外观
论文arXiv 2610.1273420 天前
StereoEngine：无需双目相机扩展双目双臂机器人数据
原文链接：StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras（arXiv 2610.12734 · 发布日期：2026-10-08）
StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras
为缓解真实双目机器人数据稀缺，StereoEngine用单目提升和仿真生成双目数据，并在双臂操作中验证。
核心要点
- 真实大规模双目数据稀缺，限制将双目视觉用于VLA机器人操作策略扩展。
- 方法一用估计深度将单目左视角视频变形为右视角，并以视频扩散补全遮挡区域。
- 方法二在仿真中渲染双目对，并联合生成照片级真实的左右一致双目数据。
- 合成数据用于策略中期训练或任务微调，可提升下游双臂操作表现；项目网站已给出。
验证范围与局限：验证包括生成双目质量和下游双臂操作，摘要未说明具体机器人平台或任务范围。
英文摘要 (Abstract)
Stereo vision is increasingly used for robotic manipulation, with a growing body of work incorporating it into Vision-Language-Action (VLA) models. However, the scarcity of large-scale, real-world stereo datasets remains a fundamental bottleneck for scaling such policies. Recent generative monocular-to-stereo methods target settings such as VR content and autonomous driving. No prior work produces realistic synthetic stereo data for robotic manipulation, where stereo supervision has come predominantly from simulation. We propose StereoEngine, which introduces two complementary methods to synthesize stereo data for robotic manipulation. In the first, we warp a monocular (left) video into the right view using estimated depth and inpaint the disoccluded regions with a video diffusion model, lifting monocular demonstrations into stereo pairs without training on real stereo. In the second, we render a stereo pair in simulation and jointly generate both photorealistic views, producing consistent left-right data without any real video as input. StereoEngine outperforms existing baselines in generated stereo quality, and using its synthetic data for policy mid-training or task-specific fine-tuning substantially improves downstream bimanual manipulation. Project website: https://stereoengine.github.io
作者：Jason Chen, I-Chun Arthur Liu, Gaurav S. Sukhatme, Daniel Seita
来源
本页事实对应的公开页面，以原文为准。