{"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/hnerv-a-hybrid-neural-representation-for","title":"HNeRV: A Hybrid Neural Representation for Videos","arxiv_id":"2304.02633","date":"2023-04-05","proceeding":"CVPR 2023 1","authors":["Hao Chen","Matt Gwilliam","Ser-Nam Lim","Abhinav Shrivastava"],"abstract":"Implicit neural representations store videos as neural networks and have performed well for various vision tasks such as video compression and denoising. With frame index or positional index as input, implicit representations (NeRV, E-NeRV, \\etc) reconstruct video from fixed and content-agnostic embeddings. Such embedding largely limits the regression capacity and internal generalization for video interpolation. In this paper, we propose a Hybrid Neural Representation for Videos (HNeRV), where a learnable encoder generates content-adaptive embeddings, which act as the decoder input. Besides the input embedding, we introduce HNeRV blocks, which ensure model parameters are evenly distributed across the entire network, such that higher layers (layers near the output) can have more capacity to store high-resolution content and video details. With content-adaptive embeddings and re-designed architecture, HNeRV outperforms implicit methods in video regression tasks for both reconstruction quality ($+4.7$ PSNR) and convergence speed ($16\\times$ faster), and shows better internal generalization. As a simple and efficient video representation, HNeRV also shows decoding advantages for speed, flexibility, and deployment, compared to traditional codecs~(H.264, H.265) and learning-based compression methods. Finally, we explore the effectiveness of HNeRV on downstream tasks such as video compression and video inpainting. We provide project page at https://haochen-rye.github.io/HNeRV, and Code at https://github.com/haochen-rye/HNeRV","url_abs":"https://arxiv.org/abs/2304.02633v1","url_pdf":"https://arxiv.org/pdf/2304.02633v1.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":"hnerv-a-hybrid-neural-representation-for","repo_url":"https://github.com/haochen-rye/hnerv","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"denoising","task_name":"Denoising"},{"task_slug":"video-compression","task_name":"Video Compression"},{"task_slug":"video-inpainting","task_name":"Video Inpainting"},{"task_slug":"video-reconstruction","task_name":"Video Reconstruction"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"speed","method_name":"SPEED"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/video-reconstruction-on-uvg","task":"Video Reconstruction","dataset":"UVG","model":"HNeRV","rank_in_archive_order":4,"of":7,"metrics":{"Average PSNR (dB)":"35.23","Model Size (M)":"12.87M"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2304.02633","atlas_url":"https://app.syntology.ai/?focus=2304.02633","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.02633"}},"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/haochen-rye/hnerv","reach":null}],"summary":{"ran_draft_wrong":1,"ran":6,"ran_fixture":1,"unverified":1},"by_repo_kind":{"official":{"samples":9,"ran":8,"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":9,"samples":[{"code_sha256_prefix":"2798c7e0f39b709e","entry":"ActivationLayer","repo":"haochen-rye/hnerv","repo_kind":"official","path":"model_all.py","file_url":"https://github.com/haochen-rye/hnerv/blob/HEAD/model_all.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2798c7e0f39b709e"}},{"code_sha256_prefix":"b0de12d36f1727f2","entry":"ConvNeXt","repo":"haochen-rye/hnerv","repo_kind":"official","path":"model_all.py","file_url":"https://github.com/haochen-rye/hnerv/blob/HEAD/model_all.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"b0de12d36f1727f2"}},{"code_sha256_prefix":"2f0b07dfa92f0524","entry":"DownConv","repo":"haochen-rye/hnerv","repo_kind":"official","path":"model_all.py","file_url":"https://github.com/haochen-rye/hnerv/blob/HEAD/model_all.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2f0b07dfa92f0524"}},{"code_sha256_prefix":"eec5f1dcb74ff87a","entry":"NeRVBlock","repo":"haochen-rye/hnerv","repo_kind":"official","path":"model_all.py","file_url":"https://github.com/haochen-rye/hnerv/blob/HEAD/model_all.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":"eec5f1dcb74ff87a"}},{"code_sha256_prefix":"7096d2bc3a411504","entry":"OutImg","repo":"haochen-rye/hnerv","repo_kind":"official","path":"model_all.py","file_url":"https://github.com/haochen-rye/hnerv/blob/HEAD/model_all.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7096d2bc3a411504"}},{"code_sha256_prefix":"bd7b495abeba892f","entry":"PositionEncoding","repo":"haochen-rye/hnerv","repo_kind":"official","path":"model_all.py","file_url":"https://github.com/haochen-rye/hnerv/blob/HEAD/model_all.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"bd7b495abeba892f"}},{"code_sha256_prefix":"6a4b88c02d94376c","entry":"Sin","repo":"haochen-rye/hnerv","repo_kind":"official","path":"model_all.py","file_url":"https://github.com/haochen-rye/hnerv/blob/HEAD/model_all.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6a4b88c02d94376c"}},{"code_sha256_prefix":"a44d6c3b8812b4e0","entry":"UpConv","repo":"haochen-rye/hnerv","repo_kind":"official","path":"model_all.py","file_url":"https://github.com/haochen-rye/hnerv/blob/HEAD/model_all.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"a44d6c3b8812b4e0"}},{"code_sha256_prefix":"e18cfef2479b9b91","entry":"HNeRV","repo":"haochen-rye/hnerv","repo_kind":"official","path":"model_all.py","file_url":"https://github.com/haochen-rye/hnerv/blob/HEAD/model_all.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e18cfef2479b9b91"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}