From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model

• URL: http://arxiv.org/abs/2607.05396v1
• Date: Mon, 06 Jul 2026 17:59:59 GMT
• Title: From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model
• Abstract summary: Camera-Centric VLA (CamVLA) is a new VLA model that decouples manipulation controls from camera geometry.<n>CamVLA consistently improves success rates across diverse unseen viewpoints.
• Score: 72.8641426724502
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Real-world robot deployment rarely maintains the training-stage camera setup, where cameras often experience repositioning or remounting depending on actual scenarios. Existing view-robust Vision-Language-Action (VLA) policies tolerate such camera variations only when the camera extrinsics are explicitly provided, making them fragile and hard to use especially when view robustness is critical. We argue that the policy should not be told where the camera is, but rather figure it out by itself. To this end, we introduce Camera-Centric VLA (CamVLA), a new VLA model that decouples manipulation controls from camera geometry by predicting (i) a camera-centric end-effector action expressed in the local camera frame, and (ii) a 6-DoF hand-eye matrix relating cameras to the robot base. A deterministic geometric transformation composes the two predictions into a robot base-frame action. This disentangles how I should move in pose-independent camera-centric action generation from where I am looking from in camera-perspective geometric grounding. The resulting policy is calibration-free, depth-free, and single-view, requiring only a single monocular RGB image as the visual observation and task instruction at deployment. Evaluations in both simulation and real-world robot data show that CamVLA consistently improves success rates across diverse unseen viewpoints. Project page: https://alibaba-damo-academy.github.io/CamVLA/.

Related papers

• UniMoCa: Unifying Motion and Camera Controls as Visual Proxies for Faithful Human Video Generation [50.391925716274926]
  textbfUniMoCa is a representation-driven framework that unifies motion and camera controls in visual space.<n>We show that UniMoCa achieves substantial gains in human motion control, camera control, temporal consistency, and camera-aware robustness with minimal additional complexity.
  arXiv  Detail & Related papers  (2026-08-03T09:18:13Z)
• See like a Robot: Robot-Centric Pointmaps for Vision-Language-Action Models [51.019904314336124]
  Vision-language-action (VLA) models predict robot actions from visual observations and language instructions.<n>Most VLAs observe the scene in the camera frame, creating a frame mismatch between where the scene is observed and where actions are defined.<n>We address this mismatch with robot-centric pointmaps, images whose pixels store the 3D coordinates of scene points in the robot frame.
  arXiv  Detail & Related papers  (2026-07-13T12:50:32Z)
• LIME: Learning Intent-aware Camera Motion from Egocentric Video [56.023644847494836]
  We propose a vision-language camera-motion generator that combines an auto-regressive observation-gain output with a continuous flow-matching pose head.<n>We show that LIME can learn to actively choose camera poses from passive human video, turning ordinary egocentric recordings into supervision for intent-aware active perception.
  arXiv  Detail & Related papers  (2026-07-02T16:48:43Z)
• CamPilot: Improving Camera Control in Video Diffusion Model with Efficient Camera Reward Feedback [43.174121093566264]
  We build upon Reward Feedback Learning and aim to further improve camera controllability.<n>Current reward models lack the capacity to assess video-camera alignment.<n>We introduce an efficient camera-aware 3D decoder that decodes video latent into 3D representations for reward quantization.
  arXiv  Detail & Related papers  (2026-01-22T18:59:56Z)
• Do You Know Where Your Camera Is? View-Invariant Policy Learning with Camera Conditioning [22.045823914539408]
  We study view-invariant imitation learning by explicitly conditioning policies on camera extrinsics.<n>We show that conditioning on extrinsics significantly improves generalization across viewpoints for standard behavior cloning policies.
  arXiv  Detail & Related papers  (2025-10-02T17:47:06Z)
• CameraCtrl: Enabling Camera Control for Text-to-Video Generation [86.36135895375425]
  Controllability plays a crucial role in video generation, as it allows users to create and edit content more precisely.<n>Existing models, however, lack control of camera pose that serves as a cinematic language to express deeper narrative nuances.<n>We introduce CameraCtrl, enabling accurate camera pose control for video diffusion models.
  arXiv  Detail & Related papers  (2024-04-02T16:52:41Z)
• SmartMocap: Joint Estimation of Human and Camera Motion using Uncalibrated RGB Cameras [49.110201064166915]
  Markerless human motion capture (mocap) from multiple RGB cameras is a widely studied problem. Existing methods either need calibrated cameras or calibrate them relative to a static camera, which acts as the reference frame for the mocap system. We propose a mocap method which uses multiple static and moving extrinsically uncalibrated RGB cameras.
  arXiv  Detail & Related papers  (2022-09-28T08:21:04Z)
• AirPose: Multi-View Fusion Network for Aerial 3D Human Pose and Shape Estimation [51.17610485589701]
  We present a novel markerless 3D human motion capture (MoCap) system for unstructured, outdoor environments. AirPose estimates human pose and shape using images captured by multiple uncalibrated flying cameras. AirPose itself calibrates the cameras relative to the person instead of relying on any pre-calibration.
  arXiv  Detail & Related papers  (2022-01-20T09:46:20Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.