{"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/octnetfusion-learning-depth-fusion-from-data","title":"OctNetFusion: Learning Depth Fusion from Data","arxiv_id":"1704.01047","date":"2017-04-04","proceeding":null,"authors":["Gernot Riegler","Ali Osman Ulusoy","Horst Bischof","Andreas Geiger"],"abstract":"In this paper, we present a learning based approach to depth fusion, i.e.,\ndense 3D reconstruction from multiple depth images. The most common approach to\ndepth fusion is based on averaging truncated signed distance functions, which\nwas originally proposed by Curless and Levoy in 1996. While this method is\nsimple and provides great results, it is not able to reconstruct (partially)\noccluded surfaces and requires a large number frames to filter out sensor noise\nand outliers. Motivated by the availability of large 3D model repositories and\nrecent advances in deep learning, we present a novel 3D CNN architecture that\nlearns to predict an implicit surface representation from the input depth maps.\nOur learning based method significantly outperforms the traditional volumetric\nfusion approach in terms of noise reduction and outlier suppression. By\nlearning the structure of real world 3D objects and scenes, our approach is\nfurther able to reconstruct occluded regions and to fill in gaps in the\nreconstruction. We demonstrate that our learning based approach outperforms\nboth vanilla TSDF fusion as well as TV-L1 fusion on the task of volumetric\nfusion. Further, we demonstrate state-of-the-art 3D shape completion results.","url_abs":"http://arxiv.org/abs/1704.01047v3","url_pdf":"http://arxiv.org/pdf/1704.01047v3.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":"octnetfusion-learning-depth-fusion-from-data","repo_url":"https://github.com/griegler/octnetfusion","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"3d-reconstruction","task_name":"3D Reconstruction"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1704.01047","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1704.01047"}},"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/griegler/octnetfusion","reach":null}],"summary":{"ran_honours":1},"by_repo_kind":{"official":{"samples":1,"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":"454d683edd688589","entry":"load_values","repo":"griegler/octnetfusion","repo_kind":"official","path":"src/completion_common.py","file_url":"https://github.com/griegler/octnetfusion/blob/HEAD/src/completion_common.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":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"454d683edd688589"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}