153 datasets found

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

The DTU benchmark dataset consists of scenes featuring real objects, including images, corresponding camera poses, and reference point clouds obtained from a structured-light...

Generating geometric 3D reconstructions from Neural Radiance Fields (NeRFs) is of great interest. However, accurate and complete reconstructions based on the density values are...

The authors propose a novel Factorized 3D Gaussian Splatting (F-3DGS) method to reduce the storage requirements while maintaining image quality compared to 3DGS.

AXYZ is a dataset of 207 3D scans of people in various poses.

The dataset used for testing and evaluation of the volumetric performance capture system.

ARCH (Animatable Reconstruction of Clothed Humans) is a novel end-to-end framework for accurate reconstruction of animation-ready 3D clothed humans from a monocular image.

The KITTI Vision Benchmark Suite is a dataset used for object detection and tracking in autonomous vehicles.

The Middlebury dataset is a benchmark for stereo vision and 3D reconstruction.

Shapenet is a large-scale synthesis 3D object dataset, where we follow [9] to use the official test splits of chair, car, and motorbike categories for evaluation since they...

DeepFashion3D is a dataset for 3D garment reconstruction from single images.

Google Scanned Object dataset contains 3D scanned household items.

Envision3D generates 32 dense view images and extracts high-quality 3D content from one input image in 3-4 minutes.

CAPE dataset

The dataset used for volumetric performance capture and rendering from a single RGB camera.

GALA: Generating Animatable Layered Assets from a Single Scan

Real-time 3D object reconstruction pipeline based on streamed instance segmented data

The MITI Dataset provides multimodal sensor information from IMU, stereoscopic video, and infrared IR tracking as ground truth for evaluating SLAM/SfM/3D...

Dense pixel matching is required for many computer vision algorithms such as disparity, optical flow or scene flow estimation. Feature Pyramid Networks (FPN) have proven to be a...

The Tanks and Temples dataset is a benchmark for 3D reconstruction from multi-view images. It consists of 50 images of 10 scenes, each with 5 views.