Computer Vision and Geometry Lab ORG

Visual localization made easy with hloc

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

A toolbox for mapping and localization with line features.

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

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

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

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

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

Training library for local feature detection and matching

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

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)

Factor graphs with Ceres in Python

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

ReSplat: Learning Recurrent Gaussian Splatting

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

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

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

[T-PAMI 2025] DiffMVS & CasDiffMVS

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

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

MegaFlow: Zero-Shot Large Displacement Optical Flow

ZipSplat: Fewer Gaussians, Better Splats

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

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

No description.

[CVPR 2024] GLACE: Global Local Accelerated Coordinate Encoding

Ranking and Covariances for Practical Learned Keypoints

Mask3D predicts accurate 3D semantic instances achieving state-of-the-art on ScanNet, ScanNet200, S3DIS and STPLS3D.

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

A repository for PIXHAWK open source code running on ROS

Point cloud meshing with CGAL

Fast CPU rendering in Python using the Intel® Embree backend

CroCoDL (CVPR 2025) fork containing the additions on top of LaMAR (ECCV 2022)

No description.

No description.

No description.

No description.

Modular framework for online informative path planning.

A Unified Framework for Surface Reconstruction

No description.

time delay single and multi sensor fusion framework based on an EKF

ROS2 driver package for boston dynamic's spot

Packaged version of Grounded-SAM to be used in LabelMaker

This is a build code for building open3d wheels on manylinux 2014 docker, so that ETHz's Euler (CentOS 7) can run it.

Framework for data aquisition and position control to be used with the highlevel processor of Ascending Technologies helicopters

No description.

No description.

No description.

Packaged version of Recognize Anything to be used in LabelMaker

Code for "OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models" NeurIPS 2022

cvg development fork of maplab (to be able to create pull requests)

Custom ROS messages for maplab