3D Shape Reconstruction

Local Light Field Fusion (LLFF) is a practical and robust deep learning solution for capturing and rendering novel views of complex real-world scenes for virtual exploration. The dataset consists of both renderings and real images of natural scenes. The synthetic images are rendered from the SUNCG and UnrealCV where SUNCG contains 45000 simplistic house and room environments with texture-mapped surfaces and low geometric complexity. UnrealCV contains a few large-scale environments modeled and rendered with extreme detail. The real images are 24 scenes captured from a handheld cellphone.

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. Source: http://pix3d.csail.mit.edu/ Image Source: http://pix3d.csail.mit.edu/

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. Source: https://github.com/apple/ml-hypersim Image Source: https://github.com/apple/ml-hypersim

ApolloCar3DT is a dataset that contains 5,277 driving images and over 60K car instances, where each car is fitted with an industry-grade 3D CAD model with absolute model size and semantically labelled keypoints. This dataset is above 20 times larger than PASCAL3D+ and KITTI, the current state-of-the-art. Source: ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving Image Source: http://apolloscape.auto/car_instance.html

4DFAB is a large scale database of dynamic high-resolution 3D faces which consists of recordings of 180 subjects captured in four different sessions spanning over a five-year period (2012 - 2017), resulting in a total of over 1,800,000 3D meshes. It contains 4D videos of subjects displaying both spontaneous and posed facial behaviours. The database can be used for both face and facial expression recognition, as well as behavioural biometrics. It can also be used to learn very powerful blendshapes for parametrising facial behaviour. Source: ibug

HUMAN4D is a large and multimodal 4D dataset that contains a variety of human activities simultaneously captured by a professional marker-based MoCap, a volumetric capture and an audio recording system. By capturing 2 female and $2$ male professional actors performing various full-body movements and expressions, HUMAN4D provides a diverse set of motions and poses encountered as part of single- and multi-person daily, physical and social activities (jumping, dancing, etc. ), along with multi-RGBD (mRGBD), volumetric and audio data. Description from: HUMAN4D: A Human-Centric Multimodal Dataset for Motions and Immersive Media Image source: https://github.com/tofis/human4d_dataset

The Few-Shot Object Learning (FewSOL) dataset can be used for object recognition with a few images per object. It contains 336 real-world objects with 9 RGB-D images per object from different views. Object segmentation masks, object poses and object attributes are provided. In addition, synthetic images generated using 330 3D object models are used to augment the dataset. FewSOL dataset can be used to study a set of few-shot object recognition problems such as classification, detection and segmentation, shape reconstruction, pose estimation, keypoint correspondences and attribute recognition. Motivation: If robots can recognize objects from a few exemplar images, it is possible to scale up the number of objects a robot can recognize because collecting a few images per object is a much easier process compared to building a 3D model of an object. In addition, models trained in the meta-learning setting can generalize to new objects without re-training.

A dataset of high resolution, textured scans of articulated left feet, useful for 3D shape representation learning.

The dataset is designed specifically to solve a range of computer vision problems (2D-3D tracking, posture) faced by biologists while designing behavior studies with animals. Typically, datasets for animal-specific vision tasks are created using open-source video material. This might be effective for an initial start, but these methods are not deployment ready for the behavior community. Therefore, we designed a semi-automated method for biologists to create well-curated datasets at a large scale for the ML and Vision community. 3D-POP is the first dataset with 3D ground truth for multi-animal, multi-view tracking problems. Highlight: The dataset is captured with the intention of using it for various vision problems and with different levels of complexity (no of cameras, no of individuals) Video explanation: Link to YouTube video Video teaser: Link to YouTube video ## Dataset Features: ### Marker-based videos: - 6 hours+ of annotations of 18 individuals (groups of 1, 2, 5, 10). - Bounding box - Trajectories (2D and 3D) - Posture (2D and 3D) with 9 key points - Identities - Total of 57 sequences (4K) with 4 views. - Dataset customization* (Users can modify the dataset and add key points to the dataset) ### Markerless: - 1Hr+ videos of 18 individuals in groups of 1, 2, 5, 11. The birds have no markers. This data is provided as test cases and unsupervised approaches. ## Problems: ### 2D domain: - Position, Posture of birds (different group sizes n = 1, 2, 5, 10) with Single/Multiview. - Tracking with single - multiview ### 3D domain: - Position, Posture of birds (different group sizes n = 1, 2, 5, 10) with Single/Multiview. - Tracking with single - multiview ### Fine-grained recognition: - Identity tracking with ground truth. ### Unsupervised learning: - 2D or 3D posture problems ## Idea: The dataset is created with a motion capture system, using the 6-DOF tracking ability. Assumptions are that head and body act as rigid bodies when birds walk and forage (proved with experiment). Therefore, we get the 3D position of key points by tracking head/body orientation.

Large Shape and Texture dataset (LAS&T) is a giant dataset of shapes and textures for tasks of visual shapes and textures identification and retrieval from single image. LAS&T is the largest and most diverse dataset for shape, texture and material recognition and retrieval in 2D and 3D with 650,000 images, based on real world shapes and textures ## Overview The LAS&T Dataset aims to test the most basic aspect of vision in the most general way. Mainly the ability to identify any shape, texture, and material in any setting and environment, without being limited to specific types or classes of objects, materials, and environments. For shapes, this means identifying and retrieving any shape in 2D or 3D with every element of the shape changed between images, including the shape material and texture, orientation, size, and environment. For textures and materials, the goal is to recognize the same texture or material when appearing on different objects, environments, and light conditions. The dataset relies on shapes, textures, and materials extracted from real-world images, leading to an almost unlimited quantity and diversity of real-world natural patterns. Each section of the dataset (shapes, and textures), contains 3D parts that rely on physics-based scenes with realistic light materials and object simulation and abstract 2D parts. In addition, the real-world benchmark for 3D shapes. ## The dataset divided to several parts 3D shape recognition and retrieval. 2D shape recognition and retrieval. 3D Materials recognition and retrieval. 2D Texture recognition and retrieval. Each can be used independently for training and testing. Additional assets are a set of 350,000 natural 2D shapes extracted from real-world images 3D shape recognition real-world images benchmark

The SurfaceGrid dataset contains nearly a million 512x512 images for use in training neural networks on shape-fron-surface contour task.