently from minimal human input while adapting to real-world uncertainties and diverse embodiments. Existing approaches face a dilemma: i…

Semantic Parsing

AVI-Bench: Toward Human-like Audio-Visual Intelligence of Omni-MLLMs

2026-06-01 · Yaoting Wang, Ziyi Zhang, Wenming Tu, Shaoxuan Xu 외 arxiv

Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their audio-visual intelligence (AVI) remains insufficiently evaluated due to…