ShapeNet is a large scale repository for 3D CAD models developed by researchers from Stanford University, Princeton University and the Toyota Technological Institute at Chicago, USA. The repository contains over 300M models with 220,000 classified into 3,135 classes arranged using WordNet hypernym-hyponym relationships. ShapeNet Parts subset contains 31,693 meshes categorised into 16 common object classes (i.e. table, chair, plane etc.). Each shapes ground truth contains 2-5 parts (with a total of 50 part classes).

1,195 PAPERS • 11 BENCHMARKS

The ModelNet40 dataset contains synthetic object point clouds. As the most widely used benchmark for point cloud analysis, ModelNet40 is popular because of its various categories, clean shapes, well-constructed dataset, etc. The original ModelNet40 consists of 12,311 CAD-generated meshes in 40 categories (such as airplane, car, plant, lamp), of which 9,843 are used for training while the rest 2,468 are reserved for testing. The corresponding point cloud data points are uniformly sampled from the mesh surfaces, and then further preprocessed by moving to the origin and scaling into a unit sphere.

952 PAPERS • 7 BENCHMARKS

The nuScenes dataset is a large-scale autonomous driving dataset. The dataset has 3D bounding boxes for 1000 scenes collected in Boston and Singapore. Each scene is 20 seconds long and annotated at 2Hz. This results in a total of 28130 samples for training, 6019 samples for validation and 6008 samples for testing. The dataset has the full autonomous vehicle data suite: 32-beam LiDAR, 6 cameras and radars with complete 360° coverage. The 3D object detection challenge evaluates the performance on 10 classes: cars, trucks, buses, trailers, construction vehicles, pedestrians, motorcycles, bicycles, traffic cones and barriers.

742 PAPERS • 15 BENCHMARKS

The Stanford 3D Indoor Scene Dataset (S3DIS) dataset contains 6 large-scale indoor areas with 271 rooms. Each point in the scene point cloud is annotated with one of the 13 semantic categories.

293 PAPERS • 7 BENCHMARKS

The Matterport3D dataset is a large RGB-D dataset for scene understanding in indoor environments. It contains 10,800 panoramic views inside 90 real building-scale scenes, constructed from 194,400 RGB-D images. Each scene is a residential building consisting of multiple rooms and floor levels, and is annotated with surface construction, camera poses, and semantic segmentation.

268 PAPERS • 4 BENCHMARKS

The Waymo Open Dataset is comprised of high resolution sensor data collected by autonomous vehicles operated by the Waymo Driver in a wide variety of conditions.

209 PAPERS • 9 BENCHMARKS

The Pascal3D+ multi-view dataset consists of images in the wild, i.e., images of object categories exhibiting high variability, captured under uncontrolled settings, in cluttered scenes and under many different poses. Pascal3D+ contains 12 categories of rigid objects selected from the PASCAL VOC 2012 dataset. These objects are annotated with pose information (azimuth, elevation and distance to camera). Pascal3D+ also adds pose annotated images of these 12 categories from the ImageNet dataset.

204 PAPERS • 1 BENCHMARK

The 3D Poses in the Wild dataset is the first dataset in the wild with accurate 3D poses for evaluation. While other datasets outdoors exist, they are all restricted to a small recording volume. 3DPW is the first one that includes video footage taken from a moving phone camera.

200 PAPERS • 4 BENCHMARKS

MPI-INF-3DHP is a 3D human body pose estimation dataset consisting of both constrained indoor and complex outdoor scenes. It records 8 actors performing 8 activities from 14 camera views. It consists on >1.3M frames captured from the 14 cameras.

176 PAPERS • 4 BENCHMARKS

SUNCG is a large-scale dataset of synthetic 3D scenes with dense volumetric annotations.

173 PAPERS • NO BENCHMARKS YET

AMASS is a large database of human motion unifying different optical marker-based motion capture datasets by representing them within a common framework and parameterization. AMASS is readily useful for animation, visualization, and generating training data for deep learning.

133 PAPERS • 1 BENCHMARK

ScanObjectNN is a newly published real-world dataset comprising of 2902 3D objects in 15 categories. It is a challenging point cloud classification datasets due to the background, missing parts and deformations.

130 PAPERS • 2 BENCHMARKS

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.

