https://cvg.cit.tum.de/ 2026-04-20T21:17:37+00:00 FeedCreator 1.8 (info@mypapit.net) 2012-01-20T12:01:00+00:00 2012-01-20T12:01:00+00:00 https://cvg.cit.tum.de/data/datasets/3dreconstruction?rev=1327057260&do=diff Anonymous anonymous@undisclosed.example.com Multiview Datasets We provide multiple datasets capturing objects from various vantage points. Each entry contains an image sequence, corresponding silhouettes and full calibration parameters. We are happy to share our data with other researchers. Please refer to the respective publication when using this data.

Multiview Datasets We provide multiple datasets capturing objects from various vantage points. Each entry contains an image sequence, corresponding silhouettes and full calibration parameters. We are happy to share our data with other researchers. Please refer to the respective publication when using this data.

2025-02-06T13:47:58+00:00 2025-02-06T13:47:58+00:00 https://cvg.cit.tum.de/data/datasets/4seasons-dataset?rev=1738846078&do=diff Anonymous anonymous@undisclosed.example.com 4seasons 4Seasons Dataset 4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving. Among others, it enables research on visual odometry, global place recognition, and map-based re-localization tracking. The data was collected in different scenarios and under a wide variety of weather conditions and illuminations, including day and night. This resulted in more tha…

4seasons 4Seasons Dataset 4Seasons: A Cross-Season Dataset for Multi-Weather SLAM in Autonomous Driving We present a novel dataset covering seasonal and challenging perceptual conditions for autonomous driving. Among others, it enables research on visual odometry, global place recognition, and map-based re-localization tracking. The data was collected in different scenarios and under a wide variety of weather conditions and illuminations, including day and night. This resulted in more tha…

2014-07-14T13:58:58+00:00 2014-07-14T13:58:58+00:00 https://cvg.cit.tum.de/data/datasets/clutter?rev=1405339138&do=diff Anonymous anonymous@undisclosed.example.com 3D Object in Clutter Recognition and Segmentation ---------- This dataset focuses on the recognition of known objects in cluttered and incomplete 3D scans. It is composed of 150 synthetic scenes, captured with a (perspective) virtual camera, and

3D Object in Clutter Recognition and Segmentation ---------- This dataset focuses on the recognition of known objects in cluttered and incomplete 3D scans. It is composed of 150 synthetic scenes, captured with a (perspective) virtual camera, and

2026-03-10T09:16:18+00:00 2026-03-10T09:16:18+00:00 https://cvg.cit.tum.de/data/datasets/ddff12scene?rev=1773130578&do=diff Anonymous anonymous@undisclosed.example.com DDFF 12-Scene 4.5D Lightfield-Depth Benchmark Depth From Focus Competition on the DDFF 12-Scene Dataset DDFF 12-Scene dataset consists of 720 lightfield images and coregistered depth maps. * Lightfield: 4D lightfield images; each of which has 9 × 9 × 383 × 552 undistorted subapertures Images are saved as numpy arrays and can be loaded as follows:

DDFF 12-Scene 4.5D Lightfield-Depth Benchmark Depth From Focus Competition on the DDFF 12-Scene Dataset DDFF 12-Scene dataset consists of 720 lightfield images and coregistered depth maps. * Lightfield: 4D lightfield images; each of which has 9 × 9 × 383 × 552 undistorted subapertures Images are saved as numpy arrays and can be loaded as follows:

2012-06-18T15:59:50+00:00 2012-06-18T15:59:50+00:00 https://cvg.cit.tum.de/data/datasets/deformable_shape_tracking_datasets?rev=1340027990&do=diff Anonymous anonymous@undisclosed.example.com We are happy to share our data with other researchers. Please refer to the respective publication when using this data. Deformable Shape Tracking Datasets Shape Priors in Variational Image Segmentation: Convexity, Lipschitz Continuity and Globally Optimal Solutions

We are happy to share our data with other researchers. Please refer to the respective publication when using this data. Deformable Shape Tracking Datasets Shape Priors in Variational Image Segmentation: Convexity, Lipschitz Continuity and Globally Optimal Solutions

