158 datasets found

Dynamic 3D Gaussians: Tracking by persistent dynamic view synthesis.

Scannet: Richly-annotated 3D reconstructions of indoor scenes.

3D-retr: End-to-end single and multi-view 3D reconstruction with transformers

Pix2vox: Context-aware 3D reconstruction from single and multi-view images

Few-shot single-view 3D reconstruction with memory prior contrastive network

UMIFormer: Mining the Correlations between Similar Tokens for Multi-View 3D Reconstruction

The KITTI 2012 and 2015 datasets are used for stereo matching experiments.

The dataset used in this paper for 3D point cloud classification and adversarial example generation.

The MobileBrick dataset contains videos of LEGO models, with corresponding 3D ground-truth meshes.

Pedestrian trajectory forecasting is a fundamental task in multiple utility areas, such as self-driving, autonomous robots, and surveillance systems. The future trajectory...

A novel 3D point cloud registration framework that boosts models with generative data for improved performance.

The mip-NeRF 360 dataset contains 360-degree panoramic images of indoor and outdoor scenes.

Our dataset contains 7 real-world nighttime scenes captured with cell phones, with varying exposure and lighting conditions.

A large-scale 3D model repository containing over 16,000 3D models.

Neural Radiance Fields (NeRFs) model a 3D scene as a volumetric function, which can be rendered from arbitrary viewpoints to generate highly-realistic images.

The DTU, BlendMVS, and H3DS datasets are used for evaluating the performance of the VQ-NeRF method.

The 3DMatch [26] is a well-known indoor registration dataset of 62 scenes captured by RGBD sensor.

Seeing 3D chairs: exemplar part-based 2D-3D alignment using a large dataset of CAD models

A synthetic dataset of shoes for training and testing the proposed method.

A unified object-centric implicit representation that can be used for RGB and depth novel view rendering, 3D reconstruction, and proposing stable grasps.