124 PAPERS • 1 BENCHMARK

The Replica Dataset is a dataset of high quality reconstructions of a variety of indoor spaces. Each reconstruction has clean dense geometry, high resolution and high dynamic range textures, glass and mirror surface information, planar segmentation as well as semantic class and instance segmentation.

119 PAPERS • 2 BENCHMARKS

The Chairs dataset contains rendered images of around 1000 different three-dimensional chair models.

107 PAPERS • 1 BENCHMARK

The Pix3D dataset is a large-scale benchmark of diverse image-shape pairs with pixel-level 2D-3D alignment. Pix3D has wide applications in shape-related tasks including reconstruction, retrieval, viewpoint estimation, etc.

102 PAPERS • 5 BENCHMARKS

AFLW2000-3D is a dataset of 2000 images that have been annotated with image-level 68-point 3D facial landmarks. This dataset is used for evaluation of 3D facial landmark detection models. The head poses are very diverse and often hard to be detected by a CNN-based face detector.

97 PAPERS • 8 BENCHMARKS

SUN3D contains a large-scale RGB-D video database, with 8 annotated sequences. Each frame has a semantic segmentation of the objects in the scene and information about the camera pose. It is composed by 415 sequences captured in 254 different spaces, in 41 different buildings. Moreover, some places have been captured multiple times at different moments of the day.

90 PAPERS • NO BENCHMARKS YET

The smallNORB dataset is a datset for 3D object recognition from shape. It contains images of 50 toys belonging to 5 generic categories: four-legged animals, human figures, airplanes, trucks, and cars. The objects were imaged by two cameras under 6 lighting conditions, 9 elevations (30 to 70 degrees every 5 degrees), and 18 azimuths (0 to 340 every 20 degrees). The training set is composed of 5 instances of each category (instances 4, 6, 7, 8 and 9), and the test set of the remaining 5 instances (instances 0, 1, 2, 3, and 5).

90 PAPERS • 1 BENCHMARK

PartNet is a consistent, large-scale dataset of 3D objects annotated with fine-grained, instance-level, and hierarchical 3D part information. The dataset consists of 573,585 part instances over 26,671 3D models covering 24 object categories. This dataset enables and serves as a catalyst for many tasks such as shape analysis, dynamic 3D scene modeling and simulation, affordance analysis, and others.

89 PAPERS • 3 BENCHMARKS

FaceWarehouse is a 3D facial expression database that provides the facial geometry of 150 subjects, covering a wide range of ages and ethnic backgrounds.

80 PAPERS • NO BENCHMARKS YET

The BP4D-Spontaneous dataset is a 3D video database of spontaneous facial expressions in a diverse group of young adults. Well-validated emotion inductions were used to elicit expressions of emotion and paralinguistic communication. Frame-level ground-truth for facial actions was obtained using the Facial Action Coding System. Facial features were tracked in both 2D and 3D domains using both person-specific and generic approaches. The database includes forty-one participants (23 women, 18 men). They were 18 – 29 years of age; 11 were Asian, 6 were African-American, 4 were Hispanic, and 20 were Euro-American. An emotion elicitation protocol was designed to elicit emotions of participants effectively. Eight tasks were covered with an interview process and a series of activities to elicit eight emotions. The database is structured by participants. Each participant is associated with 8 tasks. For each task, there are both 3D and 2D videos. As well, the Metadata include manually annotated

77 PAPERS • 3 BENCHMARKS

FreiHAND is a 3D hand pose dataset which records different hand actions performed by 32 people. For each hand image, MANO-based 3D hand pose annotations are provided. It currently contains 32,560 unique training samples and 3960 unique samples for evaluation. The training samples are recorded with a green screen background allowing for background removal. In addition, it applies three different post processing strategies to training samples for data augmentation. However, these post processing strategies are not applied to evaluation samples.

65 PAPERS • 1 BENCHMARK

Aachen Day-Night is a dataset designed for benchmarking 6DOF outdoor visual localization in changing conditions. It focuses on localizing high-quality night-time images against a day-time 3D model. There are 14,607 images with changing conditions of weather, season and day-night cycles.

60 PAPERS • 1 BENCHMARK

The ABC Dataset is a collection of one million Computer-Aided Design (CAD) models for research of geometric deep learning methods and applications. Each model is a collection of explicitly parametrized curves and surfaces, providing ground truth for differential quantities, patch segmentation, geometric feature detection, and shape reconstruction. Sampling the parametric descriptions of surfaces and curves allows generating data in different formats and resolutions, enabling fair comparisons for a wide range of geometric learning algorithms.

