{"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/light-field-networks-neural-scene","title":"Light Field Networks: Neural Scene Representations with Single-Evaluation Rendering","arxiv_id":"2106.02634","date":"2021-06-04","proceeding":"NeurIPS 2021 12","authors":["Vincent Sitzmann","Semon Rezchikov","William T. Freeman","Joshua B. Tenenbaum","Fredo Durand"],"abstract":"Inferring representations of 3D scenes from 2D observations is a fundamental problem of computer graphics, computer vision, and artificial intelligence. Emerging 3D-structured neural scene representations are a promising approach to 3D scene understanding. In this work, we propose a novel neural scene representation, Light Field Networks or LFNs, which represent both geometry and appearance of the underlying 3D scene in a 360-degree, four-dimensional light field parameterized via a neural implicit representation. Rendering a ray from an LFN requires only a single network evaluation, as opposed to hundreds of evaluations per ray for ray-marching or volumetric based renderers in 3D-structured neural scene representations. In the setting of simple scenes, we leverage meta-learning to learn a prior over LFNs that enables multi-view consistent light field reconstruction from as little as a single image observation. This results in dramatic reductions in time and memory complexity, and enables real-time rendering. The cost of storing a 360-degree light field via an LFN is two orders of magnitude lower than conventional methods such as the Lumigraph. Utilizing the analytical differentiability of neural implicit representations and a novel parameterization of light space, we further demonstrate the extraction of sparse depth maps from LFNs.","url_abs":"https://arxiv.org/abs/2106.02634v2","url_pdf":"https://arxiv.org/pdf/2106.02634v2.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":"light-field-networks-neural-scene","repo_url":"https://github.com/vsitzmann/light-field-networks","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2106.02634","atlas_url":"https://app.syntology.ai/?focus=2106.02634","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.02634"}},"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/vsitzmann/light-field-networks","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":11},"by_repo_kind":{"listed":{"samples":11,"ran":11,"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":"39d9d9a53aa724b7","entry":"class_string_2_class_id","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"multiclass_dataio.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/multiclass_dataio.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":"39d9d9a53aa724b7"}},{"code_sha256_prefix":"43f00a2b03f12c8a","entry":"closest_to_origin","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"geometry.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/geometry.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":"43f00a2b03f12c8a"}},{"code_sha256_prefix":"b37c86f63a99f99a","entry":"get_num_instances","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"hdf5_dataio.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/hdf5_dataio.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":"b37c86f63a99f99a"}},{"code_sha256_prefix":"3e1e570476a17777","entry":"get_num_instances","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"multiclass_dataio.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/multiclass_dataio.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3e1e570476a17777"}},{"code_sha256_prefix":"63cb0313b04ef0e5","entry":"get_ray_origin","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"geometry.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/geometry.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"63cb0313b04ef0e5"}},{"code_sha256_prefix":"e044b869782c53a7","entry":"image_loss","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"loss_functions.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/loss_functions.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":"e044b869782c53a7"}},{"code_sha256_prefix":"83666af2324d73b9","entry":"load_depth","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"data_util.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/data_util.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":"83666af2324d73b9"}},{"code_sha256_prefix":"313ece65b8317903","entry":"load_pose","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"data_util.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/data_util.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":"313ece65b8317903"}},{"code_sha256_prefix":"0952740a9ea73ed3","entry":"load_rgb","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"data_util.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/data_util.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":"0952740a9ea73ed3"}},{"code_sha256_prefix":"943737ea63cae867","entry":"normalize_imagenet","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"conv_modules.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/conv_modules.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"943737ea63cae867"}},{"code_sha256_prefix":"1879debc023ea214","entry":"plucker_embedding","repo":"vsitzmann/light-field-networks","repo_kind":"listed","path":"geometry.py","file_url":"https://github.com/vsitzmann/light-field-networks/blob/HEAD/geometry.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1879debc023ea214"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}