OC-VLA++: Monocular Geometry-Guided Cross-View Consistency for Viewpoint-Robust Robotic Manipulation

• URL: http://arxiv.org/abs/2608.01066v1
• Date: Sun, 02 Aug 2026 08:06:20 GMT
• Title: OC-VLA++: Monocular Geometry-Guided Cross-View Consistency for Viewpoint-Robust Robotic Manipulation
• Abstract summary: OC-VLA++ is an extension of OC-VLA for viewpoint generalization under limited camera coverage.<n>We introduce geometry-guided paired-view supervision and an explicit cross-view action-equivariance objective.<n>Experiments demonstrate substantial improvements in unseen-view generalization under limited camera coverage.
• Score: 9.018471602754213
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We propose OC-VLA++, an extension of OC-VLA for viewpoint generalization under limited camera coverage. While OC-VLA grounds robot actions in the camera coordinate system to align action supervision with visual observations, camera-space grounding alone can still overfit to the few viewpoints observed during training. OC-VLA++ addresses this limitation by introducing geometry-guided paired-view supervision and an explicit cross-view action-equivariance objective. Given paired observations of the same manipulation scene from geometrically related viewpoints, the model is trained such that their camera-space predictions correspond to the same robot-frame action. This objective explicitly supervises how action predictions should transform across viewpoints, rather than relying solely on image-level augmentation. Experiments demonstrate substantial improvements in unseen-view generalization under limited camera coverage, with performance degrading more gracefully under increasing camera displacement. These results establish cross-view action equivariance as an effective complement to observation-centric action grounding for robust real-world deployment.

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)
• LIBERO-Occ: Evaluating and Improving Vision-Language-Action Models under Scene-Induced Occlusion via Viewpoint Imagination [66.06027569507403]
  textbfViewpoint Imagination (VIM) generates a complementary view from an occluded primary observation and conditions action prediction on both observed and imagined evidence.<n>VIM improves robustness across task suites, occlusion types, and severity levels without requiring additional cameras at deployment time.
  arXiv  Detail & Related papers  (2026-06-09T13:39:49Z)
• DisCo: World Models with Discrete Camera Motion Control [79.86256515640231]
  We propose DisCo, a controllable video world model that conditions generation on a compact set of discrete action primitives to improve action separability.<n>DisCo achieves significantly more reliable action following while preserving visual quality.
  arXiv  Detail & Related papers  (2026-06-06T03:50:45Z)
• AxisGuide: Grounding Robot Action Coordinate System in RGB Observations for Robust Visuomotor Manipulation [17.509625759060473]
  Visuomotor manipulation policies trained via large-scale behavior cloning often fail to execute correct low-level actions under distribution shifts.<n>We introduce AxisGuide, a lightweight guidance method that bridges semantic scene understanding and action-coordinate interpretation.
  arXiv  Detail & Related papers  (2026-06-04T22:57:34Z)
• Mitigating State Aliasing in Vision-Language-Action Models via Inverse Dynamics Learning [32.59795755994378]
  We introduce inverse dynamics learning as an auxiliary objective that directly supervises the Vision-Language-Action (VLA) vision encoder.<n>By predicting the action between current and future observations, our objective encourages the encoder to capture fine-grained visual distinctions that determine low-level actions.<n> Experiments on CALVIN ABC-D and SimplerEnv show consistent gains across diverse VLA baselines.
  arXiv  Detail & Related papers  (2026-05-28T08:22:49Z)
• Universal Pose Pretraining for Generalizable Vision-Language-Action Policies [83.39008378156647]
  Existing Vision-Language-Action (VLA) models often suffer from feature collapse and low training efficiency.<n>We propose Pose-VLA, a decoupled paradigm that separates VLA training into a pre-training phase for extracting universal 3D spatial priors.<n>Our framework follows a two-stage pre-training pipeline, establishing fundamental spatial grounding via poses followed by motion alignment.
  arXiv  Detail & Related papers  (2026-02-23T11:00:08Z)
• PosA-VLA: Enhancing Action Generation via Pose-Conditioned Anchor Attention [92.85371254435074]
  PosA-VLA framework anchors visual attention via pose-conditioned supervision, consistently guiding the model's perception toward task-relevant regions.<n>We show that our method executes embodied tasks with precise and time-efficient behavior across diverse robotic manipulation benchmarks.
  arXiv  Detail & Related papers  (2025-12-03T12:14:29Z)
• 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)
• Observe Then Act: Asynchronous Active Vision-Action Model for Robotic Manipulation [19.17977467107072]
  Our model serially connects a camera Next-Best-View (NBV) policy with a gripper Next-Best Pose (NBP) policy, and trains them in a sensor-motor coordination framework using few-shot reinforcement learning.<n>This approach allows the agent to adjust a third-person camera to actively observe the environment based on the task goal, and subsequently infer the appropriate manipulation actions.<n>The results demonstrate that our model consistently outperforms baseline algorithms, showcasing its effectiveness in handling visual constraints in manipulation tasks.
  arXiv  Detail & Related papers  (2024-09-23T10:38:20Z)

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.