Parskatt

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.

DKM

[CVPR 2023] DKM: Dense Kernelized Feature Matching for Geometry Estimation

DeDoDe

[3DV 2024 Oral] DeDoDe 🎶 Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching

micro-bundle-adjustment

A minimal PyTorch implementation of Bundle Adjustment

PoseLib

Minimal solvers for calibrated camera pose estimation

ACMMP

Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo (TPAMI 2022)

denoising-diffusion-pytorch

Implementation of Denoising Diffusion Probabilistic Model in Pytorch

dust3r

DUSt3R: Geometric 3D Vision Made Easy

gaussian_surfels

Implementation of the SIGGRAPH 2024 conference paper "High-quality Surface Reconstruction using Gaussian Surfels".

pycolmap

Python bindings for COLMAP

rotation-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.

accelerated_features

Implementation of XFeat (CVPR 2024). Do you need robust and fast local feature extraction? You are in the right place!

AdaMatcher

Code for CVPR2023 paper:Adaptive Assignment for Geometry Aware Local Feature Matching

cmake_example

Example pybind11 module built with a CMake-based build system

colmap

COLMAP - Structure-from-Motion and Multi-View Stereo

croco

gaussian-opacity-fields

Gaussian Opacity Fields for Efficient and Compact Surface Reconstruction in Unbounded Scenes

Hierarchical-Localization

Visual localization made easy with hloc

kornia

Geometric Computer Vision Library for Spatial AI

map-free-reloc

[ECCV 2022] Map-free Visual Relocalization: Metric Pose Relative to a Single Image

neuralangelo

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

NeuS2

Test fork, don't read

personal-website

Pointnet2.PyTorch

A faster implementation of PointNet++ based on PyTorch.

python_example

Example pybind11 module built with a Python-based build system

silk

SiLK (Simple Learned Keypoint) is a self-supervised deep learning keypoint model.

silk-mega1500-eval

Related to https://github.com/facebookresearch/silk/issues/27

storage

vision

Datasets, Transforms and Models specific to Computer Vision

wasp_SE_course

Resources and student assignments for the WASP Software Engineering course