2020-10-12T14:29:29+00:00 2020-10-12T14:29:29+00:00 https://cvg.cit.tum.de/data/datasets/intrinsic3d?rev=1602505769&do=diff Anonymous anonymous@undisclosed.example.com Intrinsic3D Dataset Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting Robert Maier1,2 Kihwan Kim1 Daniel Cremers2 Jan Kautz1 Matthias Nießner2,3 1NVIDIA 2Technical University of Munich 3Stanford University IEEE International Conference on Computer Vision (ICCV) 2017

Intrinsic3D Dataset Intrinsic3D: High-Quality 3D Reconstruction by Joint Appearance and Geometry Optimization with Spatially-Varying Lighting Robert Maier1,2 Kihwan Kim1 Daniel Cremers2 Jan Kautz1 Matthias Nießner2,3 1NVIDIA 2Technical University of Munich 3Stanford University IEEE International Conference on Computer Vision (ICCV) 2017

2016-04-08T15:39:58+00:00 2016-04-08T15:39:58+00:00 https://cvg.cit.tum.de/data/datasets/kids?rev=1460122798&do=diff Anonymous anonymous@undisclosed.example.com Deformable 3D Shape Matching ---------- This dataset consists of a collection of 3D shapes undergoing nearly-isometric and within-class deformations. In particular, we provide two shape classes ("kid" and "fat kid") under different poses, where the same poses are applied to both classes. Filenames within each class are ordered by deviation from isometry, i.e. the last shape has the largest deformation with respect to the null pose. All shapes in the dataset are given in OFF format, have arou…

Deformable 3D Shape Matching ---------- This dataset consists of a collection of 3D shapes undergoing nearly-isometric and within-class deformations. In particular, we provide two shape classes ("kid" and "fat kid") under different poses, where the same poses are applied to both classes. Filenames within each class are ordered by deviation from isometry, i.e. the last shape has the largest deformation with respect to the null pose. All shapes in the dataset are given in OFF format, have arou…

2018-10-18T00:22:15+00:00 2018-10-18T00:22:15+00:00 https://cvg.cit.tum.de/data/datasets/mdff?rev=1539814935&do=diff Anonymous anonymous@undisclosed.example.com

no summary

2021-07-07T10:30:38+00:00 2021-07-07T10:30:38+00:00 https://cvg.cit.tum.de/data/datasets/mono-dataset?rev=1625646638&do=diff Anonymous anonymous@undisclosed.example.com Monocular Visual Odometry Dataset We present a dataset for evaluating the tracking accuracy of monocular Visual Odometry (VO) and SLAM methods. It contains 50 real-world sequences comprising over 100 minutes of video, recorded across different environments

Monocular Visual Odometry Dataset We present a dataset for evaluating the tracking accuracy of monocular Visual Odometry (VO) and SLAM methods. It contains 50 real-world sequences comprising over 100 minutes of video, recorded across different environments

2021-03-15T10:29:58+00:00 2021-03-15T10:29:58+00:00 https://cvg.cit.tum.de/data/datasets/omni-lsdslam?rev=1615800598&do=diff Anonymous anonymous@undisclosed.example.com Large-Scale Direct SLAM for Omnidirectional Cameras We propose a real-time, direct monocular SLAM method for omnidirectional or wide field-of-view fisheye cam- eras. Both tracking (direct image alignment) and mapping (pixel-wise distance filtering) are directly formulated for the unified omnidirectional model, which can model central imaging devices with a field of view well above 150° . This is in stark contrast to existing direct mono-SLAM approaches like DTAM or LSD-SLAM, which operate on re…

Large-Scale Direct SLAM for Omnidirectional Cameras We propose a real-time, direct monocular SLAM method for omnidirectional or wide field-of-view fisheye cam- eras. Both tracking (direct image alignment) and mapping (pixel-wise distance filtering) are directly formulated for the unified omnidirectional model, which can model central imaging devices with a field of view well above 150° . This is in stark contrast to existing direct mono-SLAM approaches like DTAM or LSD-SLAM, which operate on re…

2016-04-18T22:28:31+00:00 2016-04-18T22:28:31+00:00 https://cvg.cit.tum.de/data/datasets/partial?rev=1461011311&do=diff Anonymous anonymous@undisclosed.example.com 3D Deformable Partial Shape Matching ---------- Description The datasets we provide here can be used for tasks of deformable 3D shape matching and retrieval under partiality transformations. This is considered a more challenging setting if compared to the more classical tasks dealing with full shapes.

