Metraipolis › archive › dc_f6a12e111995

E3tereo: Improving Stereo Matching at Depth Boundaries with Learned Geometric Edges — arXiv:2610.33704

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.33704
License (as archived)
CC0-1.0
Archived
2026-10-27T08:00:24.395Z
SHA-256 of the archived text
c3c67699f16e2473f464fe955f4b96b2904c8994adc8b6a815cdb7bbbfe46c56
Stable URL of this page
https://metraipolis.com/documento/dc_f6a12e111995

How to cite

E3tereo: Improving Stereo Matching at Depth Boundaries with Learned Geometric Edges — arXiv:2610.33704 — arXiv (en), https://arxiv.org/abs/2610.33704 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f6a12e111995 (Metraipolis archive dc_f6a12e111995, sha256 c3c67699f16e2473f464fe955f4b96b2904c8994adc8b6a815cdb7bbbfe46c56)
BibTeX
@misc{dcf6a12e111995,
  title = {E3tereo: Improving Stereo Matching at Depth Boundaries with Learned Geometric Edges — arXiv:2610.33704},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.33704},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f6a12e111995; sha256 c3c67699f16e2473f464fe955f4b96b2904c8994adc8b6a815cdb7bbbfe46c56},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.33704. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Depth boundaries remain a major source of error in stereo matching. For IGEV on Scene Flow, geometric edge pixels account for only 6% of evaluated pixels but about half of the total absolute disparity error. Photometric edges can respond to texture changes without corresponding depth discontinuities, making them unreliable cues for boundary refinement. We propose E3Stereo, which learns geometric edges from disparity supervision and combines these boundary cues with the backbone disparity and image details to predict full-resolution disparity corrections. The same edge map also emphasizes boundary errors during training, while joint optimization allows the edge predictor to adapt to disparity refinement. On the Scene Flow dataset, E3Stereo reduces end-point error (EPE) at depth boundaries by 9.5%-14.3% across RAFT-Stereo, IGEV, and MonSter, while also reducing overall EPE. After fine-tuning, our IGEV-based model improves upon IGEV on all eleven reported metrics across ETH3D, KITTI 2012, and KITTI 2015. The source code will be made publicly available upon acceptance.

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/2610.33704 — 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 2026-10-27T07:55:30.842Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).