cvg

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

Visual localization made easy with hloc

[CVPR'22] NICE-SLAM: Neural Implicit Scalable Encoding for SLAM

Pixel-Perfect Structure-from-Motion with Featuremetric Refinement (ICCV 2021, Best Student Paper Award)

[CVPR'25] DepthSplat: Connecting Gaussian Splatting and Depth

Training library for local feature detection and matching

[ICLR'25 Oral] No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images

GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

A toolbox for 3D visual mapping, localization, and SfM with structured geometric features (points, lines, planes, vanishing points, wireframes, etc.).

Back to the Feature: Learning Robust Camera Localization from Pixels to Pose (CVPR 2021)

Joint Deep Matcher for Points and Lines 🖼️💥🖼️ (ICCV 2023)

Implementation of the paper "DeepLSD: Line Segment Detection and Refinement with Deep Image Gradients"

Joint deep network for feature line detection and description

MP-SfM: Monocular Surface Priors for Robust Structure-from-Motion (CVPR 2025)

VidMap: Exploiting Temporal Structure for Video-Based Structure-from-Motion (ECCV 2026)

[ECCV'26 Spotlight] ReSplat: Learning Recurrent Gaussian Splatting

Factor graphs with Ceres in Python

Making Structure-from-Motion (COLMAP) more robust to symmetries and duplicated structures

FlexGlue: Sparse-to-Dense Feature Matching and Visual Disambiguation

Ranking and Covariances for Practical Learned Keypoints

[ICLR'26] YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting

ZipSplat: Fewer Gaussians, Better Splats

[3DV'24 Best Paper Honorable Mention] NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM

ETH-Microsoft dataset for the ICCV 2021 visual localization challenge

[CVPR'24] 3D Neural Edge Reconstruction

[CVPR'24] NeRF On-the-go: Exploiting Uncertainty for Distractor-free NeRFs in the Wild

Benchmarking Visual-Inertial SLAM at City Scale (ICCV 2025).

[RA-L 2025] FrontierNet: Learning Visual Cues to Explore

[T-PAMI 2025] DiffMVS & CasDiffMVS

MegaFlow: Zero-Shot Large Displacement Optical Flow

[CVPR 2025] A unified framework for Scene Coordinate Regression-based visual localization

[ICCV'25] 3D-MOOD: Lifting 2D to 3D for Monocular Open-Set Object Detection

[ECCV'26] VIGS-SLAM: Visual Inertial Gaussian Splatting SLAM

Vanishing Point Estimation in Uncalibrated Images with Prior Gravity Direction (ICCV 2023)

[CVPR 2024] GLACE: Global Local Accelerated Coordinate Encoding

[RSS 2026] OpenFrontier: General Navigation with Visual-Language Grounded Frontiers

[CoRL 2025] ActLoc: Learning to Localize on the Move via Active Viewpoint Selection

[ECCV'26] Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs

A repository for PIXHAWK open source code running on ROS