{"url":"/task/3d-reconstruction","name":"3D Reconstruction","slug":"3d-reconstruction","description_markdown":"**3D Reconstruction** is the task of creating a 3D model or representation of an object or scene from 2D images or other data sources. The goal of 3D reconstruction is to create a virtual representation of an object or scene that can be used for a variety of purposes, such as visualization, animation, simulation, and analysis. It can be used in fields such as computer vision, robotics, and virtual reality.\r\n\r\nImage: [Gwak et al](https://arxiv.org/pdf/1705.10904v2.pdf)","categories":[{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":2326,"papers_with_code":793,"benchmarks":10,"benchmark_tables_in_archive":10,"benchmark_tables_shown":10,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":58,"subtasks":7,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/3d-reconstruction-on-dtu","slug":"3d-reconstruction-on-dtu","dataset":"DTU","dataset_url":"/dataset/dtu","rows_in_archive":24,"metrics":["Overall","Acc","Comp"],"first_row_in_archive_order":{"model":"MVSFormer++","paper_title":"MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo","paper_url":"/paper/mvsformer-revealing-the-devil-in-transformer","paper_date":"2024-01-22","arxiv_id":"2401.11673","code_links":[{"title":"maybelx/mvsformerplusplus","url":"https://github.com/maybelx/mvsformerplusplus"}],"syntology":{"n":19,"n_ran":15,"n_unverified":4,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-reconstruction-on-shapenet","slug":"3d-reconstruction-on-shapenet","dataset":"ShapeNet","dataset_url":"/dataset/shapenet","rows_in_archive":8,"metrics":["IoU","Chamfer Distance","F-Score@1%"],"first_row_in_archive_order":{"model":"MD-GON","paper_title":"Mixing-Denoising Generalizable Occupancy Networks","paper_url":"/paper/mixing-denoising-generalizable-occupancy","paper_date":"2023-11-20","arxiv_id":"2311.12125","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-reconstruction-on-data3dr2n2","slug":"3d-reconstruction-on-data3dr2n2","dataset":"Data3D−R2N2","dataset_url":null,"rows_in_archive":4,"metrics":["3DIoU"],"first_row_in_archive_order":{"model":"AttSets","paper_title":"Robust Attentional Aggregation of Deep Feature Sets for Multi-view 3D Reconstruction","paper_url":"/paper/attentional-aggregation-of-deep-feature-sets","paper_date":"2018-08-02","arxiv_id":"1808.00758","code_links":[{"title":"Yang7879/AttSets","url":"https://github.com/Yang7879/AttSets"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-reconstruction-on-scan2cad","slug":"3d-reconstruction-on-scan2cad","dataset":"Scan2CAD","dataset_url":"/dataset/scan2cad","rows_in_archive":2,"metrics":["Average Accuracy"],"first_row_in_archive_order":{"model":"Scan2CAD","paper_title":"Scan2CAD: Learning CAD Model Alignment in RGB-D Scans","paper_url":"/paper/scan2cad-learning-cad-model-alignment-in-rgb","paper_date":"2018-11-27","arxiv_id":"1811.11187","code_links":[{"title":"skanti/Scan2CAD","url":"https://github.com/skanti/Scan2CAD"},{"title":"skanti/Scan2CAD-Annotation-Webapp","url":"https://github.com/skanti/Scan2CAD-Annotation-Webapp"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}}},{"leaderboard":"/sota/3d-reconstruction-on-300w","slug":"3d-reconstruction-on-300w","dataset":"300W","dataset_url":"/dataset/300w","rows_in_archive":1,"metrics":["1-of-100 Accuracy"],"first_row_in_archive_order":{"model":"ResNet","paper_title":"What Do Single-view 3D Reconstruction Networks Learn?","paper_url":"/paper/190503678","paper_date":"2019-05-09","arxiv_id":"1905.03678","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-reconstruction-on-3dpeople","slug":"3d-reconstruction-on-3dpeople","dataset":"3DPeople","dataset_url":null,"rows_in_archive":1,"metrics":["Chamfer","IoU","Normal Consistency","P2S"],"first_row_in_archive_order":{"model":"SVCP","paper_title":"Single-view 3D Body and Cloth Reconstruction under Complex