55 PAPERS • NO BENCHMARKS YET

Semantic3D is a point cloud dataset of scanned outdoor scenes with over 3 billion points. It contains 15 training and 15 test scenes annotated with 8 class labels. This large labelled 3D point cloud data set of natural covers a range of diverse urban scenes: churches, streets, railroad tracks, squares, villages, soccer fields, castles to name just a few. The point clouds provided are scanned statically with state-of-the-art equipment and contain very fine details.

55 PAPERS • 1 BENCHMARK

T-LESS is a dataset for estimating the 6D pose, i.e. translation and rotation, of texture-less rigid objects. The dataset features thirty industry-relevant objects with no significant texture and no discriminative color or reflectance properties. The objects exhibit symmetries and mutual similarities in shape and/or size. Compared to other datasets, a unique property is that some of the objects are parts of others. The dataset includes training and test images that were captured with three synchronized sensors, specifically a structured-light and a time-of-flight RGB-D sensor and a high-resolution RGB camera. There are approximately 39K training and 10K test images from each sensor. Additionally, two types of 3D models are provided for each object, i.e. a manually created CAD model and a semi-automatically reconstructed one. Training images depict individual objects against a black background. Test images originate from twenty test scenes having varying complexity, which increases from

55 PAPERS • 2 BENCHMARKS

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

54 PAPERS • 1 BENCHMARK

MuPoTs-3D (Multi-person Pose estimation Test Set in 3D) is a dataset for pose estimation composed of more than 8,000 frames from 20 real-world scenes with up to three subjects. The poses are annotated with a 14-point skeleton model.

48 PAPERS • 4 BENCHMARKS

The SEMAINE videos dataset contains spontaneous data capturing the audiovisual interaction between a human and an operator undertaking the role of an avatar with four personalities: Poppy (happy), Obadiah (gloomy), Spike (angry) and Prudence (pragmatic). The audiovisual sequences have been recorded at a video rate of 25 fps (352 x 288 pixels). The dataset consists of audiovisual interaction between a human and an operator undertaking the role of an agent (Sensitive Artificial Agent). SEMAINE video clips have been annotated with couples of epistemic states such as agreement, interested, certain, concentration, and thoughtful with continuous rating (within the range [1,-1]) where -1 indicates most negative rating (i.e: No concentration at all) and +1 defines the highest (Most concentration). Twenty-four recording sessions are used in the Solid SAL scenario. Recordings are made of both the user and the operator, and there are usually four character interactions in each recording session,

44 PAPERS • 1 BENCHMARK

SceneNN is an RGB-D scene dataset consisting of more than 100 indoor scenes. The scenes are captured at various places, e.g., offices, dormitory, classrooms, pantry, etc., from University of Massachusetts Boston and Singapore University of Technology and Design. All scenes are reconstructed into triangle meshes and have per-vertex and per-pixel annotation. The dataset is additionally enriched with fine-grained information such as axis-aligned bounding boxes, oriented bounding boxes, and object poses.

43 PAPERS • 1 BENCHMARK

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.

41 PAPERS • 1 BENCHMARK

Structured3D is a large-scale photo-realistic dataset containing 3.5K house designs (a) created by professional designers with a variety of ground truth 3D structure annotations (b) and generate photo-realistic 2D images (c). The dataset consists of rendering images and corresponding ground truth annotations (e.g., semantic, albedo, depth, surface normal, layout) under different lighting and furniture configurations.

40 PAPERS • NO BENCHMARKS YET

The PanoContext dataset contains 500 annotated cuboid layouts of indoor environments such as bedrooms and living rooms.

34 PAPERS • 1 BENCHMARK

BUFF consists of 5 subjects, 3 male and 2 female wearing 2 clothing styles: a) t-shirt and long pants and b) a soccer outfit. They perform 3 different motions i) hips ii) tilt_twist_left iii) shoulders_mill.

