{"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/hypernerf-a-higher-dimensional-representation","title":"HyperNeRF: A Higher-Dimensional Representation for Topologically Varying Neural Radiance Fields","arxiv_id":"2106.13228","date":"2021-06-24","proceeding":null,"authors":["Keunhong Park","Utkarsh Sinha","Peter Hedman","Jonathan T. Barron","Sofien Bouaziz","Dan B Goldman","Ricardo Martin-Brualla","Steven M. Seitz"],"abstract":"Neural Radiance Fields (NeRF) are able to reconstruct scenes with unprecedented fidelity, and various recent works have extended NeRF to handle dynamic scenes. A common approach to reconstruct such non-rigid scenes is through the use of a learned deformation field mapping from coordinates in each input image into a canonical template coordinate space. However, these deformation-based approaches struggle to model changes in topology, as topological changes require a discontinuity in the deformation field, but these deformation fields are necessarily continuous. We address this limitation by lifting NeRFs into a higher dimensional space, and by representing the 5D radiance field corresponding to each individual input image as a slice through this \"hyper-space\". Our method is inspired by level set methods, which model the evolution of surfaces as slices through a higher dimensional surface. We evaluate our method on two tasks: (i) interpolating smoothly between \"moments\", i.e., configurations of the scene, seen in the input images while maintaining visual plausibility, and (ii) novel-view synthesis at fixed moments. We show that our method, which we dub HyperNeRF, outperforms existing methods on both tasks. Compared to Nerfies, HyperNeRF reduces average error rates by 4.1% for interpolation and 8.6% for novel-view synthesis, as measured by LPIPS. Additional videos, results, and visualizations are available at https://hypernerf.github.io.","url_abs":"https://arxiv.org/abs/2106.13228v2","url_pdf":"https://arxiv.org/pdf/2106.13228v2.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":"hypernerf-a-higher-dimensional-representation","repo_url":"https://github.com/google/hypernerf","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"jax","reach":null},{"paper_slug":"hypernerf-a-higher-dimensional-representation","repo_url":"https://github.com/songrise/HyperNeRF-torch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"dynamic-reconstruction","task_name":"Dynamic Reconstruction"},{"task_slug":"nerf","task_name":"NeRF"},{"task_slug":"novel-view-synthesis","task_name":"Novel View Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/dynamic-reconstruction-on-iphone-dataset","task":"Dynamic Reconstruction","dataset":"iPhone (Monocular Dynamic View Synthesis)","model":"HyperNeRF","rank_in_archive_order":3,"of":7,"metrics":{"LPIPS":"0.51"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.13228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.13228"}},"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/google/hypernerf","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/songrise/HyperNeRF-torch","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"unverified":14},"by_repo_kind":{"listed":{"samples":15,"ran":1,"repositories":2}},"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":"5759498c262e96a8","entry":"filter_sigma","repo":"google/hypernerf","repo_kind":"listed","path":"hypernerf/models.py","file_url":"https://github.com/google/hypernerf/blob/HEAD/hypernerf/models.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5759498c262e96a8"}},{"code_sha256_prefix":"de7f6494f81eec14","entry":"filter_sigma","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/models.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/models.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":"de7f6494f81eec14"}},{"code_sha256_prefix":"b40a11a1f283ae21","entry":"get_norm_layer","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/modules.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/modules.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":"b40a11a1f283ae21"}},{"code_sha256_prefix":"716a1b1a799842f1","entry":"im","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/quaternion.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/quaternion.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":"716a1b1a799842f1"}},{"code_sha256_prefix":"bb54387d604c4be0","entry":"matmul","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/rigid_body.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/rigid_body.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":"bb54387d604c4be0"}},{"code_sha256_prefix":"c832923b546e9fb3","entry":"mse","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"metrics.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/metrics.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":"c832923b546e9fb3"}},{"code_sha256_prefix":"8a99c52cce39071b","entry":"piecewise_constant_pdf","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/model_utils.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/model_utils.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":"8a99c52cce39071b"}},{"code_sha256_prefix":"b5b388448f22219a","entry":"psnr","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"metrics.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/metrics.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":"b5b388448f22219a"}},{"code_sha256_prefix":"aa14ef5c29cc6bf5","entry":"re","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/quaternion.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/quaternion.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":"aa14ef5c29cc6bf5"}},{"code_sha256_prefix":"4ccc04a19903a881","entry":"rp_to_se3","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/rigid_body.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/rigid_body.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":"4ccc04a19903a881"}},{"code_sha256_prefix":"f2df2a98d9c97d7f","entry":"safe_acos","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/quaternion.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/quaternion.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":"f2df2a98d9c97d7f"}},{"code_sha256_prefix":"e38315d5f89ab19f","entry":"sample_along_rays","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/model_utils.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/model_utils.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":"e38315d5f89ab19f"}},{"code_sha256_prefix":"bc2fe5051710c834","entry":"skew","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/rigid_body.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/rigid_body.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":"bc2fe5051710c834"}},{"code_sha256_prefix":"895ffdb66b75e1b4","entry":"ssim","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"metrics.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/metrics.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":"895ffdb66b75e1b4"}},{"code_sha256_prefix":"0bb57f70ad847b9a","entry":"volumetric_rendering","repo":"songrise/HyperNeRF-torch","repo_kind":"listed","path":"hypernerf/model_utils.py","file_url":"https://github.com/songrise/HyperNeRF-torch/blob/HEAD/hypernerf/model_utils.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":"0bb57f70ad847b9a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}