10 datasets found

A dataset of 121 video sequences of common household objects, captured by GoPro Hero9 action cameras at 30 FPS and 1920 × 1080 resolution.

We present MVSGaussian, a new fast generalizable Gaussian Splatting method. We evaluate our method on the widely-used DTU [1], Real Forward-facing [28], NeRF Synthetic [29], and...

The dataset used in the paper is the LLFF dataset, which contains real-world scenes and is used for training and testing the proposed neural radiance field model.

A dataset of synthetic photorealistic images for training and testing material-aware diffusion models

The dataset contains five tabletop real scenes imaged by 352 cameras in a dome.

The dataset contains 80 real-world scenes with image sequences and structured light 3D scans as reference data.

LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation

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

Large scale datasets [18, 17, 27, 6] boosted text conditional image generation quality. However, in some domains it could be difficult to make such datasets and usually it could...

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...