{"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/through-the-looking-glass-neural-3d","title":"Through the Looking Glass: Neural 3D Reconstruction of Transparent Shapes","arxiv_id":"2004.10904","date":"2020-04-22","proceeding":"CVPR 2020 6","authors":["Zhengqin Li","Yu-Ying Yeh","Manmohan Chandraker"],"abstract":"Recovering the 3D shape of transparent objects using a small number of unconstrained natural images is an ill-posed problem. Complex light paths induced by refraction and reflection have prevented both traditional and deep multiview stereo from solving this challenge. We propose a physically-based network to recover 3D shape of transparent objects using a few images acquired with a mobile phone camera, under a known but arbitrary environment map. Our novel contributions include a normal representation that enables the network to model complex light transport through local computation, a rendering layer that models refractions and reflections, a cost volume specifically designed for normal refinement of transparent shapes and a feature mapping based on predicted normals for 3D point cloud reconstruction. We render a synthetic dataset to encourage the model to learn refractive light transport across different views. Our experiments show successful recovery of high-quality 3D geometry for complex transparent shapes using as few as 5-12 natural images. Code and data are publicly released.","url_abs":"https://arxiv.org/abs/2004.10904v2","url_pdf":"https://arxiv.org/pdf/2004.10904v2.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":"through-the-looking-glass-neural-3d","repo_url":"https://github.com/lzqsd/TransparentShapeReconstruction","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"3d-point-cloud-reconstruction","task_name":"3D Point Cloud Reconstruction"},{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"},{"task_slug":"3d-geometry","task_name":"3D geometry"},{"task_slug":"point-cloud-reconstruction","task_name":"Point cloud reconstruction"},{"task_slug":"transparent-objects","task_name":"Transparent objects"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2004.10904","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2004.10904"}},"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/lzqsd/TransparentShapeReconstruction","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_fixture":3,"unverified":3},"by_repo_kind":{"official":{"samples":6,"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":0,"samples":[{"code_sha256_prefix":"b9f3546dde325b9a","entry":"farthest_point_sample","repo":"lzqsd/TransparentShapeReconstruction","repo_kind":"official","path":"PointCloud/model/pointnet_util.py","file_url":"https://github.com/lzqsd/TransparentShapeReconstruction/blob/HEAD/PointCloud/model/pointnet_util.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b9f3546dde325b9a"}},{"code_sha256_prefix":"573cb024ea47999f","entry":"index_points","repo":"lzqsd/TransparentShapeReconstruction","repo_kind":"official","path":"PointCloud/model/pointnet_util.py","file_url":"https://github.com/lzqsd/TransparentShapeReconstruction/blob/HEAD/PointCloud/model/pointnet_util.py","link_basis":"plan_row","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"573cb024ea47999f"}},{"code_sha256_prefix":"580dee6761649b29","entry":"square_distance","repo":"lzqsd/TransparentShapeReconstruction","repo_kind":"official","path":"PointCloud/model/pointnet_util.py","file_url":"https://github.com/lzqsd/TransparentShapeReconstruction/blob/HEAD/PointCloud/model/pointnet_util.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"580dee6761649b29"}},{"code_sha256_prefix":"72e4a5120dccb21a","entry":"computeConfMap","repo":"lzqsd/TransparentShapeReconstruction","repo_kind":"official","path":"Normal/utils.py","file_url":"https://github.com/lzqsd/TransparentShapeReconstruction/blob/HEAD/Normal/utils.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":"72e4a5120dccb21a"}},{"code_sha256_prefix":"81b8291587867ae8","entry":"normalErrToColorMap","repo":"lzqsd/TransparentShapeReconstruction","repo_kind":"official","path":"Normal/utils.py","file_url":"https://github.com/lzqsd/TransparentShapeReconstruction/blob/HEAD/Normal/utils.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":"81b8291587867ae8"}},{"code_sha256_prefix":"cafb69a3d8bb9e39","entry":"turnErrorIntoNumpy","repo":"lzqsd/TransparentShapeReconstruction","repo_kind":"official","path":"Normal/utils.py","file_url":"https://github.com/lzqsd/TransparentShapeReconstruction/blob/HEAD/Normal/utils.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":"cafb69a3d8bb9e39"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}