MonSter++: Unified Stereo Matching, Multi-View Stereo, and Real-Time Stereo With Monodepth Priors
IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-10 · 48 (10) · 13567-13584
DOI: 10.1109/tpami.2026.3708185 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-10. Verfasst von Junda Cheng und 12 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 103 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
We introduce MonSter++, a geometric foundation model for multi-view depth estimation, unifying rectified stereo matching and unrectified multi-view stereo. Both tasks fundamentally recover metric depth from correspondence search and consequently face the same dilemma: struggling to handle ill-posed regions with limited matching cues. To address this, we propose MonSter++, a novel method that integrates monocular depth priors into multi-view depth estimation, effectively combining the complementary strengths of single-view and multi-view cues. MonSter++ fuses monocular depth and multi-view depth into a dual-branched architecture. Confidence-based guidance adaptively selects reliable multi-view cues to correct scale ambiguity in monocular depth. The refined monocular predictions, in turn, effectively guide multi-view estimation in ill-posed regions. This iterative mutual enhancement enables MonSter++ to evolve coarse object-level monocular priors into fine-grained, pixel-level geometry, fully unlocking the potential of multi-view depth estimation. MonSter++ achieves new state-of-the-art on both stereo matching and multi-view stereo. By effectively incorporating monocular priors through our cascaded search and multi-scale depth fusion strategy, our real-time variant RT-MonSter++ also outperforms previous real-time methods by a large margin. As shown in Fig. 1, MonSter++ achieves significant improvements over previous methods across eight benchmarks from three tasks-stereo matching, real-time stereo matching, and multi-view stereo, demonstrating the strong generality of our framework. Besides high accuracy, MonSter++ also demonstrates superior zero-shot generalization capability. We will release both the large and the real-time models to facilitate their use by the open-source community.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Cheng, J., Liao, W., Cai, Z., Liu, L., Xu, G., Wang, X., Wang, Y., Yuan, Z., Deng, Y., Zang, J., Shi, Y., Tang, J., & Yang, X. (2026). MonSter++: Unified Stereo Matching, Multi-View Stereo, and Real-Time Stereo With Monodepth Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(10), 13567-13584. https://doi.org/10.1109/tpami.2026.3708185
Vancouver
Cheng J, Liao W, Cai Z, Liu L, Xu G, Wang X, et al. MonSter++: Unified Stereo Matching, Multi-View Stereo, and Real-Time Stereo With Monodepth Priors. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(10):13567-13584. doi:10.1109/tpami.2026.3708185
BibTeX
@article{Cheng2026,
author = {Cheng, Junda and Liao, Wenjing and Cai, Zhipeng and Liu, Longliang and Xu, Gangwei and Wang, Xianqi and Wang, Yuzhou and Yuan, Zikang and Deng, Yong and Zang, Jinliang and Shi, Yangyang and Tang, Jinhui and Yang, Xin},
title = {MonSter++: Unified Stereo Matching, Multi-View Stereo, and Real-Time Stereo With Monodepth Priors},
journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
year = {2026},
volume = {48},
number = {10},
pages = {13567--13584},
doi = {10.1109/tpami.2026.3708185}
}
EUVIMED