{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/megadepth-learning-single-view-depth","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","arxiv_id":"1804.00607","date":"2018-04-02","proceeding":"CVPR 2018 6","authors":["Zhengqi Li","Noah Snavely"],"abstract":"Single-view depth prediction is a fundamental problem in computer vision.\nRecently, deep learning methods have led to significant progress, but such\nmethods are limited by the available training data. Current datasets based on\n3D sensors have key limitations, including indoor-only images (NYU), small\nnumbers of training examples (Make3D), and sparse sampling (KITTI). We propose\nto use multi-view Internet photo collections, a virtually unlimited data\nsource, to generate training data via modern structure-from-motion and\nmulti-view stereo (MVS) methods, and present a large depth dataset called\nMegaDepth based on this idea. Data derived from MVS comes with its own\nchallenges, including noise and unreconstructable objects. We address these\nchallenges with new data cleaning methods, as well as automatically augmenting\nour data with ordinal depth relations generated using semantic segmentation. We\nvalidate the use of large amounts of Internet data by showing that models\ntrained on MegaDepth exhibit strong generalization-not only to novel scenes,\nbut also to other diverse datasets including Make3D, KITTI, and DIW, even when\nno images from those datasets are seen during training.","url_abs":"http://arxiv.org/abs/1804.00607v4","url_pdf":"http://arxiv.org/pdf/1804.00607v4.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"megadepth-learning-single-view-depth","repo_url":"https://github.com/fabio-sim/DeDoDe-ONNX-TensorRT","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"megadepth-learning-single-view-depth","repo_url":"https://github.com/zhengqili/MegaDepth","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[{"slug":"megadepth","name":"MegaDepth","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1804.00607","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1804.00607"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/zhengqili/MegaDepth","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/fabio-sim/DeDoDe-ONNX-TensorRT","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":3},"by_repo_kind":{"listed":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"91d4d7845ec139d1","entry":"encode","repo":"zhengqili/MegaDepth","repo_kind":"listed","path":"util/png.py","file_url":"https://github.com/zhengqili/MegaDepth/blob/HEAD/util/png.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"91d4d7845ec139d1"}},{"code_sha256_prefix":"9fe591ca11b7e715","entry":"tensor2im","repo":"zhengqili/MegaDepth","repo_kind":"listed","path":"util/util.py","file_url":"https://github.com/zhengqili/MegaDepth/blob/HEAD/util/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9fe591ca11b7e715"}},{"code_sha256_prefix":"4f813f672cd81eda","entry":"varname","repo":"zhengqili/MegaDepth","repo_kind":"listed","path":"util/util.py","file_url":"https://github.com/zhengqili/MegaDepth/blob/HEAD/util/util.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4f813f672cd81eda"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}