54 datasets found

CompoNeRF: Text-guided Multi-object Compositional NeRF with Editable 3D Scene Layout

The Unbounded-360 dataset is a large-scale indoor scene dataset used for training and testing the proposed MixRT method.

ManifoldNeRF is a few-shot novel view synthesis method that uses a manifold loss function to provide supervision for arbitrary viewpoints.

NeRF realistic synthetic 360° dataset, used for training and testing NeRF models for few-shot view synthesis.

The dataset used in the 2D-GUIDED 3D GAUSSIAN SEGMENTATION paper, which is a 3D Gaussian segmentation method guided by 2D segmentation maps.

Real-world forward-facing dataset for view synthesis, containing 1008x756 images.

A dataset for registration of real-world grapevine scans and a synthetic dataset with known ground truth registration.

A dataset for registration of real-world scenes from opposite sides with infinitesimal overlaps that cannot be accurately registered using prior methods.

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

The dataset used in the paper for training and testing the NeRF model.

NeRF LLFF dataset is a benchmark dataset for learning implicit 3D representations and addressing different tasks such as novel-view synthesis or depth-map estimation.

The dataset used in the paper is a large-scale paired dataset for training a NeRF-agnostic restorer. It consists of 8 virtual scenes, each with 400 images.

The dataset used in the paper is a large-scale paired dataset for training a NeRF-agnostic restorer. It consists of 8 different forward-facing scenes with 20-62 high-quality...

Real-S and Real-L datasets for NeRF inpainting

A dataset for generative object insertion in 3D scenes

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

A system for applying sim2real approaches to “in the wild” scenes with realistic visuals, and to policies which rely on active perception using RGB cameras.

A scene-level dataset called ScanNet-GSReg, comprising 1379 scenes obtained from the ScanNet dataset and collect an in-the-wild dataset called GSReg, comprising 6 indoor and 4...

NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis

D-NeRF: Neural Radiance Fields for Dynamic Scenes