32 PAPERS • 1 BENCHMARK

The Florence 3D faces dataset consists of:

32 PAPERS • 1 BENCHMARK

The TotalCapture dataset consists of 5 subjects performing several activities such as walking, acting, a range of motion sequence (ROM) and freestyle motions, which are recorded using 8 calibrated, static HD RGB cameras and 13 IMUs attached to head, sternum, waist, upper arms, lower arms, upper legs, lower legs and feet, however the IMU data is not required for our experiments. The dataset has publicly released foreground mattes and RGB images. Ground-truth poses are obtained using a marker-based motion capture system, with the markers are <5mm in size. All data is synchronised and operates at a framerate of 60Hz, providing ground truth poses as joint positions.

31 PAPERS • 2 BENCHMARKS

AGORA is a synthetic human dataset with high realism and accurate ground truth. It consists of around 14K training and 3K test images by rendering between 5 and 15 people per image using either image-based lighting or rendered 3D environments, taking care to make the images physically plausible and photoreal. In total, AGORA contains 173K individual person crops. AGORA provides (1) SMPL/SMPL-X parameters and (2) segmentation masks for each subject in images.

29 PAPERS • 4 BENCHMARKS

The H3D is a large scale full-surround 3D multi-object detection and tracking dataset. It is gathered from HDD dataset, a large scale naturalistic driving dataset collected in San Francisco Bay Area. H3D consists of following features:

29 PAPERS • NO BENCHMARKS YET

The Microsoft Research Cambridge-12 Kinect gesture data set consists of sequences of human movements, represented as body-part locations, and the associated gesture to be recognized by the system. The data set includes 594 sequences and 719,359 frames—approximately six hours and 40 minutes—collected from 30 people performing 12 gestures. In total, there are 6,244 gesture instances. The motion files contain tracks of 20 joints estimated using the Kinect Pose Estimation pipeline. The body poses are captured at a sample rate of 30Hz with an accuracy of about two centimeters in joint positions.

29 PAPERS • 2 BENCHMARKS

The SemanticPOSS dataset for 3D semantic segmentation contains 2988 various and complicated LiDAR scans with large quantity of dynamic instances. The data is collected in Peking University and uses the same data format as SemanticKITTI.

28 PAPERS • 1 BENCHMARK

The Gaming 3D Dataset (G3D) focuses on real-time action recognition in a gaming scenario. It contains 10 subjects performing 20 gaming actions: “punch right”, “punch left”, “kick right”, “kick left”, “defend”, “golf swing”, “tennis swing forehand”, “tennis swing backhand”, “tennis serve”, “throw bowling ball”, “aim and fire gun”, “walk”, “run”, “jump”, “climb”, “crouch”, “steer a car”, “wave”, “flap” and “clap”.

26 PAPERS • 2 BENCHMARKS

InteriorNet is a RGB-D for large scale interior scene understanding and mapping. The dataset contains 20M images created by pipeline:

23 PAPERS • NO BENCHMARKS YET

Dynamic FAUST extends the FAUST dataset to dynamic 4D data. It consists of high-resolution 4D scans of human subjects in motion, captured at 60 fps.

22 PAPERS • NO BENCHMARKS YET

Habitat-Matterport 3D (HM3D) is a large-scale dataset of 1,000 building-scale 3D reconstructions from a diverse set of real-world locations. Each scene in the dataset consists of a textured 3D mesh reconstruction of interiors such as multi-floor residences, stores, and other private indoor spaces.

21 PAPERS • NO BENCHMARKS YET

ReferIt3D provides two large-scale and complementary visio-linguistic datasets: i) Sr3D, which contains 83.5K template-based utterances leveraging spatial relations among fine-grained object classes to localize a referred object in a scene, and ii) Nr3D which contains 41.5K natural, free-form, utterances collected by deploying a 2-player object reference game in 3D scenes. This dataset can be used for 3D visual grounding and 3D dense captioning tasks.

21 PAPERS • NO BENCHMARKS YET

MINOS is a simulator designed to support the development of multisensory models for goal-directed navigation in complex indoor environments. MINOS leverages large datasets of complex 3D environments and supports flexible configuration of multimodal sensor suites.

20 PAPERS • NO BENCHMARKS YET

Obstacle Tower is a high fidelity, 3D, 3rd person, procedurally generated environment for reinforcement learning. An agent playing Obstacle Tower must learn to solve both low-level control and high-level planning problems in tandem while learning from pixels and a sparse reward signal. Unlike other benchmarks such as the Arcade Learning Environment, evaluation of agent performance in Obstacle Tower is based on an agent’s ability to perform well on unseen instances of the environment.

20 PAPERS • 6 BENCHMARKS