{"ID":2827250,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.17908","arxiv_id":"2512.17908","title":"ReDepth Anything: Test-Time Depth Refinement via Self-Supervised Re-lighting","abstract":"Monocular depth estimation remains challenging, as foundation models such as Depth Anything V2 (DA-V2) struggle with real-world images that are far from the training distribution. We introduce Re-Depth Anything, a test-time self-supervision framework that bridges this domain gap by fusing foundation models with the powerful priors of large-scale 2D diffusion models. Our method performs label-free refinement directly on the input image by re-lighting the predicted depth map and augmenting the input. This re-synthesis method replaces classical photometric reconstruction by leveraging shape from shading (SfS) cues in a new, generative context with Score Distillation Sampling (SDS). To prevent optimization collapse, our framework updates only intermediate embeddings and the decoder's weights, rather than optimizing the depth tensor directly or fine-tuning the full model. Across diverse benchmarks, Re-Depth Anything yields substantial gains in depth accuracy and realism over DA-V2, and applied on top of Depth Anything 3 (DA3) achieves state-of-the-art results, showcasing new avenues for self-supervision by geometric reasoning.","short_abstract":"Monocular depth estimation remains challenging, as foundation models such as Depth Anything V2 (DA-V2) struggle with real-world images that are far from the training distribution. We introduce Re-Depth Anything, a test-time self-supervision framework that bridges this domain gap by fusing foundation models with the pow...","url_abs":"https://arxiv.org/abs/2512.17908","url_pdf":"https://arxiv.org/pdf/2512.17908v2","authors":"[\"Ananta R. Bhattarai\",\"Helge Rhodin\"]","published":"2025-12-19T18:59:56Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\",\"cs.LG\"]","methods":"[\"Diffusion Model\"]","has_code":false}