aiqbench analysis
This arXiv paper proposes a diffusion-based visuomotor policy that uses end-effector trajectories to guide which image features the policy attends to, so robots can manipulate objects from one global camera instead of a multi-camera rig with wrist views. The simulation results show gains over single-view baselines and parity with multi-camera setups, while the real-world tests are more limited in scope. For readers, the practical question is whether this cuts sensing cost and hardware complexity enough to matter outside the lab.
Spatially Conditioned Diffusion Policy: Learning Precise and Robust Manipulation with a Single RGB Camera
arXiv:2606.14535v2 Announce Type: replace Abstract: Recent visual imitation learning systems have widely adopted multi-camera setups with wrist-mounted cameras as the de facto standard. However, manipulation from a single global view remains challenging, as the policy should capture fine-grained interaction details and identify task-relevant regions without local wrist views. To address this challenge, we present Spatially Conditioned Diffusion Policy (SCDP), a diffusion-based visuomotor policy that achieves precise and robust manipulation in a single-camera setting. Our key idea is that end-effector trajectories can serve as visual attention anchors that reflect task-relevant regions. Building on this idea, SCDP consists of two key components: (i) a visual encoder that produces multi-scale feature maps to capture both broader context and fine-grained visual features, and (ii) a spatial conditioning module that samples point-wise features along intermediate end-effector trajectories in the diffusion loop. Extensive simulation experiments show that SCDP consistently outperforms strong single-view baselines and achieves performance comparable to multi-camera baselines. Real-world experiments further demonstrate precise manipulation and robustness to visual distractors, highlighting the potential of single-camera imitation learning.
Abstract:Recent visual imitation learning systems have widely adopted multi-camera setups with wrist-mounted cameras as the de facto standard. However, manipulation from a single global view remains challenging, as the policy should capture fine-grained interaction details and identify task-relevant regions without local wrist views. To address this challenge, we present Spatially Conditioned Diffusion Policy (SCDP), a diffusion-based visuomotor policy that achieves precise and robust manipulation in a single-camera setting. Our key idea is that end-effector trajectories can serve as visual attention anchors that reflect task-relevant regions. Building on this idea, SCDP consists of two key components: (i) a visual encoder that produces multi-scale feature maps to capture both broader context and fine-grained visual features, and (ii) a spatial conditioning module that samples point-wise features along intermediate end-effector trajectories in the diffusion loop. Extensive simulation experiments show that SCDP consistently outperforms strong single-view baselines and achieves performance comparable to multi-camera baselines. Real-world experiments further demonstrate precise manipulation and robustness to visual distractors, highlighting the potential of single-camera imitation learning.
Robotics (cs.RO)
arXiv:2606.14535 [cs.RO]
(or arXiv:2606.14535v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2606.14535 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 258 words
Related coverage
Spatially Conditioned Diffusion Policy: Learning Precise and Robust Manipulation with a Single RGB Camera
arXiv · Jun 16, 2026
The Machines that Make the Machines
NVIDIA · Oct 7, 2026
Pretrained to Imagine, Fine-Tuned to Act: The Rise of World-Action Models
NVIDIA · Jun 15, 2026
MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency
arXiv · Jun 17, 2026