Metraipolis › archive › dc_799a555bcbb2

DEQ-Stereo: Deep Euilibrium Video Stereo Matching via Adaptive Convergence — arXiv:2610.39701

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.39701
License (as archived): CC0-1.0
Archived: 2026-11-01T02:42:08.029Z
SHA-256 of the archived text: 62d55d52f4ccd24f08372429878d3222554e4d7b33078c95ce36ac4c622b1b48
Stable URL of this page: https://metraipolis.com/documento/dc_799a555bcbb2

How to cite

DEQ-Stereo: Deep Euilibrium Video Stereo Matching via Adaptive Convergence — arXiv:2610.39701 — arXiv (en), https://arxiv.org/abs/2610.39701 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_799a555bcbb2 (Metraipolis archive dc_799a555bcbb2, sha256 62d55d52f4ccd24f08372429878d3222554e4d7b33078c95ce36ac4c622b1b48)

BibTeX

@misc{dc799a555bcbb2,
  title = {DEQ-Stereo: Deep Euilibrium Video Stereo Matching via Adaptive Convergence — arXiv:2610.39701},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39701},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_799a555bcbb2; sha256 62d55d52f4ccd24f08372429878d3222554e4d7b33078c95ce36ac4c622b1b48},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39701. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Iterative refinement models have significantly improved stereo matching accuracy, but their rigid, fixed update schedules incur heavy computational costs and a strict trade-off between speed and accuracy. This challenge is magnified in video streams, where traditional online methods resort to reducing feature channels or relying on expensive temporal warping. To address this, we propose \textbf{DEQ-Stereo}, a novel video stereo matching framework based on the Deep Equilibrium (DEQ) paradigm. Instead of unrolling a fixed number of iterations, DEQ-Stereo reformulates the refinement as an implicit fixed-point problem, adaptively terminating once convergence is met. To ensure fast and stable intra-frame convergence, we introduce the \textbf{Convolutional Simplified Gated Unit (ConvSGU)}, which eliminates unnecessary non-linearities by modeling the latent state as a gated, element-wise sum of inputs. Furthermore, to exploit cross-frame temporal coherence, we propose \textbf{Temporal State Transfer (TST)}, a warm-start strategy that propagates the converged hidden state to the next frame without requiring explicit pose or warping priors. Extensive evaluations demonstrate that DEQ-Stereo delivers state-of-the-art performance with a superior accuracy-to-latency trade-off.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.39701 — 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 2026-11-01T02:16:43.948Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).