StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo Cameras
We propose StereoEngine, which introduces two complementary methods to synthesize stereo data for robotic manipulation.
ProofPaper ↗
Key points
- Stereo vision is increasingly used for robotic manipulation, with a growing body of work incorporating it into Vision-Language-Action (VLA) models.
- 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.
- 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.
Sources (1)
- [1]StereoEngine: Scaling Stereo Bimanual Robot Data without Stereo CamerasarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 09:28 PM
We propose StereoEngine, which introduces two complementary methods to synthesize stereo data for robotic manipulation.
Stereo vision is increasingly used for robotic manipulation, with a growing body of work incorporating it into Vision-Language-Action (VLA) models.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026Spa-Bench: A Real-Robot Benchmark for Spatial Grounding in Vision-Language-Action Models
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 7, 2026Enabling Preference-driven Unlearning in Few-step Distilled Text-to-Image Diffusion Models
- Oct 7, 2026GRACE: Generation-aware latent compression for efficient video generation
- Oct 7, 2026Many Ways to Succeed: Diversity-Driven RL Fine-Tuning for VLA Generalization
- Oct 7, 2026TempoBridge: Language-Guided Tempo Control for Vision-Language-Action Policies