153 datasets found

The dataset is a collection of 3D point clouds for reconstruction.

NeRF [33] has demonstrated amazing ability to synthesize images of 3D scenes from novel views. However, they rely upon specialized volumetric rendering algorithms based on ray...

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...

Feature matching is a fundamental problem for many computer vision tasks, such as object recognition, structure from motion, and simultaneous localization and mapping.

Common Objects in 3D: Large-scale learning and evaluation of real-life 3D category reconstruction

Google Scanned Objects is a real-scanned 3D object dataset and we use all its 1030 samples for evaluation unlike existing works [29, 31] that only use 30 of them.

A large-scale dataset of 3D objects for training and testing 3D reconstruction models.

The DyNeRF dataset contains 3D dynamic scenes with moving or deforming objects.

The MeetRoom dataset contains 3D dynamic scenes with moving or deforming objects.

The D-NeRF dataset contains 3D dynamic scenes with moving or deforming objects.

The Mip-NeRF360 dataset contains scenes taken from a 360 degree view, with emphasis on minimizing photometric variations.

The DTU dataset is a large-scale dataset for 3D reconstruction and editing. It contains 15 scenes with images of 1600x1200 resolution and accompanying foreground masks.

The LLFF dataset contains 8 forward-facing scenes. Following [19, 26, 35, 42], we take every 8-th image as the novel views for testing. The input views are evenly sampled across...