# Improving Robotic Manipulation with Efficient Geometry-Aware Vision Encoder

arXiv: https://arxiv.org/abs/2509.15880 · HTML: https://mlsanity.com/paper/2509.15880/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- First posted on arXiv 19 Sep 2025.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- Offline RL and imitation learning from data / [Robot manipulation imitation learning](https://mlsanity.com/offlinerl/robot-manipulation-imitation-learning/)

## Built on by (most cited first, 9 of 9)

- [VGGT-Omega](https://mlsanity.com/paper/2605.15195/) (2026)
- [VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation](https://mlsanity.com/paper/2603.18943/) (2026)
- [Action-Geometry Prediction with 3D Geometric Prior for Bimanual Manipulation](https://mlsanity.com/paper/2602.23814/) (2026)
- [R3DP: Real-Time 3D-Aware Policy for Embodied Manipulation](https://mlsanity.com/paper/2603.14498/) (2026)
- [R3D: Revisiting 3D Policy Learning](https://mlsanity.com/paper/2604.15281/) (2026)
- [Think Locally, Refine Globally for Memory-Efficient 3D Reconstruction](https://mlsanity.com/paper/2609.21437/) (2026)
- [Geometric Foundation Model Distillation for Efficient Lunar 3D Reconstruction](https://mlsanity.com/paper/2607.01851/) (2026)
- [What VGGT Knows About Overlap: Probing Geometric Foundation Models for Co-Visibility](https://mlsanity.com/paper/2607.09503/) (2026)
- [RayViT: Ray-Conditioned Visual Representations for Viewpoint-Robust Imitation Learning](https://mlsanity.com/paper/2607.29622/) (2026)

## Abstract (arXiv)

Geometry-grounded vision models, such as VGGT, have emerged as robust visual encoders, providing essential geometric priors for robotic manipulation. However, the high computational cost of these models often leads to slow inference, limiting their practical applications in real-world robotics. This paper introduces eVGGT, a lightweight geometry-aware vision encoder distilled from the high-performing VGGT. Our findings demonstrate two primary advantages: i) integrating eVGGT into imitation learning frameworks (including ACT and Diffusion Policy) yields up to a 6.3% improvement in success rate over standard 2D encoders across bimanual and single-arm tasks in both simulation and real-world settings with variable viewpoints; ii) eVGGT achieves a nearly 5 times speedup and a 63% reduction in memory usage compared to state-of-the-art geometry-aware encoders while maintaining comparable task performance. These results suggest that eVGGT substantially alleviates the performance-latency bottleneck that has limited geometry-aware visuomotor policies in real-world deployment.