paper-with-me

Papers

Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulation

2024-09-24 · Homanga Bharadhwaj, Debidatta Dwibedi, Abhinav Gupta, Shubham Tulsiani, Carl Doersch, Ted Xiao, Dhruv Shah, Fei Xia, Dorsa Sadigh, Sean Kirmani

How can robot manipulation policies generalize to novel tasks involving unseen object types and new motions? In this paper, we provide a solution in terms of predicting motion information from web data through human video generation and conditioning a robot policy on the generated video. Instead of attempting to scale robot data collection which is expensive, we show how we can leverage video generation models trained on easily available web data, for enabling generalization. Our approach Gen2Act casts language-conditioned manipulation as zero-shot human video generation followed by execution with a single policy conditioned on the generated video. To train the policy, we use an order of magnitude less robot interaction data compared to what the video prediction model was trained on. Gen2Act doesn't require fine-tuning the video model at all and we directly use a pre-trained model for generating human videos. Our results on diverse real-world scenarios show how Gen2Act enables manipulating unseen object types and performing novel motions for tasks not present in the robot data. Videos are at https://homangab.github.io/gen2act/

📄 PDF Abstract BibTeX arXiv:2409.16283

Code (0)

등록된 구현이 없습니다.

Tasks

Robot ManipulationVideo GenerationVideo Prediction

Similar Papers 제목 키워드 기반

Mitty: Diffusion-based Human-to-Robot Video Generation

2025-12-19 · Yiren Song, Cheng Liu, Weijia Mao, Mike Zheng Shou arxiv

Learning directly from human demonstration videos is a key milestone toward scalable and generalizable robot learning. Yet existing methods rely on intermediate representations such as keypoints or trajectories, introduc…

Video Generation

Exploring the Role of Synthetic Data Augmentation in Controllable Human-Centric Video Generation

2026-04-23 · Yuanchen Fei, Yude Zou, Zejian Kang, Ming Li 외 arxiv

Controllable human video generation aims to produce realistic videos of humans with explicitly guided motions and appearances,serving as a foundation for digital humans, animation, and embodied AI.However, the scarcity o…

Data AugmentationVideo Generation

Generalizable task representation learning from human demonstration videos: a geometric approach

2022-02-28 · Jun Jin, Martin Jagersand

We study the problem of generalizable task learning from human demonstration videos without extra training on the robot or pre-recorded robot motions. Given a set of human demonstration videos showing a task with differe…

Representation Learning

iVS-Net: Learning Human View Synthesis from Internet Videos

2023-01-01 · ICCV 2023 1 · Junting Dong, Qi Fang, Tianshuo Yang, Qing Shuai 외

Recent advances in implicit neural representations make it possible to generate free-viewpoint videos of the human from sparse view images. To avoid the expensive training for each person, previous methods adopt the …

VQQA: An Agentic Approach for Video Evaluation and Quality Improvement

2026-03-12 · Yiwen Song, Tomas Pfister, Yale Song arxiv

Despite rapid advancements in video generation models, aligning their outputs with complex user intent remains challenging. Existing test-time optimization methods are typically either computationally expensive or requir…

Question AnsweringVideo Generation