🔔 Share your dataset with the ML community!

Filter by Modality (clear)

Filter by Task

Filter by Language

22 dataset results for 3d meshes

ShapeNetCore is a subset of the full ShapeNet dataset with single clean 3D models and manually verified category and alignment annotations. It covers 55 common object categories with about 51,300 unique 3D models. The 12 object categories of PASCAL 3D+, a popular computer vision 3D benchmark dataset, are all covered by ShapeNetCore.

109 PAPERS • 1 BENCHMARK

COMA

CoMA contains 17,794 meshes of the human face in various expressions

42 PAPERS • 1 BENCHMARK

Scan2CAD

Scan2CAD is an alignment dataset based on 1506 ScanNet scans with 97607 annotated keypoints pairs between 14225 (3049 unique) CAD models from ShapeNet and their counterpart objects in the scans. The top 3 annotated model classes are chairs, tables and cabinets which arises due to the nature of indoor scenes in ScanNet. The number of objects aligned per scene ranges from 1 to 40 with an average of 9.3.

35 PAPERS • 1 BENCHMARK

NoW Benchmark

The goal of this benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods under variations in viewing angle, lighting, and common occlusions.

16 PAPERS • 1 BENCHMARK

Hypersim

For many fundamental scene understanding tasks, it is difficult or impossible to obtain per-pixel ground truth labels from real images. Hypersim is a photorealistic synthetic dataset for holistic indoor scene understanding. It contains 77,400 images of 461 indoor scenes with detailed per-pixel labels and corresponding ground truth geometry.

14 PAPERS • 1 BENCHMARK

SHREC'19 (SHREC'19 track Matching Humans with Different Connectivity)

Shape matching plays an important role in geometry processing and shape analysis. In the last decades, much research has been devoted to improve the quality of matching between surfaces. This huge effort is motivated by several applications such as object retrieval, animation and information transfer just to name a few. Shape matching is usually divided into two main categories: rigid and non rigid matching. In both cases, the standard evaluation is usually performed on shapes that share the same connectivity, in other words, shapes represented by the same mesh. This is mainly due to the availability of a “natural” ground truth that is given for these shapes. Indeed, in most cases the consistent connectivity directly induces a ground truth correspondence between vertices. However, this standard practice obviously does not allow to estimate the robustness of a method with respect to different connectivity. With this track, we propose a benchmark to evaluate the performance of point-to-p

12 PAPERS • 1 BENCHMARK

SSP-3D (Sports Shape and Pose 3D)

SSP-3D is an evaluation dataset consisting of 311 images of sportspersons in tight-fitted clothes, with a variety of body shapes and poses. The images were collected from the Sports-1M dataset. SSP-3D is intended for use as a benchmark for body shape prediction methods. Pseudo-ground-truth 3D shape labels (using the SMPL body model) were obtained via multi-frame optimisation with shape consistency between frames, as described here.

10 PAPERS • 1 BENCHMARK

3D AffordanceNet

3D AffordanceNet is a dataset of 23k shapes for visual affordance. It consists of 56,307 well-defined affordance information annotations for 22,949 shapes covering 18 affordance classes and 23 semantic object categories.

3 PAPERS • 1 BENCHMARK

CAPE (Clothed Auto Person Encoding)

The CAPE dataset is a 3D dynamic dataset of clothed humans, featuring:

3 PAPERS • 1 BENCHMARK

AMA (Articulated Mesh Animation)

Articulated Mesh Animation (AMA) is a real-world dataset containing 10 mesh sequences depicting 3 different humans performing various actions

2 PAPERS • NO BENCHMARKS YET

HOPE-Image (Household Objects for Pose Estimation)

The NVIDIA HOPE datasets consist of RGBD images and video sequences with labeled 6-DoF poses for 28 toy grocery objects. The toy grocery objects are readily available for purchase and have ideal size and weight for robotic manipulation. 3D textured meshes for generating synthetic training data are provided.