Poses","paper_url":"/paper/single-view-3d-body-and-cloth-reconstruction","paper_date":"2022-05-09","arxiv_id":"2205.04087","code_links":[],"syntology":null}},{"leaderboard":"/sota/3d-reconstruction-on-apollocar3d","slug":"3d-reconstruction-on-apollocar3d","dataset":"ApolloCar3D","dataset_url":"/dataset/apollocar3d","rows_in_archive":1,"metrics":["A3DP"],"first_row_in_archive_order":{"model":"GSNet","paper_title":"GSNet: Joint Vehicle Pose and Shape Reconstruction with Geometrical and Scene-aware Supervision","paper_url":"/paper/gsnet-joint-vehicle-pose-and-shape","paper_date":"2020-07-26","arxiv_id":"2007.13124","code_links":[{"title":"lkeab/gsnet","url":"https://github.com/lkeab/gsnet"}],"syntology":null}},{"leaderboard":"/sota/3d-reconstruction-on-aria-digital-twin","slug":"3d-reconstruction-on-aria-digital-twin","dataset":"Aria Digital Twin Dataset","dataset_url":"/dataset/aria-digital-twin-dataset","rows_in_archive":1,"metrics":["Accuracy","Completeness","Precision"],"first_row_in_archive_order":{"model":"EVL","paper_title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","paper_url":"/paper/efm3d-a-benchmark-for-measuring-progress","paper_date":"2024-06-14","arxiv_id":"2406.10224","code_links":[{"title":"facebookresearch/efm3d","url":"https://github.com/facebookresearch/efm3d"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-reconstruction-on-aria-synthetic","slug":"3d-reconstruction-on-aria-synthetic","dataset":"Aria Synthetic Environments","dataset_url":"/dataset/aria-synthetic-environments","rows_in_archive":1,"metrics":["Accuracy","Completeness","Precision","Recall"],"first_row_in_archive_order":{"model":"EVL","paper_title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","paper_url":"/paper/efm3d-a-benchmark-for-measuring-progress","paper_date":"2024-06-14","arxiv_id":"2406.10224","code_links":[{"title":"facebookresearch/efm3d","url":"https://github.com/facebookresearch/efm3d"}],"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/3d-reconstruction-on-scannet","slug":"3d-reconstruction-on-scannet","dataset":"ScanNet","dataset_url":"/dataset/scannet","rows_in_archive":1,"metrics":["3DIoU","Chamfer Distance","L1"],"first_row_in_archive_order":{"model":"Atlas (finetuned)","paper_title":"Atlas: End-to-End 3D Scene Reconstruction from Posed Images","paper_url":"/paper/atlas-end-to-end-3d-scene-reconstruction-from","paper_date":"2020-03-23","arxiv_id":"2003.10432","code_links":[{"title":"magicleap/Atlas","url":"https://github.com/magicleap/Atlas"}],"syntology":{"n":12,"n_ran":1,"n_unverified":11,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/shapenet","name":"ShapeNet","full_name":"","num_papers_in_archive":1947},{"url":"/dataset/scannet","name":"ScanNet","full_name":"","num_papers_in_archive":1595},{"url":"/dataset/dtu","name":"DTU","full_name":"DTU MVS dataset - 2014","num_papers_in_archive":313},{"url":"/dataset/300w","name":"300W","full_name":"300 Faces-In-The-Wild","num_papers_in_archive":206},{"url":"/dataset/shapenetcore","name":"ShapeNetCore","full_name":"","num_papers_in_archive":180},{"url":"/dataset/megadepth","name":"MegaDepth","full_name":"","num_papers_in_archive":152},{"url":"/dataset/eth3d","name":"ETH3D","full_name":"","num_papers_in_archive":121},{"url":"/dataset/hypersim","name":"Hypersim","full_name":"","num_papers_in_archive":108},{"url":"/dataset/blendedmvs","name":"BlendedMVS","full_name":"","num_papers_in_archive":105},{"url":"/dataset/abc-dataset-1","name":"ABC Dataset","full_name":"","num_papers_in_archive":104},{"url":"/dataset/abo","name":"ABO","full_name":"Amazon Berkeley Objects","num_papers_in_archive":82},{"url":"/dataset/scan2cad","name":"Scan2CAD","full_name":"","num_papers_in_archive":72},{"url":"/dataset/tanks-and-temples","name":"Tanks and Temples","full_name":"","num_papers_in_archive":55},{"url":"/dataset/people-snapshot-dataset","name":"People Snapshot Dataset","full_name":"","num_papers_in_archive":36},{"url":"/dataset/dynamic-faust","name":"Dynamic FAUST","full_name":"","num_papers_in_archive":28},{"url":"/dataset/arctic","name":"ARCTIC","full_name":"Articulated Objects in Free-form Hand Interaction","num_papers_in_archive":23},{"url":"/dataset/common-objects-in-3d","name":"Common Objects in 