{"url":"/dataset/dttd2","name":"DTTD-Mobile","full_name":null,"description_markdown":"Are current 3D object tracking methods truely robust enough for low-fidelity depth sensors like the iPhone LiDAR?\r\nWe introduce DTTD-Mobile (fully compatible w/ YCB toolbox), a new benchmark built on real-world data captured from mobile devices; 18 objects observed in 100 videos with 47,668 sampled frames and 114,143 object annotations. We evaluate several popular methods—including BundleSDF, ES6D, MegaPose, and DenseFusion—and highlight their limitations in this challenging setting.\r\n\r\nKeywords: ObjectPoseEstimation, MobileAI, EdgeAI, ARVR, CVPR","description_withheld":null,"homepage":"https://openark-berkeley.github.io/DTTDNet/","introduced_date":"2023-09-24","introduced_date_note":null,"introduced_by":{"paper":"/paper/towards-subcentimeter-accuracy-digital-twin","title":"Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset","first_author":"Zixun Huang","url":null},"license":{"name":"MIT","url":null},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Videos","url":"/datasets/modality/videos"},{"name":"3D","url":"/datasets/modality/3d"}],"tasks":[{"name":"Object Detection","url":"/task/object-detection","datasets_with_task":"/datasets/task/object-detection"},{"name":"Semantic Segmentation","url":"/task/semantic-segmentation","datasets_with_task":"/datasets/task/semantic-segmentation"},{"name":"2D Semantic Segmentation","url":"/task/2d-semantic-segmentation","datasets_with_task":"/datasets/task/2d-semantic-segmentation"},{"name":"3D Object Detection","url":"/task/3d-object-detection","datasets_with_task":"/datasets/task/3d-object-detection"},{"name":"Depth Estimation","url":"/task/depth-estimation","datasets_with_task":"/datasets/task/depth-estimation"},{"name":"Multi-Object Tracking","url":"/task/multi-object-tracking","datasets_with_task":"/datasets/task/multi-object-tracking"},{"name":"Monocular Depth Estimation","url":"/task/monocular-depth-estimation","datasets_with_task":"/datasets/task/monocular-depth-estimation"},{"name":"3D Semantic Segmentation","url":"/task/3d-semantic-segmentation","datasets_with_task":"/datasets/task/3d-semantic-segmentation"},{"name":"3D Object Reconstruction","url":"/task/3d-object-reconstruction","datasets_with_task":"/datasets/task/3d-object-reconstruction"},{"name":"6D Pose Estimation","url":"/task/6d-pose-estimation-1","datasets_with_task":"/datasets/task/6d-pose-estimation-1"},{"name":"Video Object Detection","url":"/task/video-object-detection","datasets_with_task":"/datasets/task/video-object-detection"},{"name":"Video Inpainting","url":"/task/video-inpainting","datasets_with_task":"/datasets/task/video-inpainting"},{"name":"Robotic Grasping","url":"/task/robotic-grasping","datasets_with_task":"/datasets/task/robotic-grasping"},{"name":"Video Object Tracking","url":"/task/video-object-tracking","datasets_with_task":"/datasets/task/video-object-tracking"},{"name":"Video Grounding","url":"/task/video-grounding","datasets_with_task":"/datasets/task/video-grounding"},{"name":"3D Depth Estimation","url":"/task/3d-depth-estimation","datasets_with_task":"/datasets/task/3d-depth-estimation"},{"name":"3D Object Tracking","url":"/task/3d-object-tracking","datasets_with_task":"/datasets/task/3d-object-tracking"},{"name":"Semantic SLAM","url":"/task/semantic-slam","datasets_with_task":"/datasets/task/semantic-slam"},{"name":"Monocular 3D Object Localization","url":"/task/monocular-3d-object-localization","datasets_with_task":"/datasets/task/monocular-3d-object-localization"}],"languages":[],"variants":["DTTD-Mobile"],"data_loaders":[{"repo":"https://github.com/augcog/dttd2","url":"https://github.com/augcog/dttd2","frameworks":["pytorch"]}],"num_papers_in_archive":8,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/6d-pose-estimation-on-dttd2","task":"6D Pose Estimation","dataset_variant":"DTTD-Mobile","rows":8,"metrics":["ADD AUC","ADD-S AUC","AR CoU","AR CH","AR pCH"],"first_row_in_archive_order":{"model":"DTTDNet","paper":"/paper/towards-subcentimeter-accuracy-digital-twin","metrics":{"ADD AUC":"73.99","ADD-S AUC":"88.10"},"code_links":[{"title":"augcog/dttdv1","url":"https://github.com/augcog/dttdv1"},{"title":"augcog/robust-digital-twin-tracking","url":"https://github.com/augcog/robust-digital-twin-tracking"},{"title":"augcog/dttd2","url":"https://github.com/augcog/dttd2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/3d-object-detection-on-dttd2","task":"3D Object Detection","dataset_variant":"DTTD-Mobile","rows":5,"metrics":["ADD AUC","ADD-S AUC"],"first_row_in_archive_order":{"model":"DTTDNet","paper":"/paper/towards-subcentimeter-accuracy-digital-twin","metrics":{"ADD AUC":"73.99","ADD-S AUC":"88.10"},"code_links":[{"title":"augcog/dttdv1","url":"https://github.com/augcog/dttdv1"},{"title":"augcog/robust-digital-twin-tracking","url":"https://github.com/augcog/robust-digital-twin-tracking"},{"title":"augcog/dttd2","url":"https://github.com/augcog/dttd2"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers_with_a_benchmark_row":[{"paper":"/paper/6d-object-pose-tracking-in-internet-videos","title":"6D Object Pose Tracking in Internet Videos for Robotic Manipulation","date":"2025-03-13","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/foundpose-unseen-object-pose-estimation-with","title":"FoundPose: Unseen Object Pose Estimation with Foundation Features","date":"2023-11-30","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/gigapose-fast-and-robust-novel-object-pose","title":"GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence","date":"2023-11-23","rows_on_this_dataset":1,"code_links":1,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":3,"samples_ran":2,"samples_unverified":1,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}},{"paper":"/paper/towards-subcentimeter-accuracy-digital-twin","title":"Robust 6DoF Pose Estimation Against Depth Noise and a Comprehensive Evaluation on a Mobile Dataset","date":"2023-09-24","rows_on_this_dataset":2,"code_links":3,"syntology":null},{"paper":"/paper/bundlesdf-neural-6-dof-tracking-and-3d","title":"BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects","date":"2023-03-24","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/megapose-6d-pose-estimation-of-novel-objects","title":"MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare","date":"2022-12-13","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/es6d-a-computation-efficient-and-symmetry","title":"ES6D: A Computation Efficient and Symmetry-Aware 6D Pose Regression Framework","date":"2022-04-03","rows_on_this_dataset":2,"code_links":1,"syntology":null},{"paper":"/paper/densefusion-6d-object-pose-estimation-by","title":"DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion","date":"2019-01-15","rows_on_this_dataset":1,"code_links":8,"syntology":{"read_at":"2026-09-24T18:15:14+00:00","samples_harvested":19,"samples_ran":1,"samples_unverified":18,"pointer_only_for_licence":0,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim."}}],"syntology_totals":{"read_at":"2026-09-24T18:15:14+00:00","papers_with_samples":2,"samples_harvested":22,"samples_ran":3,"samples_unverified":19,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"note":"the per-paper counts above, summed; not a rate"},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks."}