{"ID":2877451,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.19555","arxiv_id":"2508.19555","title":"MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery","abstract":"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.","short_abstract":"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 impro...","url_abs":"https://arxiv.org/abs/2508.19555","url_pdf":"https://arxiv.org/pdf/2508.19555v1","authors":"[\"Yu-Wei Zhang\",\"Tongju Han\",\"Lipeng Gao\",\"Mingqiang Wei\",\"Hui Liu\",\"Changbao Li\",\"Caiming Zhang\"]","published":"2025-08-27T04:03:03Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":610381,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2877451,"paper_url":"https://arxiv.org/abs/2508.19555","paper_title":"MonoRelief V2: Leveraging Real Data for High-Fidelity Monocular Relief Recovery","repo_url":"https://github.com/glp1001/MonoreliefV2","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}