{"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/f-b-alpha-matting","title":"$F$, $B$, Alpha Matting","arxiv_id":"2003.07711","date":"2020-03-17","proceeding":null,"authors":["Marco Forte","François Pitié"],"abstract":"Cutting out an object and estimating its opacity mask, known as image matting, is a key task in many image editing applications. Deep learning approaches have made significant progress by adapting the encoder-decoder architecture of segmentation networks. However, most of the existing networks only predict the alpha matte and post-processing methods must then be used to recover the original foreground and background colours in the transparent regions. Recently, two methods have shown improved results by also estimating the foreground colours, but at a significant computational and memory cost. In this paper, we propose a low-cost modification to alpha matting networks to also predict the foreground and background colours. We study variations of the training regime and explore a wide range of existing and novel loss functions for the joint prediction. Our method achieves the state of the art performance on the Adobe Composition-1k dataset for alpha matte and composite colour quality. It is also the current best performing method on the alphamatting.com online evaluation.","url_abs":"https://arxiv.org/abs/2003.07711v1","url_pdf":"https://arxiv.org/pdf/2003.07711v1.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":"f-b-alpha-matting","repo_url":"https://github.com/MarcoForte/FBA-Matting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"f-b-alpha-matting","repo_url":"https://github.com/marcoforte/fba_matting","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"image-matting","task_name":"Image Matting"}],"methods":[{"method_slug":"lfpnet-tta","method_name":"LFPNet (TTA)"}],"datasets_introduced":[],"methods_introduced":[{"slug":"lfpnet-tta","name":"LFPNet (TTA)","full_name":"LFPNet with test time augmentation"}],"results":[{"leaderboard":"/sota/image-matting-on-composition-1k-1","task":"Image Matting","dataset":"Composition-1K","model":"FBAMatting","rank_in_archive_order":8,"of":13,"metrics":{"Conn":"21.5","Grad":"10.6","MSE":"5.3","SAD":"26.4"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.07711","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.07711"}},"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/MarcoForte/FBA-Matting","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/marcoforte/fba_matting","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":6},"by_repo_kind":{"listed":{"samples":7,"ran":1,"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":"fac5364e2f53c6db","entry":"conv3x3","repo":"MarcoForte/FBA-Matting","repo_kind":"listed","path":"networks/resnet_bn.py","file_url":"https://github.com/MarcoForte/FBA-Matting/blob/HEAD/networks/resnet_bn.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fac5364e2f53c6db"}},{"code_sha256_prefix":"0e62194a5993e8a5","entry":"dt","repo":"MarcoForte/FBA-Matting","repo_kind":"listed","path":"networks/transforms.py","file_url":"https://github.com/MarcoForte/FBA-Matting/blob/HEAD/networks/transforms.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":"0e62194a5993e8a5"}},{"code_sha256_prefix":"654781286b8ec328","entry":"fba_fusion","repo":"MarcoForte/FBA-Matting","repo_kind":"listed","path":"networks/models.py","file_url":"https://github.com/MarcoForte/FBA-Matting/blob/HEAD/networks/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":"654781286b8ec328"}},{"code_sha256_prefix":"ae4cb5a004002b75","entry":"norm","repo":"MarcoForte/FBA-Matting","repo_kind":"listed","path":"networks/layers_WS.py","file_url":"https://github.com/MarcoForte/FBA-Matting/blob/HEAD/networks/layers_WS.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":"ae4cb5a004002b75"}},{"code_sha256_prefix":"4870b97151f983af","entry":"read_image","repo":"MarcoForte/FBA-Matting","repo_kind":"listed","path":"dataloader.py","file_url":"https://github.com/MarcoForte/FBA-Matting/blob/HEAD/dataloader.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":"4870b97151f983af"}},{"code_sha256_prefix":"02c2d24a82390ae0","entry":"read_trimap","repo":"MarcoForte/FBA-Matting","repo_kind":"listed","path":"dataloader.py","file_url":"https://github.com/MarcoForte/FBA-Matting/blob/HEAD/dataloader.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":"02c2d24a82390ae0"}},{"code_sha256_prefix":"c3e008bd64313608","entry":"trimap_transform","repo":"MarcoForte/FBA-Matting","repo_kind":"listed","path":"networks/transforms.py","file_url":"https://github.com/MarcoForte/FBA-Matting/blob/HEAD/networks/transforms.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":"c3e008bd64313608"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}