3D","full_name":"","num_papers_in_archive":20},{"url":"/dataset/apollocar3d","name":"ApolloCar3D","full_name":"","num_papers_in_archive":17},{"url":"/dataset/scenenet","name":"SceneNet","full_name":"SceneNet","num_papers_in_archive":17},{"url":"/dataset/dublincity","name":"DublinCity","full_name":"","num_papers_in_archive":15},{"url":"/dataset/dynamic-replica","name":"Dynamic Replica","full_name":"","num_papers_in_archive":10},{"url":"/dataset/csd","name":"CSD","full_name":"Collaborative SLAM Dataset","num_papers_in_archive":8},{"url":"/dataset/eth-sfm","name":"ETH SfM","full_name":"ETH Structure-from-Motion","num_papers_in_archive":8},{"url":"/dataset/monoperfcap-dataset","name":"MonoPerfCap Dataset","full_name":"","num_papers_in_archive":7},{"url":"/dataset/oxford-affine","name":"Oxford-Affine","full_name":"","num_papers_in_archive":7},{"url":"/dataset/3dpeople-dataset","name":"3DPeople Dataset","full_name":"","num_papers_in_archive":6},{"url":"/dataset/mobilebrick","name":"MobileBrick","full_name":"","num_papers_in_archive":6},{"url":"/dataset/a-large-dataset-of-object-scans","name":"A Large Dataset of Object Scans","full_name":"A Large Dataset of Object Scans","num_papers_in_archive":5},{"url":"/dataset/aria-synthetic-environments","name":"Aria Synthetic Environments","full_name":"Aria Synthetic Environments","num_papers_in_archive":5},{"url":"/dataset/cop3d","name":"CoP3D","full_name":"","num_papers_in_archive":5},{"url":"/dataset/hod","name":"HOD","full_name":"Hand-held Object Dataset","num_papers_in_archive":5},{"url":"/dataset/refref","name":"RefRef","full_name":"RefRef: A Synthetic Dataset and Benchmark for Reconstructing Refractive and Reflective Objects","num_papers_in_archive":5},{"url":"/dataset/foot3d","name":"Foot3D","full_name":"","num_papers_in_archive":4},{"url":"/dataset/houses3k","name":"Houses3K","full_name":null,"num_papers_in_archive":4},{"url":"/dataset/shapenetrender","name":"ShapenetRender","full_name":null,"num_papers_in_archive":4},{"url":"/dataset/parcel2d-real","name":"Parcel2D Real","full_name":"","num_papers_in_archive":3},{"url":"/dataset/tragic-talkers","name":"Tragic Talkers","full_name":"","num_papers_in_archive":3},{"url":"/dataset/vbr","name":"VBR","full_name":"VBR: A Vision Benchmark in Rome","num_papers_in_archive":3},{"url":"/dataset/aria-digital-twin-dataset","name":"Aria Digital Twin Dataset","full_name":"Aria Digital Twin Dataset","num_papers_in_archive":2},{"url":"/dataset/draco20k","name":"DRACO20K","full_name":"","num_papers_in_archive":2},{"url":"/dataset/drunkard-s-dataset","name":"Drunkard's Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/enrich","name":"ENRICH","full_name":"Multi-purposE dataset for beNchmaRking In Computer vision and pHotogrammetry","num_papers_in_archive":2},{"url":"/dataset/g-vue","name":"G-VUE","full_name":"General-purpose Visual Understanding Evaluation","num_papers_in_archive":2},{"url":"/dataset/mbw-zoo-dataset","name":"MBW - Zoo Dataset","full_name":"","num_papers_in_archive":2},{"url":"/dataset/middlebury-mvs","name":"Middlebury MVS","full_name":"Middlebury MVS","num_papers_in_archive":2},{"url":"/dataset/pano3d","name":"Pano3D","full_name":"","num_papers_in_archive":2},{"url":"/dataset/parcel3d","name":"Parcel3D","full_name":"","num_papers_in_archive":2},{"url":"/dataset/amt-objects","name":"AMT Objects","full_name":"","num_papers_in_archive":1},{"url":"/dataset/danish-airs-and-grounds","name":"Danish Airs and Grounds","full_name":"","num_papers_in_archive":1},{"url":"/dataset/iiwa-robotic-arm-reconstruction-dataset","name":"iiwa Robotic Arm Reconstruction Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/indoor-and-outdoor-dfd-dataset","name":"Indoor and outdoor DFD dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/replay","name":"Replay","full_name":"","num_papers_in_archive":1},{"url":"/dataset/robust-e-nerf-synthetic-event-dataset","name":"Robust e-NeRF Synthetic Event Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/stained-mice-brain-blood-vessels-confocal-lfm","name":"Stained mice brain blood vessels. Confocal-LFM","full_name":"","num_papers_in_archive":1},{"url":"/dataset/synthetic-human-model-dataset","name":"Synthetic