{"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/learning-3d-semantics-from-pose-noisy-2d","title":"Learning 3D Semantics from Pose-Noisy 2D Images with Hierarchical Full Attention Network","arxiv_id":"2204.08084","date":"2022-04-17","proceeding":null,"authors":["Yuhang He","Lin Chen","Junkun Xie","Long Chen"],"abstract":"We propose a novel framework to learn 3D point cloud semantics from 2D multi-view image observations containing pose error. On the one hand, directly learning from the massive, unstructured and unordered 3D point cloud is computationally and algorithmically more difficult than learning from compactly-organized and context-rich 2D RGB images. On the other hand, both LiDAR point cloud and RGB images are captured in standard automated-driving datasets. This motivates us to conduct a \"task transfer\" paradigm so that 3D semantic segmentation benefits from aggregating 2D semantic cues, albeit pose noises are contained in 2D image observations. Among all difficulties, pose noise and erroneous prediction from 2D semantic segmentation approaches are the main challenges for the task transfer. To alleviate the influence of those factor, we perceive each 3D point using multi-view images and for each single image a patch observation is associated. Moreover, the semantic labels of a block of neighboring 3D points are predicted simultaneously, enabling us to exploit the point structure prior to further improve the performance. A hierarchical full attention network~(HiFANet) is designed to sequentially aggregates patch, bag-of-frames and inter-point semantic cues, with hierarchical attention mechanism tailored for different level of semantic cues. Also, each preceding attention block largely reduces the feature size before feeding to the next attention block, making our framework slim. Experiment results on Semantic-KITTI show that the proposed framework outperforms existing 3D point cloud based methods significantly, it requires much less training data and exhibits tolerance to pose noise. The code is available at https://github.com/yuhanghe01/HiFANet.","url_abs":"https://arxiv.org/abs/2204.08084v3","url_pdf":"https://arxiv.org/pdf/2204.08084v3.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":"learning-3d-semantics-from-pose-noisy-2d","repo_url":"https://github.com/yuhanghe01/hifanet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"2d-semantic-segmentation","task_name":"2D Semantic Segmentation"},{"task_slug":"3d-semantic-segmentation","task_name":"3D Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.08084","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08084"}},"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/yuhanghe01/hifanet","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":6},"by_repo_kind":{"official":{"samples":6,"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":"d3b9fb0a177b614e","entry":"float_to_rgb","repo":"yuhanghe01/hifanet","repo_kind":"official","path":"proj_pcd2img.py","file_url":"https://github.com/yuhanghe01/hifanet/blob/HEAD/proj_pcd2img.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d3b9fb0a177b614e"}},{"code_sha256_prefix":"f1418856218cb689","entry":"parse_calibration","repo":"yuhanghe01/hifanet","repo_kind":"official","path":"generate_sequential.py","file_url":"https://github.com/yuhanghe01/hifanet/blob/HEAD/generate_sequential.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f1418856218cb689"}},{"code_sha256_prefix":"3821b84b3b5bea2c","entry":"parse_poses","repo":"yuhanghe01/hifanet","repo_kind":"official","path":"generate_sequential.py","file_url":"https://github.com/yuhanghe01/hifanet/blob/HEAD/generate_sequential.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3821b84b3b5bea2c"}},{"code_sha256_prefix":"81f0592ab53fcfa9","entry":"parse_poses_default","repo":"yuhanghe01/hifanet","repo_kind":"official","path":"generate_sequential.py","file_url":"https://github.com/yuhanghe01/hifanet/blob/HEAD/generate_sequential.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81f0592ab53fcfa9"}},{"code_sha256_prefix":"432bef4a64c29181","entry":"read_calib_file","repo":"yuhanghe01/hifanet","repo_kind":"official","path":"proj_pcd2img.py","file_url":"https://github.com/yuhanghe01/hifanet/blob/HEAD/proj_pcd2img.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"432bef4a64c29181"}},{"code_sha256_prefix":"1abd8a8255e84b56","entry":"rgb_to_float","repo":"yuhanghe01/hifanet","repo_kind":"official","path":"proj_pcd2img.py","file_url":"https://github.com/yuhanghe01/hifanet/blob/HEAD/proj_pcd2img.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1abd8a8255e84b56"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}