Metraipolis › archive › dc_96c02879caf1
AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention — arXiv:2609.20106
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.20106
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-10T02:30:27.176Z
- SHA-256 of the archived text
9c7c7a192c5472b758b94df7da274080f7925368f1220073c39b0e0bcddab409- Stable URL of this page
https://metraipolis.com/documento/dc_96c02879caf1
How to cite
AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention — arXiv:2609.20106 — arXiv (en), https://arxiv.org/abs/2609.20106 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_96c02879caf1 (Metraipolis archive dc_96c02879caf1, sha256 9c7c7a192c5472b758b94df7da274080f7925368f1220073c39b0e0bcddab409)
BibTeX
@misc{dc96c02879caf1,
title = {AnyviewMeter: Adapting Robotic Reward Models with Camera Geometry and Multi-View Attention — arXiv:2609.20106},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.20106},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_96c02879caf1; sha256 9c7c7a192c5472b758b94df7da274080f7925368f1220073c39b0e0bcddab409},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.20106. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robotic reward models evaluate task execution from visual observations, but their predictions can change with camera viewpoint and occlusion even when the underlying task state is unchanged. Adapting a pretrained reward model to a local task therefore requires accounting for how that task is observed. We introduce AnyviewMeter, a geometry-conditioned adaptation framework for robotic reward models that represent task progress as a scalar reward signal. It combines low-rank fine-tuning with token-aligned Plucker rays and synchronous block attention: ray conditioning incorporates camera geometry into visual features and attention queries and keys, while block attention fuses synchronized views inside the pretrained decoder. The framework supports both single-view reward prediction and joint multi-view evaluation through parameter-efficient adaptation of a pretrained Robometer model. On PickCube, single-view adaptation improves progress prediction in every camera group and reduces mean absolute error under a changed field of view by approximately 21% relative to RGB fine-tuning. Across simulated manipulation tasks, joint multi-view prediction reduces progress error by 41-69% compared with averaging single-view RGB predictions and improves temporal ordering in approximately 88% of task-camera groups. On real tasks with fixed and wrist-mounted cameras, mean absolute error decreases by approximately 21% relative to averaged RGB fine-tuning. These results support camera geometry and joint visual evidence as useful components of task-specific robotic reward adaptation. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.RO). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.20106 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-10T02:09:55.411Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).