13 datasets found

A new system for novel view synthesis that can rapidly obtain the neural representation of a scene, passing a single time through all available source views.

Consistent-1-to-3 is a novel framework that generates consistent images of any objects from any viewpoint given a single image.

A large-scale outdoor multi-modal dataset and benchmark for novel view synthesis and implicit scene reconstruction.

NeRF dataset for large-scale urban scene reconstruction

The dataset used in the paper for 3D geometry reconstruction and novel view synthesis.

The dataset used in the paper for 3D geometry reconstruction and novel view synthesis.

A system for 3D reconstruction and novel view synthesis from an arbitrary number of unposed images.

The dataset used in the paper is the NVIDIA Dynamic Scene Dataset, which contains 8 diverse scenes with 12 sequences captured by synchronized cameras at fixed positions.

The dataset used for training and testing the Uncertainty-guided Optimal Transport (UGOT) approach for depth supervision in sparse-view 3D Gaussian splatting for novel view...

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.

The Sparsenerf dataset is used for few-shot novel view synthesis.

The FlipNeRF dataset is used for few-shot novel view synthesis.

The FreeNeRF dataset is used for few-shot novel view synthesis.