AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models

• URL: http://arxiv.org/abs/2603.05868v1
• Date: Fri, 06 Mar 2026 03:44:23 GMT
• Title: AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models
• Abstract summary: We propose a zero-shot camera adaptation framework without additional demonstration data, policy fine-tuning, or architectural modification.<n>Our key idea is to virtually adjust test-time camera observations to match the training camera configuration in real-time.<n>This approach consistently outperforms baselines that use data augmentation for policy fine-tuning or additional 3D-aware features for visual input.
• Score: 33.20237572326132
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite remarkable progress in Vision-Language-Action models (VLAs) for robot manipulation, these large pre-trained models require fine-tuning to be deployed in specific environments. These fine-tuned models are highly sensitive to camera viewpoint changes that frequently occur in unstructured environments. In this paper, we propose a zero-shot camera adaptation framework without additional demonstration data, policy fine-tuning, or architectural modification. Our key idea is to virtually adjust test-time camera observations to match the training camera configuration in real-time. For that, we use a recent feed-forward novel view synthesis model which outputs high-quality target view images, handling both extrinsic and intrinsic parameters. This plug-and-play approach preserves the pre-trained capabilities of VLAs and applies to any RGB-based policy. Through extensive experiments on the LIBERO benchmark, our method consistently outperforms baselines that use data augmentation for policy fine-tuning or additional 3D-aware features for visual input. We further validate that our approach constantly enhances viewpoint robustness in real-world robotic manipulation scenarios, including settings with varying camera extrinsics, intrinsics, and freely moving handheld cameras.

Related papers

• From Fixed to Free Cameras: Calibration-Free View-Robust Vision-Language-Action Model [72.8641426724502]
  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.
  arXiv  Detail & Related papers  (2026-07-06T17:59:59Z)
• DeltaCam: Differential Intrinsic Camera Modeling for Video Generation [8.590252585822439]
  We introduce DeltaCam, a video diffusion framework that models camera behavior through relative changes in camera motion and intrinsics instead of absolute states.<n>We extend this framework to real-world footage through two mechanisms: finetuning the controls on real image-metadata pairs for precise shot matching, and extracting disentangled embeddings for implicit video-to-video style transfer.
  arXiv  Detail & Related papers  (2026-05-24T21:39:54Z)
• CT-1: Vision-Language-Camera Models Transfer Spatial Reasoning Knowledge to Camera-Controllable Video Generation [84.82778089348285]
  Camera Transformer 1 is a specialized model designed to transfer spatial reasoning knowledge to video generation by accurately estimating camera trajectories.<n>Our framework successfully bridges the gap between spatial reasoning and video synthesis, yielding faithful and high-quality camera-controllable videos.
  arXiv  Detail & Related papers  (2026-04-10T10:43:18Z)
• InCaRPose: In-Cabin Relative Camera Pose Estimation Model and Dataset [7.117236435809274]
  InCaRPose is a Transformer-based architecture designed for robust relative pose prediction between image pairs.<n>By leveraging frozen backbone features such as DINOv3 and a Transformer-based decoder, our model effectively captures the geometric relationship between a reference and a target view.<n>Our approach achieves absolute metric-scale translation within the physically plausible adjustment range of in-cabin camera mounts.
  arXiv  Detail & Related papers  (2026-04-04T17:40:25Z)
• Virtually Being: Customizing Camera-Controllable Video Diffusion Models with Multi-View Performance Captures [18.241178853941623]
  We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models.<n>We fine-tune state-of-the-art open-source video diffusion models on this data to provide strong multi-view identity preservation.<n>Our framework also supports core capabilities for virtual production, including multi-subject generation.
  arXiv  Detail & Related papers  (2025-10-16T00:20:57Z)
• PoseDiff: A Unified Diffusion Model Bridging Robot Pose Estimation and Video-to-Action Control [67.17998939712326]
  We present PoseDiff, a conditional diffusion model that unifies robot state estimation and control within a single framework.<n>At its core, PoseDiff maps raw visual observations into structured robot states-such as 3D keypoints or joint angles-from a single RGB image.<n>Building upon this foundation, PoseDiff extends naturally to video-to-action inverse dynamics.
  arXiv  Detail & Related papers  (2025-09-29T10:55:48Z)
• Grounding Actions in Camera Space: Observation-Centric Vision-Language-Action Policy [47.51062818231493]
  We introduce the Observation-Centric VLA (OC-VLA) framework, which grounds action predictions directly in the camera observation space.<n>OC-VLA transforms end-effector poses from the robot base coordinate system into the camera coordinate system.<n>This strategy substantially improves model resilience to camera viewpoint variations.
  arXiv  Detail & Related papers  (2025-08-18T17:10:45Z)
• OG-VLA: 3D-Aware Vision Language Action Model via Orthographic Image Generation [68.11862866566817]
  3D-aware policies achieve state-of-the-art performance on precise robot manipulation tasks, but struggle with generalization to unseen instructions, scenes, and objects.<n>We introduce OG-VLA, a novel architecture and learning framework that combines the generalization strengths of Vision Language Action models (VLAs) with the robustness of 3D-aware policies.
  arXiv  Detail & Related papers  (2025-06-01T22:15:45Z)
• EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance [69.40274699401473]
  We introduce EPiC, an efficient and precise camera control learning framework.<n>It constructs high-quality anchor videos without expensive camera trajectory annotations.<n>EPiC achieves SOTA performance on RealEstate10K and MiraData for I2V camera control task.
  arXiv  Detail & Related papers  (2025-05-28T01:45:26Z)
• DriveCamSim: Generalizable Camera Simulation via Explicit Camera Modeling for Autonomous Driving [9.882070476776274]
  We present a generalizable camera simulation framework DriveCamSim.<n>Our core innovation lies in the proposed Explicit Camera Modeling mechanism.<n>For controllable generation, we identify the issue of information loss inherent in existing conditional encoding and injection pipelines.
  arXiv  Detail & Related papers  (2025-05-26T08:50:15Z)
• UniDrive: Towards Universal Driving Perception Across Camera Configurations [38.40168936403638]
  3D perception aims to infer 3D information from 2D images based on 3D-2D projection.<n>Generalizing across camera configurations is important for deploying autonomous driving models on different car models.<n>We present UniDrive, a novel framework for vision-centric autonomous driving to achieve universal perception across camera configurations.
  arXiv  Detail & Related papers  (2024-10-17T17:59:59Z)
• Diversity-Driven View Subset Selection for Indoor Novel View Synthesis [54.468355408388675]
  We propose a novel subset selection framework that integrates a comprehensive diversity-based measurement with well-designed utility functions.<n>We show that our framework consistently outperforms baseline strategies while using only 5-20% of the data.
  arXiv  Detail & Related papers  (2024-09-11T08:36:49Z)
• Self-Supervised Camera Self-Calibration from Video [34.35533943247917]
  We propose a learning algorithm to regress per-sequence calibration parameters using an efficient family of general camera models. Our procedure achieves self-calibration results with sub-pixel reprojection error, outperforming other learning-based methods.
  arXiv  Detail & Related papers  (2021-12-06T19:42:05Z)

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.