Metraipolis › archive › dc_8f0dcabaef29

Motion- and Gravity-Aware Feedforward 3D Reconstruction — arXiv:2610.22177

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.22177
License (as archived): CC0-1.0
Archived: 2026-10-16T09:31:03.460Z
SHA-256 of the archived text: e62fa494954b0fdf2cd0f9c6a1ef42fd2419f01dd80423a342739703fd0d3399
Stable URL of this page: https://metraipolis.com/documento/dc_8f0dcabaef29

How to cite

Motion- and Gravity-Aware Feedforward 3D Reconstruction — arXiv:2610.22177 — arXiv (en), https://arxiv.org/abs/2610.22177 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8f0dcabaef29 (Metraipolis archive dc_8f0dcabaef29, sha256 e62fa494954b0fdf2cd0f9c6a1ef42fd2419f01dd80423a342739703fd0d3399)

BibTeX

@misc{dc8f0dcabaef29,
  title = {Motion- and Gravity-Aware Feedforward 3D Reconstruction — arXiv:2610.22177},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.22177},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8f0dcabaef29; sha256 e62fa494954b0fdf2cd0f9c6a1ef42fd2419f01dd80423a342739703fd0d3399},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22177. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Feed-forward transformer models have recently achieved strong performance in multi-view 3D reconstruction, but they still rely primarily on appearance-based attention and often struggle in dynamic scenes with weak geometric cues. In this work, we introduce a motion- and gravity-aware framework under the Learning Using Privileged Information (LUPI) paradigm. During training, residual optical flow and gravity direction are provided as privileged signals to guide geometric representation learning; during inference, the model uses standard visual inputs only. We integrate these priors into transformer backbones with lightweight architectural changes, preserving feed-forward efficiency. Experiments on standard benchmarks show consistent gains in reconstruction accuracy and robustness, especially in scenes with dynamic objects, ambiguous structure, and challenging camera motion. Our analysis further shows that the optimal injection stage is backbone-dependent: middle-layer integration is generally preferable for VGGT, while late-stage integration is more effective for {\pi}3. These results suggest that LUPI offers a practical way to inject motion and physical priors into feed-forward 3D reconstruction without increasing test-time complexity.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.22177 — 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 2026-10-16T08:44:18.035Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).