English
Related papers

Related papers: DynaFLIP: Rethinking Robotics Perception via Tri-M…

200 papers

Large-scale vision 2D vision language models, such as CLIP can be aligned with a 3D encoder to learn generalizable (open-vocabulary) 3D vision models. However, current methods require supervised pre-training for such alignment, and the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-17 Amaya Dharmasiri , Muzammal Naseer , Salman Khan , Fahad Shahbaz Khan

Visual representations play a crucial role in developing generalist robotic policies. Previous vision encoders, typically pre-trained with single-image reconstruction or two-image contrastive learning, tend to capture static information,…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Yucheng Hu , Yanjiang Guo , Pengchao Wang , Xiaoyu Chen , Yen-Jen Wang , Jianke Zhang , Koushil Sreenath , Chaochao Lu , Jianyu Chen

Neural face avatars that are trained from multi-view data captured in camera domes can produce photo-realistic 3D reconstructions. However, at inference time, they must be driven by limited inputs such as partial views recorded by…

Computer Vision and Pattern Recognition · Computer Science 2022-03-16 Emre Aksan , Shugao Ma , Akin Caliskan , Stanislav Pidhorskyi , Alexander Richard , Shih-En Wei , Jason Saragih , Otmar Hilliges

Visual language models like Contrastive Language-Image Pretraining (CLIP) have shown impressive performance in analyzing natural images with language information. However, these models often encounter challenges when applied to specialized…

Computer Vision and Pattern Recognition · Computer Science 2024-12-11 Jiaqing Zhang , Mingxiang Cao , Xue Yang , Kai Jiang , Yunsong Li

A key challenge in scaling up robot learning to many skills and environments is removing the need for human supervision, so that robots can collect their own data and improve their own performance without being limited by the cost of…

Machine Learning · Computer Science 2017-03-14 Chelsea Finn , Sergey Levine

Manipulation of deformable objects, such as ropes and cloth, is an important but challenging problem in robotics. We present a learning-based system where a robot takes as input a sequence of images of a human manipulating a rope from an…

Computer Vision and Pattern Recognition · Computer Science 2017-03-07 Ashvin Nair , Dian Chen , Pulkit Agrawal , Phillip Isola , Pieter Abbeel , Jitendra Malik , Sergey Levine

Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robotic manipulation, leveraging large-scale pre-training to achieve strong performance. The field has rapidly evolved with additional spatial…

Robotics · Computer Science 2026-02-23 Yuankai Luo , Woping Chen , Tong Liang , Baiqiao Wang , Zhenguo Li

Existing imitation learning methods enable robots to interact autonomously with the physical environment. However, contact-rich manipulation tasks remain a significant challenge due to complex contact dynamics that demand high-precision…

Transductive zero-shot learning with vision-language models leverages image-image similarities within the dataset to achieve better classification accuracy compared to the inductive setting. However, there is little work that explores the…

Computer Vision and Pattern Recognition · Computer Science 2025-10-15 Oindrila Saha , Logan Lawrence , Grant Van Horn , Subhransu Maji

Appearance of dressed humans undergoes a complex geometric transformation induced not only by the static pose but also by its dynamics, i.e., there exists a number of cloth geometric configurations given a pose depending on the way it has…

Computer Vision and Pattern Recognition · Computer Science 2022-03-25 Jae Shin Yoon , Duygu Ceylan , Tuanfeng Y. Wang , Jingwan Lu , Jimei Yang , Zhixin Shu , Hyun Soo Park

Imitation learning from human motion capture (MoCap) data provides a promising way to train humanoid robots. However, due to differences in morphology, such as varying degrees of joint freedom and force limits, exact replication of human…

Robotics · Computer Science 2024-10-04 Wenshuai Zhao , Yi Zhao , Joni Pajarinen , Michael Muehlebach

We study how visual representations pre-trained on diverse human video data can enable data-efficient learning of downstream robotic manipulation tasks. Concretely, we pre-train a visual representation using the Ego4D human video dataset…

Robotics · Computer Science 2022-11-21 Suraj Nair , Aravind Rajeswaran , Vikash Kumar , Chelsea Finn , Abhinav Gupta

Building robots that can automate labor-intensive tasks has long been the core motivation behind the advancements in computer vision and the robotics community. Recent interest in leveraging 3D algorithms, particularly neural fields, has…

Computer Vision and Pattern Recognition · Computer Science 2023-12-13 Litian Liang , Liuyu Bian , Caiwei Xiao , Jialin Zhang , Linghao Chen , Isabella Liu , Fanbo Xiang , Zhiao Huang , Hao Su

Since current Vision-Language-Action (VLA) systems suffer from limited spatial perception and the absence of memory throughout manipulation, we investigate visual anchors as a means to enhance spatial and temporal reasoning within VLA…

Robotics · Computer Science 2026-03-16 Juan Zhu , Zhanying Shao , Xiaoqi Li , Ethan Morgan , Jiadong Xu , Hongwei Fan , Hao Dong

Learning a generalizable bimanual manipulation policy is extremely challenging for embodied agents due to the large action space and the need for coordinated arm movements. Existing approaches rely on Vision-Language-Action (VLA) models to…

Computer Vision and Pattern Recognition · Computer Science 2025-06-02 Chenyou Fan , Fangzheng Yan , Chenjia Bai , Jiepeng Wang , Chi Zhang , Zhen Wang , Xuelong Li

We explore a novel method to perceive and manipulate 3D articulated objects that generalizes to enable a robot to articulate unseen classes of objects. We propose a vision-based system that learns to predict the potential motions of the…

Robotics · Computer Science 2024-05-03 Ben Eisner , Harry Zhang , David Held

The limited scale of current 3D shape datasets hinders the advancements in 3D shape understanding, and motivates multi-modal learning approaches which transfer learned knowledge from data-abundant 2D image and language modalities to 3D…

Computer Vision and Pattern Recognition · Computer Science 2024-04-03 Zhihao Zhang , Shengcao Cao , Yu-Xiong Wang

The ability to successfully grasp objects is crucial in robotics, as it enables several interactive downstream applications. To this end, most approaches either compute the full 6D pose for the object of interest or learn to predict a set…

Learning visuomotor control policies in robotic systems is a fundamental problem when aiming for long-term behavioral autonomy. Recent supervised-learning-based vision and motion perception systems, however, are often separately built with…

Robotics · Computer Science 2020-06-17 Marvin Chancán , Michael Milford

Continuum robots possess high flexibility and redundancy, making them well suited for safe interaction in complex environments, yet their continuous deformation and nonlinear dynamics pose fundamental challenges to perception, modeling, and…

Robotics · Computer Science 2026-03-03 Peng Yu , Xin Wang , Ning Tan