Splatt3r
Visit ToolSplatt3R is a computer vision tool that predicts 3D Gaussians from uncalibrated image pairs. It is a feed-forward model enabling zero-shot Gaussian splatting.
At a glance
Trending
Also listed in
Splatt3R is a computer vision tool that predicts 3D Gaussians from uncalibrated image pairs. It is a feed-forward model enabling zero-shot Gaussian splatting.
Trending
Also listed in
About
Splatt3R is the official implementation of a research project focused on zero-shot Gaussian Splatting from uncalibrated image pairs. This feed-forward model is designed to directly predict 3D Gaussians from standard images, eliminating the need for complex calibration processes. It is particularly useful for computer vision and 3D graphics applications where rapid 3D scene reconstruction from minimal input is critical. The tool provides an initial codebase, a research paper, a project webpage, and a Gradio demo for easy experimentation. Users can set up an Anaconda environment, compile CUDA kernels, and utilize pretrained models and data from ScanNet++ to train their own models or generate 3D scene representations.
Capabilities
Pricing & Plans
Open Source
Free
FAQs
Trending