85 datasets found

A dataset of ground telescope images of a satellite in low-Earth orbit, with images affected by atmospheric turbulence and light pollution.

The dataset used in the paper is a text-to-3D generation framework, named the LucidDreamer, to distill high-fidelity textures and shapes from pretrained 2D diffusion models.

The dataset used for training and testing the proposed RGBD-based obstacle avoidance system for visually impaired people.

The PoseCNN dataset is a dataset for 6D object pose estimation in cluttered scenes.

The KinectFusion dataset is a real-time dense surface mapping and tracking system.

Instant Neural Graphics Primitives with a multiresolution hash encoding

Zero-1-to-3: Zero-shot one image to 3D object.

The Replica dataset provides real-world scenes which we use to evaluate and compare our approach with related work. The dataset consists of high quality 3D reconstructions of 5...

A dataset of synthetic images of hands performing various actions.

A dataset of images of hands performing various actions.

A dataset of synthetic images of hands performing various actions.

HumanML3D is a text-to-motion dataset built upon AMASS dataset and HumanAct12. It provides a wide range of motion-language pairs which cover ordinary activities, such as...

A unified framework for single image-to-3D creation that integrates multi-view image generation and 3D reconstruction in a recursive diffusion process.

Fine-Grained Visual Classification (FGVC) is an important computer vision prob-lem that involves small diversity within the different classes, and often requires expert...

The Replica dataset contains 18 various highly photo-realistic indoor environments. It provides dense-mesh, high-resolution RGBD images and a large range of instance annotations...

Semantic segmentation is a crucial and challenging task for image understanding. It aims to predict a dense labeling map for the input image, which assigns each pixel a unique...

The Objaverse dataset contains around 800k 3D objects. After adopting simple filter leveraging CLIP [27] to remove the objects whose rendered images are not relevant to its...

Joint 2D-3D-Semantic Data for Indoor Scene Understanding.

The dataset FAUST contains 10 different bodies in 10 different poses. The irregular surface meshes have 6890 vertices. The dataset is used to evaluate the reconstruction quality...

The DTU dataset is a large-scale dataset for multi-view stereo depth inference. It contains over 100 scans taken under 7 different lighting conditions and fixed camera...