Active Vision

Follow this topic Ask about this topic

Latest papers

21 papers6 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Look Before You Act: Bridging Active Perception and Vision-Language-Action Models via Observation-Aligned Data Adaptation
Oct 16, 2026Jiawei Geng, Zhenyang Liu, Yuzheng Wu +2Active Vision for Robot Manipulation VLA Model Adaptation
Fudan University · Shanghai Innovation Institute
VP-EVT: Active Visibility Preservation for Embodied Visual Tracking
Oct 15, 2026Yanci Wen, Tianle Zeng, Jianwei Peng +3Active Vision Visual Object Tracking
Shenzhen Key Laboratory of Robotics and Computer Vision, Southern University of Science and Technology, Shenzhen, China. · Southern University of Science and Technology, Shenzhen, China. · Tencent Robotics X, Shenzhen, China.
EyeRobot 2.0: Active Gaze for Precise Manipulation without Wrist Cameras
Oct 2, 2026Kush Hari, Justin Kerr, Nidhya Shivakumar +7Active Vision for Robot Manipulation Active Vision
UC Berkeley · Amazon FAR · Stanford University
ActiveWAM: Evidence-Aware Active Vision for World-Action Models
Oct 1, 2026Renjun Wu, Luzhou Ge, Xuesong LiWorld Action Models Multi-Task Robotic Manipulation
Beijing Institute of Technology
Recovering the View: Benchmarking Physical Active Vision for Occlusion Recovery in Robotic Manipulation
Sep 29, 2026Kaijun Luo, Yudi Huang, Qijun Zhong +3Robot Manipulation Benchmarks Active Vision for Robot Manipulation
Sun Yat-sen University · University of Electronic Science and Technology of China · X-Era AI Lab +1
MAAP: Multi-Agent Active Perception for Collaborative Manipulation
Sep 18, 2026Bruno N. Y. Chen, Li Kang, Heng Zhou +4Active Vision for Robot Manipulation Robotic Manipulation
Carnegie Mellon University · Shanghai Jiao Tong University · University of Science and Technology of China +3
INSPECT: Learning Robot View Selection from Assistant Use
Sep 17, 2026Di Wen, Kailun Yang, Wenhao Guo +7Active Perception Robotic Inspection
Karlsruhe Institute of Technology, Karlsruhe 76131, Germany · Hunan University, Changsha 410012, China · Independent Researcher
LEAP: Learning Emergent Active Perception for Quadruped Navigation
Sep 15, 2026Ü. Bora Gökbakan, Stéphane Caron, Philippe SouèresRobot Navigation Quadruped Robot Navigation
WILLOW · ISIR · LAAS-GEPETTO
Active Perception for Embodied Disambiguation
Aug 11, 2026Yiwei Liu, Luwei YangActive Visual Perception Human-Robot Interaction
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, Guangdong 518172, China · Shenzhen Research Institute of Big Data, Shenzhen 518172, China
An Exam for Active Observers
Jul 17, 2026Jiarui Zhang, Muzi Tao, Shangshang Wang +3VLM Evaluation Multimodal Large Language Models
University of Southern California
LIME: Learning Intent-aware Camera Motion from Egocentric Video
Jul 2, 2026Boyang Sun, Jiajie Li, Yung-Hsu Yang +6Active Perception VLMs for Robotics
ETH Zurich · Microsoft · University of Bonn
Event-based Gaze Control System for Accurate Real-time Spin Estimation in Professional Ball Games
Jun 25, 2026Yunpu Hu, Fabian Schilling, Valentina Cavinato +6Event-Based Vision Active Perception
Sony AI, Tokyo, Japan · Sony AI, Zürich, Switzerland · Sony Advanced Visual Sensing, Sony Europe Ltd., Zurich, Switzerland.
TAGA: Terrain-aware Active Gaze Learning for Generalizable Agile Humanoid Locomotion
Jun 4, 2026Peizhuo Li, Hongyi Li, Mingfeng Fan +9Active Perception Humanoid Robot Locomotion
MarmotLab, National University of Singapore · Center of X-Mechanics, Zhejiang University · South China University of Technology
Behavior Cloning for Active Perception with Low-Resolution Egocentric Vision
May 13, 2026Anthony Bilic, Chen Chen, Ladislau BölöniActive Vision for Robot Manipulation Active Sensing
Department of Computer Science, University of Central Florida, Orlando, FL, USA
TAVIS: A Benchmark for Egocentric Active Vision and Anticipatory Gaze in Imitation Learning
May 8, 2026Giacomo SpiglerActive Visual Perception Active Sensing
Department of Intelligent Systems Tilburg University Netherlands
GazeVLM: Active Vision via Internal Attention Control for Multimodal Reasoning
May 8, 2026Brown Ebouky, Gabriele Carrino, Niccolo Avogaro +3Active Perception VLM Reasoning
IBM Research · ETH Zurich · TU Wien
EVA: Bridging Performance and Human Alignment in Hard-Attention Vision Models for Image Classification
Mar 28, 2026Pengcheng Pan, Yonekura Shogo, Kuniyoshi YasuoScanpath Prediction Active Vision
The University of Tokyo
CanViT: Toward Active-Vision Foundation Models
Mar 23, 2026Yohaï-Eliel Berreby, Sabrina Du, Audrey Durand +1Active Vision Active Perception
McGill University · Mila - Quebec AI Institute · Université Laval
A Saccade-inspired Approach to Image Classification using Vision Transformer Attention Maps
Mar 10, 2026Matthis Dallain, Laurent Rodriguez, Laurent Udo Perrinet +1Active Vision Foveated Vision
Institut de Neurosciences de la Timone, Aix-Marseille Université, CNRS, Marseille, 13005, France · Laboratoire d’Électronique, Antennes et Télécommunications, Université Côte d’Azur, CNRS, Sophia Antipolis, 06903, France
I-Perceive: A Foundation Model for Vision-Language Active Perception
Feb 28, 2026Yongxi Huang, Zhuohang Wang, Wenjing Tang +33D Scene Understanding Robot Foundation Models
Shanghai Jiao Tong University · Shanghai Innovation Institute · Beihang University
Active Visual Perception: Opportunities and Challenges
Dec 3, 2025Yian Li, Xiaoyu Guo, Hao Zhang +3Active Visual Perception Active Vision
College of Computer Science and Engineering, Guilin University of Technology, Guilin 541004, China · New Engineering Industry College, Putian University, Putian 351100, China

