nianticspatial/scr-priors
[ICCV 2025] Scene Coordinate Reconstruction Priors
This project helps specialists in 3D scanning, augmented reality, or robotics improve the accuracy of how their systems understand and map real-world environments. It takes existing 3D scene data (like RGB-D images or point clouds) and enhances the reconstruction of scene coordinates, producing more precise 3D models and better camera pose estimation. This tool is for researchers, engineers, or developers working on spatial computing applications who need highly accurate environmental mapping.
Use this if you need to achieve state-of-the-art accuracy in 3D scene coordinate reconstruction and camera relocalization for indoor environments.
Not ideal if you are looking for a simple, out-of-the-box solution for casual 3D scanning or if your primary need is for outdoor or large-scale mapping without fine-grained prior integration.
Stars
23
Forks
2
Language
Shell
License
—
Category
Last pushed
Nov 10, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/nianticspatial/scr-priors"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.