ActiveVisionLab / DFNetLinks
DFNet: Enhance Absolute Pose Regression with Direct Feature Matching (ECCV 2022)
☆104Updated last year
Alternatives and similar repositories for DFNet
Users that are interested in DFNet are comparing it to the libraries listed below
Sorting:
- This is official repo for ICLR 2023 Paper "DENSE RGB SLAM WITH NEURAL IMPLICIT MAPS"☆198Updated last year
- Code for paper 《Efficient Multi-view Stereo by Iterative Dynamic Cost Volume》☆62Updated last year
- Official Implementation of our CVPR 2023 paper: "DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields"☆100Updated last year
- ☆124Updated last year
- [CVPR 2023] L2G-NeRF: Local-to-Global Registration for Bundle-Adjusting Neural Radiance Fields☆251Updated last year
- [CVPR 2024 Highlight] Map-Relative Pose Regression for Visual Re-Localization☆160Updated last year
- End2End Multi-View Feature Matching with Differentiable Pose Optimization☆210Updated last year
- [CVPR 2024] GLACE: Global Local Accelerated Coordinate Encoding☆93Updated 2 months ago
- [CVPR 2023] "Revisiting Rotation Averaging: Uncertainties and Robust Losses" by Ganlin Zhang, Viktor Larsson and Daniel Barath☆122Updated last year
- ☆37Updated 3 years ago
- [CVPR 2024 - Highlight] FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation☆135Updated 2 months ago
- (ICCV 2023)"Constraining Depth Map Geometry for Multi-View Stereo: A Dual-Depth Approach with Saddle-shaped Depth Cells"☆61Updated last year
- Repository for the Robust Multi-View Depth Benchmark☆91Updated 2 years ago
- [CVPR'24]🦿GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo☆145Updated 9 months ago
- [CVPR 2023] 😈BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields☆198Updated last year
- [AAAI 2023] DarkFeat: Noise-Robust Feature Detector and Descriptor for Extremely Low-Light RAW Images☆67Updated last year
- Official code of IterMVS (CVPR 2022)☆169Updated 3 years ago
- (CVPR 2024) Neural Refinement for Absolute Pose Regression with Feature Synthesis☆31Updated 6 months ago
- APD-MVS is a MVS method which adopts adaptive patch deformation and an NCC-based matching metric.☆94Updated last year
- [CVPR 23'] GeoMVSNet: Learning Multi-View Stereo with Geometry Perception☆180Updated last year
- [CVPR'24] 3D Neural Edge Reconstruction☆184Updated 9 months ago
- [CVPR 2025 Highlight] Official implementation of the solvers and estimators proposed in the paper "Relative Pose Estimation through Affin…