Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | https://arxiv.org/abs/2605.31217 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917547806294016 |
|---|---|
| author | Ali, Abid Rathinam, Arunkumar Aouada, Djamila |
| author_facet | Ali, Abid Rathinam, Arunkumar Aouada, Djamila |
| contents | Monocular 6-DoF spacecraft pose estimation methods predominantly process individual frames, discarding the temporal information present in an image sequence acquired during spacecraft manoeuvres. Few temporal approaches require full backbone fine-tuning or auxiliary optical flow networks, risking catastrophic forgetting or increasing computational cost, respectively. We propose TALON (Token-Aligned Lightweight adapters for Orbital Navigation): spatiotemporal 3D adapters injected before the self-attention layers of a frozen ViT vision transformer, combined with a patch-token alignment loss that geometrically grounds the adapted features to keypoint structure through a prototype-conditioned KL-divergence objective. Pre-attention placement allows the frozen attention to reason over temporally enriched tokens, achieving stronger performance with a single adapter per block than post-attention alternatives. The alignment loss shapes the intermediate representations so that each keypoint induces a spatially precise activation in the token field, while the framework adds less than 5% parameters to the frozen backbone. On SPADES dataset, TALON reduces the pose error by 50% over the prior state-of-the-art, and on SwissCube dataset it surpasses the prior best by 21.8% in ADD-0.1d accuracy. Zero-shot cross-domain evaluation from sim-to-real on SPARK real data reduces pose error by 4.7x, and ablations characterise the role of adapter depth across in-domain and cross-domain settings. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_31217 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | TALON: Token-Aligned Lightweight Adapters for 6-DoF Spacecraft Pose Estimation Ali, Abid Rathinam, Arunkumar Aouada, Djamila Computer Vision and Pattern Recognition Monocular 6-DoF spacecraft pose estimation methods predominantly process individual frames, discarding the temporal information present in an image sequence acquired during spacecraft manoeuvres. Few temporal approaches require full backbone fine-tuning or auxiliary optical flow networks, risking catastrophic forgetting or increasing computational cost, respectively. We propose TALON (Token-Aligned Lightweight adapters for Orbital Navigation): spatiotemporal 3D adapters injected before the self-attention layers of a frozen ViT vision transformer, combined with a patch-token alignment loss that geometrically grounds the adapted features to keypoint structure through a prototype-conditioned KL-divergence objective. Pre-attention placement allows the frozen attention to reason over temporally enriched tokens, achieving stronger performance with a single adapter per block than post-attention alternatives. The alignment loss shapes the intermediate representations so that each keypoint induces a spatially precise activation in the token field, while the framework adds less than 5% parameters to the frozen backbone. On SPADES dataset, TALON reduces the pose error by 50% over the prior state-of-the-art, and on SwissCube dataset it surpasses the prior best by 21.8% in ADD-0.1d accuracy. Zero-shot cross-domain evaluation from sim-to-real on SPARK real data reduces pose error by 4.7x, and ablations characterise the role of adapter depth across in-domain and cross-domain settings. |
| title | TALON: Token-Aligned Lightweight Adapters for 6-DoF Spacecraft Pose Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2605.31217 |