2 PAPERS • NO BENCHMARKS YET

ANIM (ANimals in Motion)

It comprises synthetic mesh sequences from Deformation Transfer for Triangle Meshes.

1 PAPER • 1 BENCHMARK

ARCTIC

ARCTIC (Articulated Objects in Free-form Hand Interaction)

ARCTIC is a dataset of free-form interactions of hands and articulated objects. ARCTIC has 1.2M images paired with accurate 3D meshes for both hands and for objects that move and deform over time. The dataset also provides hand-object contact information.

1 PAPER • NO BENCHMARKS YET

BuildingNet

BuildingNet is a large-scale dataset of 3D building models whose exteriors are consistently labeled. The dataset consists on 513K annotated mesh primitives, grouped into 292K semantic part components across 2K building models. The dataset covers several building categories, such as houses, churches, skyscrapers, town halls, libraries, and castles.

1 PAPER • 1 BENCHMARK

Fast Linking Numbers of Loopy Structures Dataset

1 PAPER • NO BENCHMARKS YET

Gait3D

Gait3D is a large-scale 3D representation-based gait recognition dataset. It contains 4,000 subjects and over 25,000 sequences extracted from 39 cameras in an unconstrained indoor scene.

1 PAPER • 2 BENCHMARKS

HOPE-Video (Household Objects for Pose Estimation)

The HOPE-Video dataset contains 10 video sequences (2038 frames) with 5-20 objects on a tabletop scene captured by a robot arm-mounted RealSense D415 RGBD camera. In each sequence, the camera is moved to capture multiple views of a set of objects in the robotic workspace. First COLMAP was applied to refine the camera poses (keyframes at 6~fps) provided by forward kinematics and RGB calibration from RealSense to Baxter's wrist camera. 3D dense point cloud was then generated via CascadeStereo (included for each sequence in 'scene.ply'). Ground truth poses for the HOPE objects models in the world coordinate system were annotated manually using the CascadeStereo point clouds. The following are provided for each frame:

1 PAPER • NO BENCHMARKS YET

PLAD (Point Line and Depth dataset)

Click to add a brief description of the dataset (Markdown and LaTeX enabled).

1 PAPER • NO BENCHMARKS YET

The RBO Dataset of Articulated Objects and Interactions

The RBO dataset of articulated objects and interactions is a collection of 358 RGB-D video sequences (67:18 minutes) of humans manipulating 14 articulated objects under varying conditions (light, perspective, background, interaction). All sequences are annotated with ground truth of the poses of the rigid parts and the kinematic state of the articulated object (joint states) obtained with a motion capture system. We also provide complete kinematic models of these objects (kinematic structure and three-dimensional textured shape models). In 78 sequences the contact wrenches during the manipulation are also provided.

1 PAPER • NO BENCHMARKS YET

WWU DUNEuro reference data set

WWU DUNEuro reference data set (The WWU DUNEuro reference data set for combined EEG/MEG source analysis)

The provided dataset consists of high-quality realistic head models and combined EEG/MEG data which can be used for state-of-the-art methods in brain research, such as modern finite element methods (FEM) to compute the EEG/MEG forward problems using the software toolbox DUNEuro (http://duneuro.org).

1 PAPER • NO BENCHMARKS YET

BTFDBB (BTF Database Bonn)

Reflectance measurements of Bidirectional Texture Functions (BTFs)

0 PAPER • NO BENCHMARKS YET

InfiniteRep

InfiniteRep is a synthetic, open-source dataset for fitness and physical therapy (PT) applications. It includes 1k videos of diverse avatars performing multiple repetitions of common exercises. It includes significant variation in the environment, lighting conditions, avatar demographics, and movement trajectories. From cadence to kinematic trajectory, each rep is done slightly differently -- just like real humans. InfiniteRep videos are accompanied by a rich set of pixel-perfect labels and annotations, including frame-specific repetition counts.

0 PAPER • NO BENCHMARKS YET

Datasets

22 dataset results for 3d meshes