{"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/megascenes-scene-level-view-synthesis-at","title":"MegaScenes: Scene-Level View Synthesis at Scale","arxiv_id":"2406.11819","date":"2024-06-17","proceeding":null,"authors":["Joseph Tung","Gene Chou","Ruojin Cai","Guandao Yang","Kai Zhang","Gordon Wetzstein","Bharath Hariharan","Noah Snavely"],"abstract":"Scene-level novel view synthesis (NVS) is fundamental to many vision and graphics applications. Recently, pose-conditioned diffusion models have led to significant progress by extracting 3D information from 2D foundation models, but these methods are limited by the lack of scene-level training data. Common dataset choices either consist of isolated objects (Objaverse), or of object-centric scenes with limited pose distributions (DTU, CO3D). In this paper, we create a large-scale scene-level dataset from Internet photo collections, called MegaScenes, which contains over 100K structure from motion (SfM) reconstructions from around the world. Internet photos represent a scalable data source but come with challenges such as lighting and transient objects. We address these issues to further create a subset suitable for the task of NVS. Additionally, we analyze failure cases of state-of-the-art NVS methods and significantly improve generation consistency. Through extensive experiments, we validate the effectiveness of both our dataset and method on generating in-the-wild scenes. For details on the dataset and code, see our project page at https://megascenes.github.io.","url_abs":"https://arxiv.org/abs/2406.11819v2","url_pdf":"https://arxiv.org/pdf/2406.11819v2.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":"megascenes-scene-level-view-synthesis-at","repo_url":"https://github.com/MegaScenes/nvs","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[{"method_slug":"diffusion","method_name":"Diffusion"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2406.11819","atlas_url":"https://app.syntology.ai/?focus=2406.11819","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.11819"}},"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/MegaScenes/nvs","reach":{"status":"ok"}}],"summary":{"ran":10},"by_repo_kind":{"official":{"samples":10,"ran":10,"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":10,"samples":[{"code_sha256_prefix":"15b3b40acf4a14d7","entry":"generate_faces","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/util_3dphoto.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/util_3dphoto.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"15b3b40acf4a14d7"}},{"code_sha256_prefix":"3c9275f3d3a4a00c","entry":"get_ccw_poses","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/evalhelpers.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/evalhelpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3c9275f3d3a4a00c"}},{"code_sha256_prefix":"041660706bfc8674","entry":"get_cw_poses","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/evalhelpers.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/evalhelpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"041660706bfc8674"}},{"code_sha256_prefix":"d13fb9a434edff4e","entry":"get_x_poses","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/evalhelpers.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/evalhelpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"d13fb9a434edff4e"}},{"code_sha256_prefix":"e7f18f4fc9687479","entry":"invert_depth","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/depth_helpers.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/depth_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e7f18f4fc9687479"}},{"code_sha256_prefix":"14306868defa0a72","entry":"load_img","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/data_helpers.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/data_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"14306868defa0a72"}},{"code_sha256_prefix":"993c90757e6f049f","entry":"load_img_and_transform","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/data_helpers.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/data_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"993c90757e6f049f"}},{"code_sha256_prefix":"8ff024de9a2540c2","entry":"resize_depth","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/util_3dphoto.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/util_3dphoto.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"8ff024de9a2540c2"}},{"code_sha256_prefix":"3a084b8ece1641e4","entry":"resize_rgb","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/util_3dphoto.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/util_3dphoto.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"3a084b8ece1641e4"}},{"code_sha256_prefix":"123cd98efa9b51d0","entry":"save_images_as_grid","repo":"MegaScenes/nvs","repo_kind":"official","path":"dataloader/data_helpers.py","file_url":"https://github.com/MegaScenes/nvs/blob/HEAD/dataloader/data_helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"123cd98efa9b51d0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}