78 datasets found

The dataset used in the paper for training and testing the RRM method.

Blender is a 3D creation software that supports modeling, rigging, animation, rendering, and more.

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 FLNeRF dataset is a 3D facial landmarks dataset for neural radiance fields. It contains 110 expressions, 5 identities, and 20 basic expressions.

DP-NeRF is a novel NeRF framework from blurry inputs, that imposes two physical priors to effectively construct a clean NeRF.

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.

The recent advances in 3D Gaussian Splatting (3DGS) show promising results on the novel view synthesis (NVS) task. With its superior rendering performance and high-fidelity...

The recent advances in 3D Gaussian Splatting (3DGS) show promising results on the novel view synthesis (NVS) task. With its superior rendering performance and high-fidelity...

The NeRF Synthetic dataset is a synthetic dataset created for testing the performance of neural radiance fields.

The dataset used in the paper is a real-world dataset containing 5 datasets: Google Scanned Object dataset, three forward-facing datasets, and DTU dataset.

The dataset used in the paper is a synthetic 3D dataset containing 13 categories of objects.

The dataset used in the paper is a 3D environment with a fox and a table.

The dataset used in the paper is a 3D environment with a bicycle and a bench.

The dataset used in the paper is a 3D environment with a cubic mesh and reflective textures, and synthetic mesh objects.

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

Deformable Neural Radiance Fields extend NeRF by modeling non-rigidly deforming scenes.

The dataset is used for learning a diffusion prior for NeRFs that can generate NeRFs and be used as a prior for different test-time optimization algorithms.

A 360-degree scene from the NeRF-Art dataset.

A 360-degree scene from the IN2N dataset.