Human Model Dataset","full_name":"","num_papers_in_archive":1},{"url":"/dataset/thermoscenes","name":"ThermoScenes","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cvgl","name":"CVGL","full_name":"","num_papers_in_archive":0},{"url":"/dataset/pinet","name":"PINet","full_name":"","num_papers_in_archive":0}],"subtasks":[{"url":"/task/3d-room-layouts-from-a-single-rgb-panorama","name":"3D Room Layouts From A Single RGB Panorama"},{"url":"/task/3d-semantic-scene-completion","name":"3D Semantic Scene Completion"},{"url":"/task/3d-shape-reconstruction-from-videos","name":"3D Shape Reconstruction from Videos"},{"url":"/task/3d-wireframe-reconstruction","name":"3D Wireframe Reconstruction"},{"url":"/task/garment-reconstruction","name":"Garment Reconstruction"},{"url":"/task/point-cloud-reconstruction","name":"Point cloud reconstruction"},{"url":"/task/unsupervised-3d-human-pose-estimation","name":"Unsupervised 3D Human Pose Estimation"}],"parent_tasks":[{"url":"/task/3d","name":"3D"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":793,"tagged_in_all":2326,"items":[{"url":"/paper/instant-neural-graphics-primitives-with-a","title":"Instant Neural Graphics Primitives with a Multiresolution Hash Encoding","date":"2022-01-16","arxiv_id":"2201.05989","repositories_listed":17,"syntology":{"n":44,"n_ran":18,"n_unverified":26,"n_pointer_only":9}},{"url":"/paper/3d-r2n2-a-unified-approach-for-single-and","title":"3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction","date":"2016-04-02","arxiv_id":"1604.00449","repositories_listed":13,"syntology":null},{"url":"/paper/kimera-an-open-source-library-for-real-time","title":"Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping","date":"2019-10-06","arxiv_id":"1910.02490","repositories_listed":12,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/the-double-sphere-camera-model","title":"The Double Sphere Camera Model","date":"2018-07-24","arxiv_id":"1807.08957","repositories_listed":9,"syntology":null},{"url":"/paper/occupancy-networks-learning-3d-reconstruction","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","date":"2018-12-10","arxiv_id":"1812.03828","repositories_listed":7,"syntology":{"n":23,"n_ran":13,"n_unverified":10,"n_pointer_only":0}},{"url":"/paper/epp-mvsnet-epipolar-assembling-based-depth","title":"EPP-MVSNet: Epipolar-Assembling Based Depth Prediction for Multi-View Stereo","date":"2021-01-01","arxiv_id":null,"repositories_listed":6,"syntology":null},{"url":"/paper/convolutional-occupancy-networks","title":"Convolutional Occupancy Networks","date":"2020-03-10","arxiv_id":"2003.04618","repositories_listed":6,"syntology":{"n":21,"n_ran":7,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/190807906","title":"PCRNet: Point Cloud Registration Network using PointNet Encoding","date":"2019-08-21","arxiv_id":"1908.07906","repositories_listed":5,"syntology":null},{"url":"/paper/incremental-visual-inertial-3d-mesh","title":"Incremental Visual-Inertial 3D Mesh Generation with Structural Regularities","date":"2019-03-04","arxiv_id":"1903.01067","repositories_listed":5,"syntology":null},{"url":"/paper/pix2vox-context-aware-3d-reconstruction-from","title":"Pix2Vox: Context-aware 3D Reconstruction from Single and Multi-view Images","date":"2019-01-31","arxiv_id":"1901.11153","repositories_listed":5,"syntology":{"n":9,"n_ran":1,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/deepsdf-learning-continuous-signed-distance","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","date":"2019-01-16","arxiv_id":"1901.05103","repositories_listed":5,"syntology":{"n":7,"n_ran":2,"n_unverified":5,"n_pointer_only":1}},{"url":"/paper/mvsnet-depth-inference-for-unstructured-multi","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","date":"2018-04-07","arxiv_id":"1804.02505","repositories_listed":5,"syntology":null},{"url":"/paper/megaloc-one-retrieval-to-place-them-all","title":"MegaLoc: One Retrieval to Place Them