3D Deformable Partial Shape Matching ---------- Description The datasets we provide here can be used for tasks of deformable 3D shape matching and retrieval under partiality transformations. This is considered a more challenging setting if compared to the more classical tasks dealing with full shapes.

2020-10-08T13:10:33+00:00 2020-10-08T13:10:33+00:00 https://cvg.cit.tum.de/data/datasets/photometricdepthsr?rev=1602155433&do=diff Anonymous anonymous@undisclosed.example.com Photometric Depth Super-Resolution Dataset Photometric Depth Super-Resolution Bjoern Haefner1 Songyou Peng2 Alok Verma1 Yvain Quéau3 Daniel Cremers1 1Technical University of Munich 2University of Illinois at Urbana-Champaign 3GREYC, UMR CNRS 6072 IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) Special Issue on RGB-D Vision: Methods and Applications

Photometric Depth Super-Resolution Dataset Photometric Depth Super-Resolution Bjoern Haefner1 Songyou Peng2 Alok Verma1 Yvain Quéau3 Daniel Cremers1 1Technical University of Munich 2University of Illinois at Urbana-Champaign 3GREYC, UMR CNRS 6072 IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) Special Issue on RGB-D Vision: Methods and Applications

2017-06-30T16:28:18+00:00 2017-06-30T16:28:18+00:00 https://cvg.cit.tum.de/data/datasets/rgbd-dataset?rev=1498832898&do=diff Anonymous anonymous@undisclosed.example.com RGB-D SLAM Dataset and Benchmark Contact: Jürgen Sturm We provide a large dataset containing RGB-D data and ground-truth data with the goal to establish a novel benchmark for the evaluation of visual odometry and visual SLAM systems. Our dataset contains the color and depth images of a Microsoft Kinect sensor along the ground-truth trajectory of the sensor. The data was recorded at full frame rate (30 Hz) and sensor resolution (640x480). The ground-truth trajectory was obtained from a high-a…

RGB-D SLAM Dataset and Benchmark Contact: Jürgen Sturm We provide a large dataset containing RGB-D data and ground-truth data with the goal to establish a novel benchmark for the evaluation of visual odometry and visual SLAM systems. Our dataset contains the color and depth images of a Microsoft Kinect sensor along the ground-truth trajectory of the sensor. The data was recorded at full frame rate (30 Hz) and sensor resolution (640x480). The ground-truth trajectory was obtained from a high-a…

2022-01-11T12:20:24+00:00 2022-01-11T12:20:24+00:00 https://cvg.cit.tum.de/data/datasets/rolling-shutter-dataset?rev=1641900024&do=diff Anonymous anonymous@undisclosed.example.com Rolling-Shutter Visual-Inertial Odometry Dataset Contact : David Schubert, Nikolaus Demmel, Lukas von Stumberg, Vladyslav Usenko. We present a novel dataset that contains time-synchronized global-shutter and rolling-shutter images, IMU data and ground-truth poses for ten different sequences. Dataset The full dataset can be found at:

Rolling-Shutter Visual-Inertial Odometry Dataset Contact : David Schubert, Nikolaus Demmel, Lukas von Stumberg, Vladyslav Usenko. We present a novel dataset that contains time-synchronized global-shutter and rolling-shutter images, IMU data and ground-truth poses for ten different sequences. Dataset The full dataset can be found at:

2016-04-19T14:15:49+00:00 2016-04-19T14:15:49+00:00 https://cvg.cit.tum.de/data/datasets/topkids?rev=1461068149&do=diff Anonymous anonymous@undisclosed.example.com Deformable 3D Shape Matching with Topological Noise ---------- This dataset consists of a collection of 3D shapes undergoing within-class deformations that include in topological changes. The changes simulate coalescence of spatially close surface regions – a scenario that frequently occurs when dealing with real data under suboptimal acquisition conditions. The dataset is based on the fat kid from the

Deformable 3D Shape Matching with Topological Noise ---------- This dataset consists of a collection of 3D shapes undergoing within-class deformations that include in topological changes. The changes simulate coalescence of spatially close surface regions – a scenario that frequently occurs when dealing with real data under suboptimal acquisition conditions. The dataset is based on the fat kid from the

2026-03-10T09:20:43+00:00 2026-03-10T09:20:43+00:00 https://cvg.cit.tum.de/data/datasets/tum-lsi?rev=1773130843&do=diff Anonymous anonymous@undisclosed.example.com TUM-LSI A Large-Scale Indoor Dataset TUM LSI Dataset[Train/Test Splits] Note The images in this dataset are all in portrait format, horizontal direction images were not rotated. By following PoseNet (ICCV, 2015) we first rescaled the images horizontally to 256 pixels, then did the random crops of size 224x224.

