Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Zhang, Yu-Wei, Han, Tongju, Gao, Lipeng, Wei, Mingqiang, Liu, Hui, Li, Changbao, Zhang, Caiming
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.19555
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866916920810274816
author Zhang, Yu-Wei
Han, Tongju
Gao, Lipeng
Wei, Mingqiang
Liu, Hui
Li, Changbao
Zhang, Caiming
author_facet Zhang, Yu-Wei
Han, Tongju
Gao, Lipeng
Wei, Mingqiang
Liu, Hui
Li, Changbao
Zhang, Caiming
contents This paper presents MonoRelief V2, an end-to-end model designed for directly recovering 2.5D reliefs from single images under complex material and illumination variations. In contrast to its predecessor, MonoRelief V1 [1], which was solely trained on synthetic data, MonoRelief V2 incorporates real data to achieve improved robustness, accuracy and efficiency. To overcome the challenge of acquiring large-scale real-world dataset, we generate approximately 15,000 pseudo real images using a text-to-image generative model, and derive corresponding depth pseudo-labels through fusion of depth and normal predictions. Furthermore, we construct a small-scale real-world dataset (800 samples) via multi-view reconstruction and detail refinement. MonoRelief V2 is then progressively trained on the pseudo-real and real-world datasets. Comprehensive experiments demonstrate its state-of-the-art performance both in depth and normal predictions, highlighting its strong potential for a range of downstream applications. Code is at: https://github.com/glp1001/MonoreliefV2.
format Preprint
id arxiv_https___arxiv_org_abs_2508_19555
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery
Zhang, Yu-Wei
Han, Tongju
Gao, Lipeng
Wei, Mingqiang
Liu, Hui
Li, Changbao
Zhang, Caiming
Computer Vision and Pattern Recognition
This paper presents MonoRelief V2, an end-to-end model designed for directly recovering 2.5D reliefs from single images under complex material and illumination variations. In contrast to its predecessor, MonoRelief V1 [1], which was solely trained on synthetic data, MonoRelief V2 incorporates real data to achieve improved robustness, accuracy and efficiency. To overcome the challenge of acquiring large-scale real-world dataset, we generate approximately 15,000 pseudo real images using a text-to-image generative model, and derive corresponding depth pseudo-labels through fusion of depth and normal predictions. Furthermore, we construct a small-scale real-world dataset (800 samples) via multi-view reconstruction and detail refinement. MonoRelief V2 is then progressively trained on the pseudo-real and real-world datasets. Comprehensive experiments demonstrate its state-of-the-art performance both in depth and normal predictions, highlighting its strong potential for a range of downstream applications. Code is at: https://github.com/glp1001/MonoreliefV2.
title MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.19555