All","date":"2025-02-24","arxiv_id":"2502.17237","repositories_listed":4,"syntology":{"n":6,"n_ran":1,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/realfusion-360deg-reconstruction-of-any","title":"RealFusion: 360° Reconstruction of Any Object from a Single Image","date":"2023-02-21","arxiv_id":"2302.10663","repositories_listed":4,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/learning-accurate-dense-correspondences-and","title":"Learning Accurate Dense Correspondences and When to Trust Them","date":"2021-01-05","arxiv_id":"2101.01710","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/event-based-stereo-visual-odometry","title":"Event-based Stereo Visual Odometry","date":"2020-07-30","arxiv_id":"2007.15548","repositories_listed":4,"syntology":null},{"url":"/paper/aslfeat-learning-local-features-of-accurate","title":"ASLFeat: Learning Local Features of Accurate Shape and Localization","date":"2020-03-23","arxiv_id":"2003.10071","repositories_listed":4,"syntology":{"n":16,"n_ran":0,"n_unverified":16,"n_pointer_only":0}},{"url":"/paper/cascade-cost-volume-for-high-resolution-multi","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","date":"2019-12-13","arxiv_id":"1912.06378","repositories_listed":4,"syntology":{"n":14,"n_ran":6,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/190503561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","date":"2019-05-09","arxiv_id":"1905.03561","repositories_listed":4,"syntology":{"n":13,"n_ran":1,"n_unverified":12,"n_pointer_only":1}},{"url":"/paper/learning-implicit-fields-for-generative-shape","title":"Learning Implicit Fields for Generative Shape Modeling","date":"2018-12-06","arxiv_id":"1812.02822","repositories_listed":4,"syntology":null},{"url":"/paper/semi-dense-3d-reconstruction-with-a-stereo","title":"Semi-Dense 3D Reconstruction with a Stereo Event Camera","date":"2018-07-19","arxiv_id":"1807.07429","repositories_listed":4,"syntology":null},{"url":"/paper/superhuman-accuracy-on-the-snemi3d","title":"Superhuman Accuracy on the SNEMI3D Connectomics Challenge","date":"2017-05-31","arxiv_id":"1706.00120","repositories_listed":4,"syntology":null},{"url":"/paper/a-point-set-generation-network-for-3d-object","title":"A Point Set Generation Network for 3D Object Reconstruction from a Single Image","date":"2016-12-02","arxiv_id":"1612.00603","repositories_listed":4,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":2}},{"url":"/paper/voxel-based-differentiable-x-ray-rendering","title":"Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstruction","date":"2024-11-28","arxiv_id":"2411.19224","repositories_listed":3,"syntology":{"n":17,"n_ran":2,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/nebla-neural-beer-lambert-for-3d","title":"NeBLa: Neural Beer-Lambert for 3D Reconstruction of Oral Structures from Panoramic Radiographs","date":"2023-04-08","arxiv_id":"2304.04027","repositories_listed":3,"syntology":null},{"url":"/paper/scrape-cut-paste-and-learn-automated-dataset","title":"Scrape, Cut, Paste and Learn: Automated Dataset Generation Applied to Parcel Logistics","date":"2022-10-18","arxiv_id":"2210.09814","repositories_listed":3,"syntology":null},{"url":"/paper/neural-rendering-for-stereo-3d-reconstruction","title":"Neural Rendering for Stereo 3D Reconstruction of Deformable Tissues in Robotic Surgery","date":"2022-06-30","arxiv_id":"2206.15255","repositories_listed":3,"syntology":null},{"url":"/paper/power-bundle-adjustment-for-large-scale-3d","title":"Power Bundle Adjustment for Large-Scale 3D Reconstruction","date":"2022-04-27","arxiv_id":"2204.12834","repositories_listed":3,"syntology":null},{"url":"/paper/centersnap-single-shot-multi-object-3d-shape","title":"CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation","date":"2022-03-03","arxiv_id":"2203.01929","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/pixel-perfect-structure-from-motion-with","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","date":"2021-08-18","arxiv_id":"2108.08291","repositories_listed":3,"syntology":{"n":10,"n_ran":0,"n_unverified":10,"n_pointer_only":0}}],"syntology_records":16,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}