{"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/flexible-svbrdf-capture-with-a-multi-image","title":"Flexible SVBRDF Capture with a Multi-Image Deep Network","arxiv_id":"1906.11557","date":"2019-06-27","proceeding":null,"authors":["Valentin Deschaintre","Miika Aittala","Fredo Durand","George Drettakis","Adrien Bousseau"],"abstract":"Empowered by deep learning, recent methods for material capture can estimate a spatially-varying reflectance from a single photograph. Such lightweight capture is in stark contrast with the tens or hundreds of pictures required by traditional optimization-based approaches. However, a single image is often simply not enough to observe the rich appearance of real-world materials. We present a deep-learning method capable of estimating material appearance from a variable number of uncalibrated and unordered pictures captured with a handheld camera and flash. Thanks to an order-independent fusing layer, this architecture extracts the most useful information from each picture, while benefiting from strong priors learned from data. The method can handle both view and light direction variation without calibration. We show how our method improves its prediction with the number of input pictures, and reaches high quality reconstructions with as little as 1 to 10 images -- a sweet spot between existing single-image and complex multi-image approaches.","url_abs":"https://arxiv.org/abs/1906.11557v1","url_pdf":"https://arxiv.org/pdf/1906.11557v1.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":"links_only","authors_date_abstract":"arXiv metadata, CC0 1.0 (https://info.arxiv.org/help/license), from the Kaggle arXiv metadata snapshot of 2026-09-12"},"code_links":[{"paper_slug":"flexible-svbrdf-capture-with-a-multi-image","repo_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1906.11557","atlas_url":"https://app.syntology.ai/?focus=1906.11557","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.11557"}},"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/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":13},"by_repo_kind":{"official":{"samples":13,"ran":0,"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":"bc1449e0d61353bd","entry":"DX","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"losses.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/losses.py","link_basis":"first_harvest_node","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":"bc1449e0d61353bd"}},{"code_sha256_prefix":"1f22cdb833c3ea59","entry":"DY","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"losses.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/losses.py","link_basis":"first_harvest_node","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":"1f22cdb833c3ea59"}},{"code_sha256_prefix":"e09790ee3cfb8b4b","entry":"concatSplitInputs","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"testHelpers.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/testHelpers.py","link_basis":"first_harvest_node","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":"e09790ee3cfb8b4b"}},{"code_sha256_prefix":"efc97c64fefbb4e6","entry":"concat_tensor_display","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"testHelpers.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/testHelpers.py","link_basis":"first_harvest_node","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":"efc97c64fefbb4e6"}},{"code_sha256_prefix":"5d73b07504860cff","entry":"conv","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"tfHelpers.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/tfHelpers.py","link_basis":"first_harvest_node","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":"5d73b07504860cff"}},{"code_sha256_prefix":"0cb6d43ff89d5ab1","entry":"deconv","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"tfHelpers.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/tfHelpers.py","link_basis":"first_harvest_node","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":"0cb6d43ff89d5ab1"}},{"code_sha256_prefix":"ea769b80518d24b6","entry":"defaultScene","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"acquisitionScene.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/acquisitionScene.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":"ea769b80518d24b6"}},{"code_sha256_prefix":"75e40f81ebf8eab9","entry":"defaultSceneSpotLight","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"acquisitionScene.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/acquisitionScene.py","link_basis":"first_harvest_node","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":"75e40f81ebf8eab9"}},{"code_sha256_prefix":"4288f8e325eb43a4","entry":"deprocess","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/helpers.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":"4288f8e325eb43a4"}},{"code_sha256_prefix":"0a80ad08bd34d0c8","entry":"l1","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"losses.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/losses.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":"0a80ad08bd34d0c8"}},{"code_sha256_prefix":"fac0ec37a83fedc7","entry":"logTensor","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/helpers.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":"fac0ec37a83fedc7"}},{"code_sha256_prefix":"19af0fe9ccd63f6b","entry":"lrelu","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"tfHelpers.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/tfHelpers.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":"19af0fe9ccd63f6b"}},{"code_sha256_prefix":"7b296d580bba710b","entry":"preprocess","repo":"valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition","repo_kind":"official","path":"helpers.py","file_url":"https://github.com/valentin-deschaintre/multi-image-deepNet-SVBRDF-acquisition/blob/HEAD/helpers.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":"7b296d580bba710b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}