{"work":{"id":"c902e427-c54a-4fc4-8aef-d0243f90ea39","openalex_id":null,"doi":null,"arxiv_id":"2302.12288","raw_key":null,"title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","authors":null,"authors_text":"Shariq Farooq Bhat, Reiner Birkl, Diana Wofk, Peter Wonka, Matthias M\\\"uller","year":2023,"venue":"cs.CV","abstract":"This paper tackles the problem of depth estimation from a single image. Existing work either focuses on generalization performance disregarding metric scale, i.e. relative depth estimation, or state-of-the-art results on specific datasets, i.e. metric depth estimation. We propose the first approach that combines both worlds, leading to a model with excellent generalization performance while maintaining metric scale. Our flagship model, ZoeD-M12-NK, is pre-trained on 12 datasets using relative depth and fine-tuned on two datasets using metric depth. We use a lightweight head with a novel bin adjustment design called metric bins module for each domain. During inference, each input image is automatically routed to the appropriate head using a latent classifier. Our framework admits multiple configurations depending on the datasets used for relative depth pre-training and metric fine-tuning. Without pre-training, we can already significantly improve the state of the art (SOTA) on the NYU Depth v2 indoor dataset. Pre-training on twelve datasets and fine-tuning on the NYU Depth v2 indoor dataset, we can further improve SOTA for a total of 21% in terms of relative absolute error (REL). Finally, ZoeD-M12-NK is the first model that can jointly train on multiple datasets (NYU Depth v2 and KITTI) without a significant drop in performance and achieve unprecedented zero-shot generalization performance to eight unseen datasets from both indoor and outdoor domains. The code and pre-trained models are publicly available at https://github.com/isl-org/ZoeDepth .","external_url":"https://arxiv.org/abs/2302.12288","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-25T05:16:39.166958+00:00","pith_arxiv_id":"2302.12288","created_at":"2026-05-10T08:22:37.472970+00:00","updated_at":"2026-05-25T05:16:39.166958+00:00","title_quality_ok":true,"display_title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","render_title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth"},"hub":{"state":{"work_id":"c902e427-c54a-4fc4-8aef-d0243f90ea39","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":48,"external_cited_by_count":null,"distinct_field_count":3,"first_pith_cited_at":"2024-03-14T17:58:41+00:00","last_pith_cited_at":"2026-05-21T23:08:42+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-05-28T10:28:26.238927+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":7},{"context_role":"method","n":2},{"context_role":"baseline","n":1}],"polarity_counts":[{"context_polarity":"background","n":7},{"context_polarity":"use_method","n":2},{"context_polarity":"baseline","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}