TUM-LSI A Large-Scale Indoor Dataset TUM LSI Dataset[Train/Test Splits] Note The images in this dataset are all in portrait format, horizontal direction images were not rotated. By following PoseNet (ICCV, 2015) we first rescaled the images horizontally to 256 pixels, then did the random crops of size 224x224.

2018-04-17T11:42:54+00:00 2018-04-17T11:42:54+00:00 https://cvg.cit.tum.de/data/datasets/vi-dataset?rev=1523958174&do=diff Anonymous anonymous@undisclosed.example.com Visual-Inertial Dataset Contact : David Schubert, Nikolaus Demmel, Vladyslav Usenko. Visual odometry and SLAM methods have a large variety of applications in domains such as augmented reality or robotics. Complementing vision sensors with inertial measurements tremendously improves tracking accuracy and robustness, and thus has spawned large interest in the development of visual-inertial (VI) odometry approaches. In this paper, we propose the TUM VI benchmark, a novel dataset with a divers…

Visual-Inertial Dataset Contact : David Schubert, Nikolaus Demmel, Vladyslav Usenko. Visual odometry and SLAM methods have a large variety of applications in domains such as augmented reality or robotics. Complementing vision sensors with inertial measurements tremendously improves tracking accuracy and robustness, and thus has spawned large interest in the development of visual-inertial (VI) odometry approaches. In this paper, we propose the TUM VI benchmark, a novel dataset with a divers…

2021-07-07T10:40:48+00:00 2021-07-07T10:40:48+00:00 https://cvg.cit.tum.de/data/datasets/visual-inertial-dataset?rev=1625647248&do=diff Anonymous anonymous@undisclosed.example.com Visual-Inertial Dataset Contact : David Schubert, Nikolaus Demmel, Vladyslav Usenko. The TUM VI Benchmark for Evaluating Visual-Inertial Odometry Visual odometry and SLAM methods have a large variety of applications in domains such as augmented reality or robotics. Complementing vision sensors with inertial measurements tremendously improves tracking accuracy and robustness, and thus has spawned large interest in the development of visual-inertial (VI) odometry approaches. In this paper…

Visual-Inertial Dataset Contact : David Schubert, Nikolaus Demmel, Vladyslav Usenko. The TUM VI Benchmark for Evaluating Visual-Inertial Odometry Visual odometry and SLAM methods have a large variety of applications in domains such as augmented reality or robotics. Complementing vision sensors with inertial measurements tremendously improves tracking accuracy and robustness, and thus has spawned large interest in the development of visual-inertial (VI) odometry approaches. In this paper…

2024-07-16T10:09:52+00:00 2024-07-16T10:09:52+00:00 https://cvg.cit.tum.de/data/datasets/visual-inertial-event-dataset?rev=1721117392&do=diff Anonymous anonymous@undisclosed.example.com tumvie Visual-Inertial Event Dataset Contact : Simon Klenk, Jason Chui, Publications. TUM-VIE: The TUM Stereo Visual-Inertial Event Data Set TUM-VIE is an event camera dataset for developing 3D perception and navigation algorithms. It contains handheld and head-mounted sequences in indoor and outdoor environments with rapid motion during sports and high dynamic range. TUM-VIE includes challenging sequences where state-of-the art VIO fails or results in large drift. Hence, it can…

tumvie Visual-Inertial Event Dataset Contact : Simon Klenk, Jason Chui, Publications. TUM-VIE: The TUM Stereo Visual-Inertial Event Data Set TUM-VIE is an event camera dataset for developing 3D perception and navigation algorithms. It contains handheld and head-mounted sequences in indoor and outdoor environments with rapid motion during sports and high dynamic range. TUM-VIE includes challenging sequences where state-of-the art VIO fails or results in large drift. Hence, it can…