cvg/scrstudio
[CVPR 2025] A unified framework for Scene Coordinate Regression-based visual localization
When navigating or precisely positioning robots or augmented reality devices, knowing the exact location and orientation of a camera within a 3D environment is crucial. This framework takes images and their rough pose estimates as input and outputs highly accurate 3D scene coordinates for each pixel, which helps determine the camera's precise position. Robotics engineers, augmented reality developers, and anyone building autonomous navigation systems would use this to improve localization accuracy.
133 stars. No commits in the last 6 months.
Use this if you need to precisely determine a camera's position and orientation in a complex 3D environment, improving upon traditional visual localization methods.
Not ideal if you are looking for a simple, out-of-the-box solution without diving into model training and data preprocessing steps, or if your application doesn't require high-precision visual localization.
Stars
133
Forks
2
Language
Python
License
Apache-2.0
Category
Last pushed
Jun 26, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/cvg/scrstudio"
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.