{"ID":5675116,"CreatedAt":"2026-07-03T01:40:09.565152011Z","UpdatedAt":"2026-07-05T03:52:30.756976999Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01677","arxiv_id":"2607.01677","title":"ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning","abstract":"Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-frame accuracy but suffer from temporal drift due to limited context windows, while generative methods improve consistency and generalization at the cost of extensive training data (10M+ samples) and lack of geometric precision. In response to these issues, we introduce \\textbf{ICDepth}, a framework that adapts pre-trained text-to-video diffusion transformers for video depth estimation via In-Context Conditioning (ICC), leveraging their rich spatial-temporal priors. To address key challenges in transferring ICC from generation to dense prediction, we propose: (1)~\\textbf{SAND-Attention}, which ensures precise spatial-temporal alignment via shared RoPE and enforces unidirectional attention to prevent noise contamination; (2)~\\textbf{SRFM}, which injects DINOv2 semantic and resolution priors to enhance geometric precision. ICDepth achieves state-of-the-art results on multiple benchmarks with remarkable data efficiency, trained on only 0.8M frames ($6$--$13\\times$ less than competing generative methods), while demonstrating strong zero-shot generalization to diverse domains.","short_abstract":"Monocular video depth estimation requires temporal consistency, geometric accuracy, and generalization across diverse scenarios, yet existing methods struggle to achieve all three simultaneously. Discriminative models excel at per-frame accuracy but suffer from temporal drift due to limited context windows, while gener...","url_abs":"https://arxiv.org/abs/2607.01677","url_pdf":"https://arxiv.org/pdf/2607.01677v1","authors":"[\"Xuanhua He\",\"Jiaxin Xie\",\"Mingzhe Zheng\",\"Qifeng Chen\"]","published":"2026-07-02T04:05:17Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Diffusion Model\",\"Transformer\"]","has_code":false}