{"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/pix2pose-pixel-wise-coordinate-regression-of","title":"Pix2Pose: Pixel-Wise Coordinate Regression of Objects for 6D Pose Estimation","arxiv_id":"1908.07433","date":"2019-08-20","proceeding":"ICCV 2019 10","authors":["Kiru Park","Timothy Patten","Markus Vincze"],"abstract":"Estimating the 6D pose of objects using only RGB images remains challenging because of problems such as occlusion and symmetries. It is also difficult to construct 3D models with precise texture without expert knowledge or specialized scanning devices. To address these problems, we propose a novel pose estimation method, Pix2Pose, that predicts the 3D coordinates of each object pixel without textured models. An auto-encoder architecture is designed to estimate the 3D coordinates and expected errors per pixel. These pixel-wise predictions are then used in multiple stages to form 2D-3D correspondences to directly compute poses with the PnP algorithm with RANSAC iterations. Our method is robust to occlusion by leveraging recent achievements in generative adversarial training to precisely recover occluded parts. Furthermore, a novel loss function, the transformer loss, is proposed to handle symmetric objects by guiding predictions to the closest symmetric pose. Evaluations on three different benchmark datasets containing symmetric and occluded objects show our method outperforms the state of the art using only RGB images.","url_abs":"https://arxiv.org/abs/1908.07433v1","url_pdf":"https://arxiv.org/pdf/1908.07433v1.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":"pix2pose-pixel-wise-coordinate-regression-of","repo_url":"https://github.com/GH3927/Pix2Pix-applied-to-cranes","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"pix2pose-pixel-wise-coordinate-regression-of","repo_url":"https://github.com/hz-ants/Pix2Pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"pix2pose-pixel-wise-coordinate-regression-of","repo_url":"https://github.com/kirumang/Pix2Pose","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"6d-pose-estimation-1","task_name":"6D Pose Estimation"},{"task_slug":"6d-pose-estimation","task_name":"6D Pose Estimation using RGB"},{"task_slug":"pose-estimation","task_name":"Pose Estimation"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/6d-pose-estimation-on-linemod","task":"6D Pose Estimation using RGB","dataset":"LineMOD","model":"Pix2Pose","rank_in_archive_order":20,"of":22,"metrics":{"Mean ADD":"32"},"uses_additional_data":false},{"leaderboard":"/sota/6d-pose-estimation-on-t-less","task":"6D Pose Estimation using RGB","dataset":"T-LESS","model":"Pix2Pose without ICP","rank_in_archive_order":1,"of":2,"metrics":{"Recall (VSD)":"29.5"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/1908.07433","atlas_url":"https://app.syntology.ai/?focus=1908.07433","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1908.07433"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/GH3927/Pix2Pix-applied-to-cranes","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/hz-ants/Pix2Pose","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/kirumang/Pix2Pose","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":3,"unverified":5},"by_repo_kind":{"listed":{"samples":8,"ran":3,"repositories":2}},"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":"f1f755c2a962bfe2","entry":"compute_rotation_from_vertex","repo":"hz-ants/Pix2Pose","repo_kind":"listed","path":"rendering/utils.py","file_url":"https://github.com/hz-ants/Pix2Pose/blob/HEAD/rendering/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f1f755c2a962bfe2"}},{"code_sha256_prefix":"0c20710ab8a2abc9","entry":"conv_block","repo":"kirumang/Pix2Pose","repo_kind":"listed","path":"pix2pose_model/resnet50_mod.py","file_url":"https://github.com/kirumang/Pix2Pose/blob/HEAD/pix2pose_model/resnet50_mod.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c20710ab8a2abc9"}},{"code_sha256_prefix":"56ef64fd9c7a6e8f","entry":"getXYZ","repo":"kirumang/Pix2Pose","repo_kind":"listed","path":"pix2pose_util/common_util.py","file_url":"https://github.com/kirumang/Pix2Pose/blob/HEAD/pix2pose_util/common_util.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"56ef64fd9c7a6e8f"}},{"code_sha256_prefix":"58e205d70619d7b4","entry":"draw_detections_2D","repo":"hz-ants/Pix2Pose","repo_kind":"listed","path":"rendering/utils.py","file_url":"https://github.com/hz-ants/Pix2Pose/blob/HEAD/rendering/utils.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":"58e205d70619d7b4"}},{"code_sha256_prefix":"2a1a7f9181849be6","entry":"get_bbox_from_mask","repo":"hz-ants/Pix2Pose","repo_kind":"listed","path":"pix2pose_util/common_util.py","file_url":"https://github.com/hz-ants/Pix2Pose/blob/HEAD/pix2pose_util/common_util.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":"2a1a7f9181849be6"}},{"code_sha256_prefix":"d73753b0d8a243a5","entry":"get_normal","repo":"kirumang/Pix2Pose","repo_kind":"listed","path":"pix2pose_util/common_util.py","file_url":"https://github.com/kirumang/Pix2Pose/blob/HEAD/pix2pose_util/common_util.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":"d73753b0d8a243a5"}},{"code_sha256_prefix":"4709da86c7cc71fd","entry":"identity_block","repo":"kirumang/Pix2Pose","repo_kind":"listed","path":"pix2pose_model/resnet50_mod.py","file_url":"https://github.com/kirumang/Pix2Pose/blob/HEAD/pix2pose_model/resnet50_mod.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":"4709da86c7cc71fd"}},{"code_sha256_prefix":"7688c81b21c2784f","entry":"singleton","repo":"hz-ants/Pix2Pose","repo_kind":"listed","path":"rendering/renderer.py","file_url":"https://github.com/hz-ants/Pix2Pose/blob/HEAD/rendering/renderer.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":"7688c81b21c2784f"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}