{"ID":2899156,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2507.01634","arxiv_id":"2507.01634","title":"Depth Anything at Any Condition","abstract":"We present Depth Anything at Any Condition (DepthAnything-AC), a foundation monocular depth estimation (MDE) model capable of handling diverse environmental conditions. Previous foundation MDE models achieve impressive performance across general scenes but not perform well in complex open-world environments that involve challenging conditions, such as illumination variations, adverse weather, and sensor-induced distortions. To overcome the challenges of data scarcity and the inability of generating high-quality pseudo-labels from corrupted images, we propose an unsupervised consistency regularization finetuning paradigm that requires only a relatively small amount of unlabeled data. Furthermore, we propose the Spatial Distance Constraint to explicitly enforce the model to learn patch-level relative relationships, resulting in clearer semantic boundaries and more accurate details. Experimental results demonstrate the zero-shot capabilities of DepthAnything-AC across diverse benchmarks, including real-world adverse weather benchmarks, synthetic corruption benchmarks, and general benchmarks. Project Page: https://ghost233lism.github.io/depthanything-AC-page Code: https://github.com/HVision-NKU/DepthAnythingAC","short_abstract":"We present Depth Anything at Any Condition (DepthAnything-AC), a foundation monocular depth estimation (MDE) model capable of handling diverse environmental conditions. Previous foundation MDE models achieve impressive performance across general scenes but not perform well in complex open-world environments that involv...","url_abs":"https://arxiv.org/abs/2507.01634","url_pdf":"https://arxiv.org/pdf/2507.01634v1","authors":"[\"Boyuan Sun\",\"Modi Jin\",\"Bowen Yin\",\"Qibin Hou\"]","published":"2025-07-02T12:05:57Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[]","has_code":false,"code_links":[{"ID":612461,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2899156,"paper_url":"https://arxiv.org/abs/2507.01634","paper_title":"Depth Anything at Any Condition","repo_url":"https://github.com/HVision-NKU/DepthAnythingAC","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}