Metraipolis › archive › dc_01245c97ef79
MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting — arXiv:2610.10759
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.10759
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:30:09.496Z
- SHA-256 of the archived text
df10f5c11454299ce31863e3b60a25c943f2447c81b1f9e665abc2586d33fc1c- Stable URL of this page
https://metraipolis.com/documento/dc_01245c97ef79
How to cite
MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting — arXiv:2610.10759 — arXiv (en), https://arxiv.org/abs/2610.10759 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_01245c97ef79 (Metraipolis archive dc_01245c97ef79, sha256 df10f5c11454299ce31863e3b60a25c943f2447c81b1f9e665abc2586d33fc1c)
BibTeX
@misc{dc01245c97ef79,
title = {MESSENGER: Memory-Enhanced Sequential Scene Flow Estimation via Autoregressive Next-Frame Forecasting — arXiv:2610.10759},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.10759},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_01245c97ef79; sha256 df10f5c11454299ce31863e3b60a25c943f2447c81b1f9e665abc2586d33fc1c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10759. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scene flow can capture low-level 3D motion displacements in dynamic scenarios. Early pairwise estimators relying on instantaneous two-frame motion lack long-term temporal correlation and also struggle with poor extrapolation ability in future prediction. Although some recent methods attempt to explore multi-frame scene flow estimation in a sequence-to-sequence manner, they typically suffer from heavy computational overhead with increasing input frames and long-horizon prediction degradation due to ineffective motion propagation. To address these problems, we propose a novel memory-enhanced sequential scene flow pipeline, called MESSENGER. To sufficiently mine long-term temporal dependencies naturally within consecutive sequences, a memory buffer is designed by explicitly storing multiple history flow estimates and latent states. For each input frame, the temporally stored flows and states are correlated and retrieved to predict the current initialized flow in a next-frame forecasting manner. Furthermore, we develop an uncertainty-aware reweighting module to filter unreliable retrievals and mitigate accumulated errors. Extensive experiments on nuScenes and Argoverse 2 demonstrate state-of-the-art performance of our MESSENGER, reducing EPE3D by 71.6% on nuScenes and 67.7% on Argoverse 2 in long-horizon future extrapolation. This superiority can be attributed to our designed autoregressive forecasting paradigm, which naturally forces the network to progressively learn the next-frame distribution based on history observations. Code will be released at this https URL . 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/2610.10759 — 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 2026-10-09T05:55:06.988Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).