{"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/deepstereo-learning-to-predict-new-views-from","title":"DeepStereo: Learning to Predict New Views from the World's Imagery","arxiv_id":"1506.06825","date":"2015-06-22","proceeding":"CVPR 2016 6","authors":["John Flynn","Ivan Neulander","James Philbin","Noah Snavely"],"abstract":"Deep networks have recently enjoyed enormous success when applied to\nrecognition and classification problems in computer vision, but their use in\ngraphics problems has been limited. In this work, we present a novel deep\narchitecture that performs new view synthesis directly from pixels, trained\nfrom a large number of posed image sets. In contrast to traditional approaches\nwhich consist of multiple complex stages of processing, each of which require\ncareful tuning and can fail in unexpected ways, our system is trained\nend-to-end. The pixels from neighboring views of a scene are presented to the\nnetwork which then directly produces the pixels of the unseen view. The\nbenefits of our approach include generality (we only require posed image sets\nand can easily apply our method to different domains), and high quality results\non traditionally difficult scenes. We believe this is due to the end-to-end\nnature of our system which is able to plausibly generate pixels according to\ncolor, depth, and texture priors learnt automatically from the training data.\nTo verify our method we show that it can convincingly reproduce known test\nviews from nearby imagery. Additionally we show images rendered from novel\nviewpoints. To our knowledge, our work is the first to apply deep learning to\nthe problem of new view synthesis from sets of real-world, natural imagery.","url_abs":"http://arxiv.org/abs/1506.06825v1","url_pdf":"http://arxiv.org/pdf/1506.06825v1.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":"deepstereo-learning-to-predict-new-views-from","repo_url":"https://github.com/imatge-upc/deep-stereo","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1506.06825","atlas_url":"https://app.syntology.ai/?focus=1506.06825","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1506.06825"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/imatge-upc/deep-stereo","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"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":"85b61872a0c4a910","entry":"conv_relu","repo":"imatge-upc/deep-stereo","repo_kind":"listed","path":"tf_deep_stereo/shared.py","file_url":"https://github.com/imatge-upc/deep-stereo/blob/HEAD/tf_deep_stereo/shared.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":"85b61872a0c4a910"}},{"code_sha256_prefix":"a6109cd930c92f5e","entry":"dotpMerge","repo":"imatge-upc/deep-stereo","repo_kind":"listed","path":"tf_deep_stereo/tf_train.py","file_url":"https://github.com/imatge-upc/deep-stereo/blob/HEAD/tf_deep_stereo/tf_train.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":"a6109cd930c92f5e"}},{"code_sha256_prefix":"f62c6b922d5a7d76","entry":"extract_multipatch","repo":"imatge-upc/deep-stereo","repo_kind":"listed","path":"dataset_preparation/kitti_generator.py","file_url":"https://github.com/imatge-upc/deep-stereo/blob/HEAD/dataset_preparation/kitti_generator.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":"f62c6b922d5a7d76"}},{"code_sha256_prefix":"e934d511180f83d7","entry":"extract_patch","repo":"imatge-upc/deep-stereo","repo_kind":"listed","path":"dataset_preparation/kitti_generator.py","file_url":"https://github.com/imatge-upc/deep-stereo/blob/HEAD/dataset_preparation/kitti_generator.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":"e934d511180f83d7"}},{"code_sha256_prefix":"9b34b039fbf3a4a1","entry":"input_definition","repo":"imatge-upc/deep-stereo","repo_kind":"listed","path":"tf_deep_stereo/shared.py","file_url":"https://github.com/imatge-upc/deep-stereo/blob/HEAD/tf_deep_stereo/shared.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":"9b34b039fbf3a4a1"}},{"code_sha256_prefix":"9fd7ac83ed1dac15","entry":"input_structure","repo":"imatge-upc/deep-stereo","repo_kind":"listed","path":"tf_deep_stereo/shared.py","file_url":"https://github.com/imatge-upc/deep-stereo/blob/HEAD/tf_deep_stereo/shared.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":"9fd7ac83ed1dac15"}},{"code_sha256_prefix":"d470d626451abf97","entry":"lossF","repo":"imatge-upc/deep-stereo","repo_kind":"listed","path":"tf_deep_stereo/tf_samplegraph.py","file_url":"https://github.com/imatge-upc/deep-stereo/blob/HEAD/tf_deep_stereo/tf_samplegraph.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":"d470d626451abf97"}},{"code_sha256_prefix":"10826b2c29b161c6","entry":"lossF","repo":"imatge-upc/deep-stereo","repo_kind":"listed","path":"tf_deep_stereo/tf_train.py","file_url":"https://github.com/imatge-upc/deep-stereo/blob/HEAD/tf_deep_stereo/tf_train.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":"10826b2c29b161c6"}},{"code_sha256_prefix":"6f096bdb5a8ec5c7","entry":"training","repo":"imatge-upc/deep-stereo","repo_kind":"listed","path":"tf_deep_stereo/tf_samplegraph.py","file_url":"https://github.com/imatge-upc/deep-stereo/blob/HEAD/tf_deep_stereo/tf_samplegraph.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":"6f096bdb5a8ec5c7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}