ActiveVisionLab/NeFeS
(CVPR 2024) Neural Refinement for Absolute Pose Regression with Feature Synthesis
This project helps robotics engineers and computer vision researchers precisely determine a camera's position and orientation (its "pose") within a known environment. It takes existing pose estimations from images and refines them to be more accurate by synthesizing new visual features. Users would typically be working on tasks requiring highly precise camera localization, such as augmented reality, robot navigation, or 3D scene reconstruction.
No commits in the last 6 months.
Use this if you need to significantly improve the accuracy of absolute camera pose estimations in static scenes, going beyond what traditional methods can achieve.
Not ideal if your application involves dynamic scenes with moving objects or if you require real-time pose estimation on highly resource-constrained devices without dedicated GPUs.
Stars
33
Forks
1
Language
Python
License
MIT
Category
Last pushed
Dec 24, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/ActiveVisionLab/NeFeS"
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.