{"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/graf-generative-radiance-fields-for-3d-aware","title":"GRAF: Generative Radiance Fields for 3D-Aware Image Synthesis","arxiv_id":"2007.02442","date":"2020-07-05","proceeding":"NeurIPS 2020 12","authors":["Katja Schwarz","Yiyi Liao","Michael Niemeyer","Andreas Geiger"],"abstract":"While 2D generative adversarial networks have enabled high-resolution image synthesis, they largely lack an understanding of the 3D world and the image formation process. Thus, they do not provide precise control over camera viewpoint or object pose. To address this problem, several recent approaches leverage intermediate voxel-based representations in combination with differentiable rendering. However, existing methods either produce low image resolution or fall short in disentangling camera and scene properties, e.g., the object identity may vary with the viewpoint. In this paper, we propose a generative model for radiance fields which have recently proven successful for novel view synthesis of a single scene. In contrast to voxel-based representations, radiance fields are not confined to a coarse discretization of the 3D space, yet allow for disentangling camera and scene properties while degrading gracefully in the presence of reconstruction ambiguity. By introducing a multi-scale patch-based discriminator, we demonstrate synthesis of high-resolution images while training our model from unposed 2D images alone. We systematically analyze our approach on several challenging synthetic and real-world datasets. Our experiments reveal that radiance fields are a powerful representation for generative image synthesis, leading to 3D consistent models that render with high fidelity.","url_abs":"https://arxiv.org/abs/2007.02442v4","url_pdf":"https://arxiv.org/pdf/2007.02442v4.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":"graf-generative-radiance-fields-for-3d-aware","repo_url":"https://github.com/autonomousvision/graf","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-aware-image-synthesis","task_name":"3D-Aware Image Synthesis"},{"task_slug":"image-generation","task_name":"Image Generation"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"},{"task_slug":"scene-generation","task_name":"Scene Generation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-generation-on-avd","task":"Scene Generation","dataset":"AVD","model":"GRAF","rank_in_archive_order":2,"of":3,"metrics":{"FID":"62.59","SwAV-FID":"6.95"},"uses_additional_data":false},{"leaderboard":"/sota/scene-generation-on-replica","task":"Scene Generation","dataset":"Replica","model":"GRAF","rank_in_archive_order":2,"of":3,"metrics":{"FID":"65.37","SwAV-FID":"5.76"},"uses_additional_data":false},{"leaderboard":"/sota/scene-generation-on-vizdoom","task":"Scene Generation","dataset":"VizDoom","model":"GRAF","rank_in_archive_order":2,"of":3,"metrics":{"FID":"47.50","SwAV-FID":"5.44"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2007.02442","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2007.02442"}},"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/autonomousvision/graf","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran":1,"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":12,"ran":3,"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":"1d6f8390d799f055","entry":"normalize","repo":"autonomousvision/graf","repo_kind":"official","path":"submodules/nerf_pytorch/load_llff.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/submodules/nerf_pytorch/load_llff.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1d6f8390d799f055"}},{"code_sha256_prefix":"8313c1fb69b28c8e","entry":"pose_spherical","repo":"autonomousvision/graf","repo_kind":"official","path":"submodules/nerf_pytorch/load_blender.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/submodules/nerf_pytorch/load_blender.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8313c1fb69b28c8e"}},{"code_sha256_prefix":"aa52acee18f54d38","entry":"viewmatrix","repo":"autonomousvision/graf","repo_kind":"official","path":"submodules/nerf_pytorch/load_llff.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/submodules/nerf_pytorch/load_llff.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"aa52acee18f54d38"}},{"code_sha256_prefix":"71ec2a9308fa61f3","entry":"color_depth_map","repo":"autonomousvision/graf","repo_kind":"official","path":"graf/utils.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/graf/utils.py","link_basis":"first_harvest_node","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":"71ec2a9308fa61f3"}},{"code_sha256_prefix":"7de1ceff1fdc469d","entry":"count_trainable_parameters","repo":"autonomousvision/graf","repo_kind":"official","path":"graf/utils.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/graf/utils.py","link_basis":"first_harvest_node","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":"7de1ceff1fdc469d"}},{"code_sha256_prefix":"856b87aabeff2342","entry":"get_data","repo":"autonomousvision/graf","repo_kind":"official","path":"graf/config.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/graf/config.py","link_basis":"first_harvest_node","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":"856b87aabeff2342"}},{"code_sha256_prefix":"4cbceee1eebaf6d4","entry":"get_nsamples","repo":"autonomousvision/graf","repo_kind":"official","path":"graf/utils.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/graf/utils.py","link_basis":"first_harvest_node","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":"4cbceee1eebaf6d4"}},{"code_sha256_prefix":"677c56fac6ae59a2","entry":"get_render_poses","repo":"autonomousvision/graf","repo_kind":"official","path":"graf/config.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/graf/config.py","link_basis":"first_harvest_node","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":"677c56fac6ae59a2"}},{"code_sha256_prefix":"83ed66ae61279dbc","entry":"load_blender_data","repo":"autonomousvision/graf","repo_kind":"official","path":"submodules/nerf_pytorch/load_blender.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/submodules/nerf_pytorch/load_blender.py","link_basis":"first_harvest_node","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":"83ed66ae61279dbc"}},{"code_sha256_prefix":"e69746042397f344","entry":"load_dv_data","repo":"autonomousvision/graf","repo_kind":"official","path":"submodules/nerf_pytorch/load_deepvoxels.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/submodules/nerf_pytorch/load_deepvoxels.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":"e69746042397f344"}},{"code_sha256_prefix":"36f5de7a0aae4a9b","entry":"ptstocam","repo":"autonomousvision/graf","repo_kind":"official","path":"submodules/nerf_pytorch/load_llff.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/submodules/nerf_pytorch/load_llff.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":"36f5de7a0aae4a9b"}},{"code_sha256_prefix":"559fa10dfa807ea5","entry":"update_config","repo":"autonomousvision/graf","repo_kind":"official","path":"graf/config.py","file_url":"https://github.com/autonomousvision/graf/blob/HEAD/graf/config.py","link_basis":"first_harvest_node","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":"559fa10dfa807ea5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}