{"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/bifuse-self-supervised-and-efficient-bi","title":"BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation","arxiv_id":"2209.02952","date":"2022-09-07","proceeding":null,"authors":["Fu-En Wang","Yu-Hsuan Yeh","Yi-Hsuan Tsai","Wei-Chen Chiu","Min Sun"],"abstract":"Due to the rise of spherical cameras, monocular 360 depth estimation becomes an important technique for many applications (e.g., autonomous systems). Thus, state-of-the-art frameworks for monocular 360 depth estimation such as bi-projection fusion in BiFuse are proposed. To train such a framework, a large number of panoramas along with the corresponding depth ground truths captured by laser sensors are required, which highly increases the cost of data collection. Moreover, since such a data collection procedure is time-consuming, the scalability of extending these methods to different scenes becomes a challenge. To this end, self-training a network for monocular depth estimation from 360 videos is one way to alleviate this issue. However, there are no existing frameworks that incorporate bi-projection fusion into the self-training scheme, which highly limits the self-supervised performance since bi-projection fusion can leverage information from different projection types. In this paper, we propose BiFuse++ to explore the combination of bi-projection fusion and the self-training scenario. To be specific, we propose a new fusion module and Contrast-Aware Photometric Loss to improve the performance of BiFuse and increase the stability of self-training on real-world videos. We conduct both supervised and self-supervised experiments on benchmark datasets and achieve state-of-the-art performance.","url_abs":"https://arxiv.org/abs/2209.02952v1","url_pdf":"https://arxiv.org/pdf/2209.02952v1.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":"bifuse-self-supervised-and-efficient-bi","repo_url":"https://github.com/fuenwang/bifusev2","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"monocular-depth-estimation","task_name":"Monocular Depth Estimation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/depth-estimation-on-stanford2d3d-panoramic","task":"Depth Estimation","dataset":"Stanford2D3D Panoramic","model":"BiFuse++","rank_in_archive_order":12,"of":18,"metrics":{"RMSE":"0.372","absolute relative error":"0.1117"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2209.02952","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2209.02952"}},"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/fuenwang/bifusev2","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"unverified":12},"by_repo_kind":{"official":{"samples":13,"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":"f6b944f50d3f15ae","entry":"count_parameters","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Tools.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Tools.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6b944f50d3f15ae"}},{"code_sha256_prefix":"2c5143fd039915ad","entry":"ContrastNormalize","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Loss/ContrastLoss.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Loss/ContrastLoss.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":"2c5143fd039915ad"}},{"code_sha256_prefix":"8cc9e684434f4bf2","entry":"SampleEuler","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Dataset/SelfSupervisedDataset.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Dataset/SelfSupervisedDataset.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":"8cc9e684434f4bf2"}},{"code_sha256_prefix":"ab0422c369265bf8","entry":"XY2lonlat","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Conversion/EquirecCoordinate.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Conversion/EquirecCoordinate.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":"ab0422c369265bf8"}},{"code_sha256_prefix":"5907af8147d2f4bc","entry":"XY2xyz","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Conversion/EquirecCoordinate.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Conversion/EquirecCoordinate.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":"5907af8147d2f4bc"}},{"code_sha256_prefix":"91e776e82a7e5a28","entry":"explainability_loss","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Loss/BasePhotometric.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Loss/BasePhotometric.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":"91e776e82a7e5a28"}},{"code_sha256_prefix":"01c030cf93556fc0","entry":"homogeneous","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Conversion/MatrixTools.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Conversion/MatrixTools.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":"01c030cf93556fc0"}},{"code_sha256_prefix":"4907f6ce41bc7042","entry":"lonlat2xyz","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Conversion/EquirecCoordinate.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Conversion/EquirecCoordinate.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":"4907f6ce41bc7042"}},{"code_sha256_prefix":"9ac2a3c4a05a69ae","entry":"normalizeDepth","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Tools.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Tools.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":"9ac2a3c4a05a69ae"}},{"code_sha256_prefix":"b1eafd66a813f82b","entry":"readDepth","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Dataset/SelfSupervisedDataset.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Dataset/SelfSupervisedDataset.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":"b1eafd66a813f82b"}},{"code_sha256_prefix":"979f9e55e5e97982","entry":"readImage","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Dataset/SelfSupervisedDataset.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Dataset/SelfSupervisedDataset.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":"979f9e55e5e97982"}},{"code_sha256_prefix":"44925cf3831bfe79","entry":"rgetattr","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Tools.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Tools.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":"44925cf3831bfe79"}},{"code_sha256_prefix":"70940e6ebfba5336","entry":"smooth_loss","repo":"fuenwang/bifusev2","repo_kind":"official","path":"BiFusev2/Loss/BasePhotometric.py","file_url":"https://github.com/fuenwang/bifusev2/blob/HEAD/BiFusev2/Loss/BasePhotometric.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":"70940e6ebfba5336"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}