{"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/occformer-dual-path-transformer-for-vision","title":"OccFormer: Dual-path Transformer for Vision-based 3D Semantic Occupancy Prediction","arxiv_id":"2304.05316","date":"2023-04-11","proceeding":"ICCV 2023 1","authors":["Yunpeng Zhang","Zheng Zhu","Dalong Du"],"abstract":"The vision-based perception for autonomous driving has undergone a transformation from the bird-eye-view (BEV) representations to the 3D semantic occupancy. Compared with the BEV planes, the 3D semantic occupancy further provides structural information along the vertical direction. This paper presents OccFormer, a dual-path transformer network to effectively process the 3D volume for semantic occupancy prediction. OccFormer achieves a long-range, dynamic, and efficient encoding of the camera-generated 3D voxel features. It is obtained by decomposing the heavy 3D processing into the local and global transformer pathways along the horizontal plane. For the occupancy decoder, we adapt the vanilla Mask2Former for 3D semantic occupancy by proposing preserve-pooling and class-guided sampling, which notably mitigate the sparsity and class imbalance. Experimental results demonstrate that OccFormer significantly outperforms existing methods for semantic scene completion on SemanticKITTI dataset and for LiDAR semantic segmentation on nuScenes dataset. Code is available at \\url{https://github.com/zhangyp15/OccFormer}.","url_abs":"https://arxiv.org/abs/2304.05316v1","url_pdf":"https://arxiv.org/pdf/2304.05316v1.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":"occformer-dual-path-transformer-for-vision","repo_url":"https://github.com/zhangyp15/occformer","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"3d-semantic-occupancy-prediction","task_name":"3D Semantic Occupancy Prediction"},{"task_slug":"3d-semantic-scene-completion","task_name":"3D Semantic Scene Completion"},{"task_slug":"3d-semantic-scene-completion-from-a-single","task_name":"3D Semantic Scene Completion from a single RGB image"},{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"lidar-semantic-segmentation","task_name":"LIDAR Semantic Segmentation"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/3d-semantic-scene-completion-on-kitti-360","task":"3D Semantic Scene Completion","dataset":"KITTI-360","model":"OccFormer","rank_in_archive_order":3,"of":7,"metrics":{"mIoU":"13.81"},"uses_additional_data":false},{"leaderboard":"/sota/3d-semantic-scene-completion-from-a-single-1","task":"3D Semantic Scene Completion from a single RGB image","dataset":"SemanticKITTI","model":"OccFormer","rank_in_archive_order":4,"of":9,"metrics":{"mIoU":"12.32"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2304.05316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2304.05316"}},"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/zhangyp15/occformer","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":1,"unverified":2},"by_repo_kind":{"official":{"samples":3,"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":"e76a491553cf9fcf","entry":"process_checkpoint","repo":"zhangyp15/occformer","repo_kind":"official","path":"mmdetection3d/.dev_scripts/gather_models.py","file_url":"https://github.com/zhangyp15/occformer/blob/HEAD/mmdetection3d/.dev_scripts/gather_models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e76a491553cf9fcf"}},{"code_sha256_prefix":"90f6ae7209cde36f","entry":"get_final_epoch","repo":"zhangyp15/occformer","repo_kind":"official","path":"mmdetection3d/.dev_scripts/gather_models.py","file_url":"https://github.com/zhangyp15/occformer/blob/HEAD/mmdetection3d/.dev_scripts/gather_models.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":"90f6ae7209cde36f"}},{"code_sha256_prefix":"da059252c88ecf40","entry":"get_model_dataset","repo":"zhangyp15/occformer","repo_kind":"official","path":"mmdetection3d/.dev_scripts/gather_models.py","file_url":"https://github.com/zhangyp15/occformer/blob/HEAD/mmdetection3d/.dev_scripts/gather_models.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":"da059252c88ecf40"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}