{"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/pixel-adaptive-convolutional-neural-networks","title":"Pixel-Adaptive Convolutional Neural Networks","arxiv_id":"1904.05373","date":"2019-04-10","proceeding":"CVPR 2019 6","authors":["Hang Su","Varun Jampani","Deqing Sun","Orazio Gallo","Erik Learned-Miller","Jan Kautz"],"abstract":"Convolutions are the fundamental building block of CNNs. The fact that their\nweights are spatially shared is one of the main reasons for their widespread\nuse, but it also is a major limitation, as it makes convolutions content\nagnostic. We propose a pixel-adaptive convolution (PAC) operation, a simple yet\neffective modification of standard convolutions, in which the filter weights\nare multiplied with a spatially-varying kernel that depends on learnable, local\npixel features. PAC is a generalization of several popular filtering techniques\nand thus can be used for a wide range of use cases. Specifically, we\ndemonstrate state-of-the-art performance when PAC is used for deep joint image\nupsampling. PAC also offers an effective alternative to fully-connected CRF\n(Full-CRF), called PAC-CRF, which performs competitively, while being\nconsiderably faster. In addition, we also demonstrate that PAC can be used as a\ndrop-in replacement for convolution layers in pre-trained networks, resulting\nin consistent performance improvements.","url_abs":"http://arxiv.org/abs/1904.05373v1","url_pdf":"http://arxiv.org/pdf/1904.05373v1.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":"pixel-adaptive-convolutional-neural-networks","repo_url":"https://github.com/NVlabs/pacnet","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"pixel-adaptive-convolutional-neural-networks","repo_url":"https://github.com/ChristophReich1996/Cell-DETR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.05373","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1904.05373"}},"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/NVlabs/pacnet","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ChristophReich1996/Cell-DETR","reach":{"status":"unanswered"}}],"summary":{"ran_fixture":1,"ran_draft_wrong":1,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"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":4,"samples":[{"code_sha256_prefix":"948661398cb84403","entry":"create_YXRGB","repo":"NVlabs/pacnet","repo_kind":"official","path":"paccrf.py","file_url":"https://github.com/NVlabs/pacnet/blob/HEAD/paccrf.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"948661398cb84403"}},{"code_sha256_prefix":"bb6fa04316fd8a74","entry":"create_position_feats","repo":"NVlabs/pacnet","repo_kind":"official","path":"paccrf.py","file_url":"https://github.com/NVlabs/pacnet/blob/HEAD/paccrf.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"bb6fa04316fd8a74"}},{"code_sha256_prefix":"d985604991eca41c","entry":"np_gaussian_2d","repo":"NVlabs/pacnet","repo_kind":"official","path":"pac.py","file_url":"https://github.com/NVlabs/pacnet/blob/HEAD/pac.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"d985604991eca41c"}},{"code_sha256_prefix":"a0f6984ad221e04d","entry":"nd2col","repo":"NVlabs/pacnet","repo_kind":"official","path":"pac.py","file_url":"https://github.com/NVlabs/pacnet/blob/HEAD/pac.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"a0f6984ad221e04d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}