PhD Student at CVL LiU.
RoMa. [CVPR 2024] RoMa: Robust Dense Feature Matching; RoMa is the robust dense feature matcher capable of estimating pixel-dense warps and reliable certainties for almost any image pair.
1.3kDeDoDe. [3DV 2024 Oral] DeDoDe 🎶 Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching
491DKM. [CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation
482dad. DaD's a pretty good keypoint detector, probably the best.
103micro-bundle-adjustment. A minimal PyTorch implementation of Bundle Adjustment
100simfitpp. Python
20torchlm. Levenberg-Marquardt optimizer in pytorch
8PoseLib. Minimal solvers for calibrated camera pose estimation
7ACMMP. Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo (TPAMI 2022)
7fused-local-corr. Python
7triangulation. Python
6is-this-harmful. Python
4robust_self_calibration. Python
3slurm_util. Python
3gaussian_surfels. Implementation of the SIGGRAPH 2024 conference paper "High-quality Surface Reconstruction using Gaussian Surfels".
3glue-factory. Training library for local feature detection and matching
2nerfbaselines. Reproducible evaluation of NeRF and 3DGS methods
2python_example. Example pybind11 module built with a Python-based build system
2easy_gravity. Python
2cmake_example. Example pybind11 module built with a CMake-based build system
2accelerated_features. Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!
2pycolmap. Python bindings for COLMAP
2denoising-diffusion-pytorch. Implementation of Denoising Diffusion Probabilistic Model in Pytorch
2silk-mega1500-eval. Related to https://github.com/facebookresearch/silk/issues/27
1dust3r. DUSt3R: Geometric 3D Vision Made Easy
1wasp_SE_course. Resources and student assignments for the WASP Software Engineering course
1silk. SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.
1Semi-supervised-learning. A Unified Semi-Supervised Learning Codebase (NeurIPS'22)
1Murre. Code for "Multi-view Reconstruction via SfM-guided Monocular Depth Estimation". CVPR 2025 (Oral Presentation)
1LightGlue_. LightGlue: Local Feature Matching at Light Speed (ICCV 2023)
1OpenEXR-Python. Repos for OpenEXR-Python
1kornia. Geometric Computer Vision Library for Spatial AI
1Pointnet2.PyTorch. A faster implementation of PointNet++ based on PyTorch.
1MVSFormerPlusPlus. Codes of MVSFormer++: Revealing the Devil in Transformer’s Details for Multi-View Stereo (ICLR2024)
1bitsandbytes. 8-bit CUDA functions for PyTorch
1FACT_for_PCMC. [SCIA 2025] FACT: Multinomial Misalignment Classification for Point Cloud Registration
1colmap. COLMAP - Structure-from-Motion and Multi-View Stereo
1croco. Python
1gaussian-opacity-fields. Gaussian Opacity Fields for Efficient and Compact Surface Reconstruction in Unbounded Scenes
1NeuS2. Test fork, don't read
1vision. Datasets, Transforms and Models specific to Computer Vision
1AdaMatcher. Code for CVPR2023 paper:Adaptive Assignment for Geometry Aware Local Feature Matching
1map-free-reloc. [ECCV 2022] Map-free Visual Relocalization: Metric Pose Relative to a Single Image
1neuralangelo. Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)
1gsplat. CUDA accelerated rasterization of gaussian splatting
1rotation-steerers. A steerer for D-dimensional keypoint descriptions is a DxD matrix that transforms the descriptions as if they were computed from a rotated image.
1Hierarchical-Localization. Visual localization made easy with hloc
1deq. [NeurIPS'19] Deep Equilibrium Models
1tensor_ops. Python
1LoFTR. Code for "LoFTR: Detector-Free Local Feature Matching with Transformers", CVPR 2021
1