Oct 16, 2026J/K move · Enter open · S save

Look Before You Act: Bridging Active Perception and Vision-Language-Action Models via Observation-Aligned Data Adaptation

Jiawei Geng, Zhenyang Liu, Yuzheng Wu, Yongchong Gu+1

Fudan University · Shanghai Innovation Institute

Active Vision for Robot Manipulation VLA Model Adaptation Active Vision Multi-Task Robotic Manipulation

Open paper AskPDF arXiv

Robots manipulating objects in clutter must decide not only how to act, but also where to look. Although active camera motion can expose an occluded target, it may move the robot into an initial observation-state distribution that differs from the manipulation policy's training distribution. We identify this problem as first-frame distribution sensitivity: under perturbed starts in LIBERO, naively prepending camera repositioning to pi_0.5 reduces success from 46.3% to 11.5%. We introduce ActiveAlign, a data-adaptation framework that trains a Vision-Language-Action (VLA) policy from the states at which active perception terminates. A learned viewpoint module first generates a camera trajectory. Offline, ActiveAlign uses closed-loop alignment to connect the trajectory endpoint to an existing demonstration, replays the remaining manipulation trajectory, and retains successful continuations for fine-tuning. At deployment, the same viewpoint module precedes the adapted VLA without modifying its architecture. Across 40 LIBERO tasks, ActiveAlign achieves 70.7% success with pi_0 and 72.7% with pi_0.5, outperforming their standard-training baselines by 40.0% and 26.4% respectively. Matched-state and data-matched controls support gains beyond prefix shortening and generic viewpoint augmentation; OpenVLA and GR00T N1 also show the same trend. Success rate under physical occlusion in real world increases from 35/90 to 83/90. These results show that active perception benefits manipulation when policy training is aligned with the observation and robot-state distribution induced by viewpoint selection.