Salvato in:
Dettagli Bibliografici
Autori principali: Zhu, Yufan, Ran, Chongzhi, Feng, Mingtao, Dong, Le, Dong, Weisheng, López, Antonio M.
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2406.07741
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915738474774528
author Zhu, Yufan
Ran, Chongzhi
Feng, Mingtao
Dong, Le
Dong, Weisheng
López, Antonio M.
author_facet Zhu, Yufan
Ran, Chongzhi
Feng, Mingtao
Dong, Le
Dong, Weisheng
López, Antonio M.
contents Accurate monocular depth estimation is a fundamental component of vision-based perception systems in intelligent transportation applications. Despite recent progress, unsupervised monocular approaches still suffer from significant performance degradation in real-world traffic scenes due to synthetic-to-real domain gaps and the presence of dynamic, non-rigid objects such as vehicles and pedestrians. In this paper, we propose Back2Color, a robust unsupervised monocular depth estimation framework that addresses these challenges through domain adaptation and uncertainty-aware fusion. Specifically, Back2Color proposes a bidirectional depth-to-color transformation strategy that learns appearance mappings from real-world driving data and applies them to synthetic depth maps, thereby constructing training samples with realistic color appearance and paired synthetic depth. In this way, the proposed approach effectively reduces the domain gap between simulated and real traffic scenes, enabling the depth prediction network to learn more stable and generalizable priors. To further improve robustness under dynamic environments, we propose an auto-learning uncertainty temporal-spatial fusion (Auto-UTSF) module, which adaptively fuses complementary temporal and spatial cues by estimating pixel-wise uncertainty, enabling reliable depth prediction in the presence of moving objects and occlusions. Extensive experiments on challenging urban driving benchmarks, including KITTI and Cityscapes, demonstrate that the proposed method consistently outperforms existing unsupervised monocular depth estimation approaches, particularly in dynamic traffic scenarios, while maintaining high computational efficiency.
format Preprint
id arxiv_https___arxiv_org_abs_2406_07741
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Back2Color: Domain-Adaptive Synthetic-to-Real Monocular Depth Estimation for Dynamic Traffic Scenes
Zhu, Yufan
Ran, Chongzhi
Feng, Mingtao
Dong, Le
Dong, Weisheng
López, Antonio M.
Computer Vision and Pattern Recognition
Accurate monocular depth estimation is a fundamental component of vision-based perception systems in intelligent transportation applications. Despite recent progress, unsupervised monocular approaches still suffer from significant performance degradation in real-world traffic scenes due to synthetic-to-real domain gaps and the presence of dynamic, non-rigid objects such as vehicles and pedestrians. In this paper, we propose Back2Color, a robust unsupervised monocular depth estimation framework that addresses these challenges through domain adaptation and uncertainty-aware fusion. Specifically, Back2Color proposes a bidirectional depth-to-color transformation strategy that learns appearance mappings from real-world driving data and applies them to synthetic depth maps, thereby constructing training samples with realistic color appearance and paired synthetic depth. In this way, the proposed approach effectively reduces the domain gap between simulated and real traffic scenes, enabling the depth prediction network to learn more stable and generalizable priors. To further improve robustness under dynamic environments, we propose an auto-learning uncertainty temporal-spatial fusion (Auto-UTSF) module, which adaptively fuses complementary temporal and spatial cues by estimating pixel-wise uncertainty, enabling reliable depth prediction in the presence of moving objects and occlusions. Extensive experiments on challenging urban driving benchmarks, including KITTI and Cityscapes, demonstrate that the proposed method consistently outperforms existing unsupervised monocular depth estimation approaches, particularly in dynamic traffic scenarios, while maintaining high computational efficiency.
title Back2Color: Domain-Adaptive Synthetic-to-Real Monocular Depth Estimation for Dynamic Traffic Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.07741