StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision

• URL: http://arxiv.org/abs/2512.21970v1
• Date: Fri, 26 Dec 2025 10:34:20 GMT
• Title: StereoVLA: Enhancing Vision-Language-Action Models with Stereo Vision
• Abstract summary: Stereo cameras closely mimic human binocular vision, providing rich spatial cues critical for precise robotic manipulation.<n>Despite their advantage, the adoption of stereo vision in vision-language-action models (VLAs) remains underexplored.<n>We present StereoVLA, a VLA model that leverages rich geometric cues from stereo vision.
• Score: 20.470652428992338
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Stereo cameras closely mimic human binocular vision, providing rich spatial cues critical for precise robotic manipulation. Despite their advantage, the adoption of stereo vision in vision-language-action models (VLAs) remains underexplored. In this work, we present StereoVLA, a VLA model that leverages rich geometric cues from stereo vision. We propose a novel Geometric-Semantic Feature Extraction module that utilizes vision foundation models to extract and fuse two key features: 1) geometric features from subtle stereo-view differences for spatial perception; 2) semantic-rich features from the monocular view for instruction following. Additionally, we propose an auxiliary Interaction-Region Depth Estimation task to further enhance spatial perception and accelerate model convergence. Extensive experiments show that our approach outperforms baselines by a large margin in diverse tasks under the stereo setting and demonstrates strong robustness to camera pose variations.

Related papers

• LiteMVS: Efficient Multi-View Stereo with Foundation Distillation and Expert Aggregation [15.55184851015005]
  LiteMVS is a lightweight multi-view depth estimation model.<n>It integrates plane-sweep geometric reasoning with strong monocular semantic priors.<n> LiteMVS achieves high-quality depth prediction and 3D reconstruction while maintaining competitive efficiency.
  arXiv  Detail & Related papers  (2026-08-04T15:54:32Z)
• StereoVGGT: A Training-Free Visual Geometry Transformer for Stereo Vision [37.95373405958899]
  Visual Geometry Grounded Transformer (VGGT) operates as a foundation model pretrained on extensive 3D priors, including camera poses.<n>We propose StereoVGGT, a feature backbone specifically tailored for stereo vision.
  arXiv  Detail & Related papers  (2026-03-31T07:41:07Z)
• Stereo World Model: Camera-Guided Stereo Video Generation [52.3922115596956]
  We present StereoWorld, a camera-conditioned stereo world model that jointly learns appearance and binocular geometry for end-to-end stereo video generation.<n>Unlike monocular RGB or RGBD approaches, StereoWorld operates exclusively within the RGB modality, while simultaneously grounding geometry directly from disparity.
  arXiv  Detail & Related papers  (2026-03-18T05:42:22Z)
• Revisiting Multi-Task Visual Representation Learning [52.93947931352643]
  We introduce MTV, a principled multi-task visual pretraining framework.<n>We leverage high-capacity "expert" models to synthesize dense, structured pseudo-labels at scale.<n>Our results demonstrate that MTV achieves "best-of-both-worlds" performance.
  arXiv  Detail & Related papers  (2026-01-20T11:59:19Z)
• Empowering Dynamic Urban Navigation with Stereo and Mid-Level Vision [13.586199223564273]
  We show that relying on monocular vision and ignoring mid-level vision priors is inefficient.<n>We present StereoWalker, which augments NFMs with stereo inputs and explicit mid-level vision such as depth estimation and dense pixel tracking.<n>We find that mid-level vision enables StereoWalker to achieve a comparable performance as the state-of-the-art using only 1.5% of the training data, and surpasses the state-of-the-art using the full data.
  arXiv  Detail & Related papers  (2025-12-11T18:59:56Z)
• Attention Guided Alignment in Efficient Vision-Language Models [56.20286899428444]
  Large Vision-Language Models (VLMs) rely on effective multimodal alignment between pre-trained vision encoders and Large Language Models (LLMs)<n>This paper presents a comprehensive analysis of attention patterns in efficient VLMs.<n>We introduce Attention-Guided Efficient Vision-Language Models (AGE-VLM), a novel framework that enhances visual grounding through interleaved cross-attention layers.
  arXiv  Detail & Related papers  (2025-11-21T21:36:48Z)
• DINOv2 Driven Gait Representation Learning for Video-Based Visible-Infrared Person Re-identification [30.593882551803855]
  Video-based Visible-Infrared person re-identification (VVI-ID) aims to retrieve the same pedestrian across visible and infrared modalities from modality.<n>To address these challenges, we propose a Gait Representation Learning framework that leverages the rich visual priors of DINOv2 to learn gait features complementary to appearance cues.<n>Specifically, we introduce a Semantic-Aware Silhouette and Gait Learning (GL) model, which generates and enhances silhouette representations with general-purpose semantic priors from DINOv2.
  arXiv  Detail & Related papers  (2025-11-06T11:21:13Z)
• Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding [11.222744122842023]
  We introduce a plug-and-play module that implicitly incorporates 3D geometry features into Vision-Language-Action (VLA) models.<n>Our method significantly improves the performance of state-of-the-art VLA models across diverse scenarios.
  arXiv  Detail & Related papers  (2025-07-01T04:05:47Z)
• ViewSpatial-Bench: Evaluating Multi-perspective Spatial Localization in Vision-Language Models [68.46716645478661]
  Vision-language models (VLMs) have demonstrated remarkable capabilities in understanding and reasoning about visual content.<n>Current VLMs excel primarily at egocentric spatial reasoning (from the camera's perspective) but fail to generalize to allocentric viewpoints.<n>We introduce ViewSpatial-Bench, the first comprehensive benchmark designed specifically for multi-viewpoint spatial localization recognition evaluation.
  arXiv  Detail & Related papers  (2025-05-27T17:59:26Z)
• Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs [57.492124844326206]
  This work delves into the task of pose-free novel view synthesis from stereo pairs, a challenging and pioneering task in 3D vision. Our innovative framework, unlike any before, seamlessly integrates 2D correspondence matching, camera pose estimation, and NeRF rendering, fostering a synergistic enhancement of these tasks.
  arXiv  Detail & Related papers  (2023-12-12T13:22:44Z)
• SGM3D: Stereo Guided Monocular 3D Object Detection [62.11858392862551]
  We propose a stereo-guided monocular 3D object detection network, termed SGM3D. We exploit robust 3D features extracted from stereo images to enhance the features learned from the monocular image. Our method can be integrated into many other monocular approaches to boost performance without introducing any extra computational cost.
  arXiv  Detail & Related papers  (2021-12-03T13:57:14Z)

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.