# Vision Foundation Models with Synthetic-Only Training for Monocular Spacecraft Pose Estimation

arXiv: https://arxiv.org/abs/2609.26561 · HTML: https://mlsanity.com/paper/2609.26561/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 30 references that are in the map.
- First posted on arXiv 22 Sep 2026.

## Builds on (most cited first, 13 of 13)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [DINOv3](https://mlsanity.com/paper/2508.10104/) (2025)
- [SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features](https://mlsanity.com/paper/2502.14786/) (2025)
- [DoRA: Weight-Decomposed Low-Rank Adaptation](https://mlsanity.com/paper/2402.09353/) (2024)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [DeiT III: Revenge of the ViT](https://mlsanity.com/paper/2204.07118/) (2022)
- [SPEED+: Next-Generation Dataset for Spacecraft Pose Estimation across Domain Gap](https://mlsanity.com/paper/2110.03101/) (2021)
- [Robust Multi-Task Learning and Online Refinement for Spacecraft Pose Estimation across Domain Gap](https://mlsanity.com/paper/2203.04275/) (2022)
- [6D Object Pose Estimation from Approximate 3D Models for Orbital Robotics](https://mlsanity.com/paper/2303.13241/) (2023)
- [Efficient Universal Perception Encoder](https://mlsanity.com/paper/2603.22387/) (2026)
- [Bridging the Domain Gap for Flight-Ready Spaceborne Vision](https://mlsanity.com/paper/2409.11661/) (2024)
- [FastPose-ViT: A Vision Transformer for Real-Time Spacecraft Pose Estimation](https://mlsanity.com/paper/2512.09792/) (2025)
- [Precision-Aware Illumination-Disentangled Vision Transformer for Spacecraft 6D Pose Estimation](https://mlsanity.com/paper/2606.11619/) (2026)

## Abstract (arXiv)

We present an improvement on previous spacecraft pose estimation architectures that results in the lowest published mean rotation errors we know of on the SPEED+ lightbox and sunlamp test sets for a known, non-cooperative spacecraft. By using a previously established heatmap-based pose estimation architecture and adapting a large self-supervised ViT foundation model (DINOv3) in place of the smaller convolutional and ViT encoders of previous work, we show that pose estimation accuracy improves from 300M to 840M parameters with no saturation yet observed. We also evaluate our 840M model on a Jetson Orin NX 16GB, measuring single-pass network inference at 133.8 ms per crop with a board draw of 32.0 W. These measurements demonstrate embedded inference feasibility on a processor family with orbital flight heritage. Our resulting model outperforms previous models across lightbox and sunlamp domains while training only on synthetic data. Our best model, using DINOv3 840M adapted with LoRA as the encoder (rank 64, three-seed ensemble with four-rotation test-time augmentation), results in 1.56^circ mean rotation error on sunlamp and 1.17^circ on lightbox, compared to the previous best mean rotation errors we know of on these test sets, 2.66^circ and 1.75^circ by EagerNet.