ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

[NeurIPS'25] Official repository of Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

Learning to Filter Outlier Edges in Global SfM.

Code for our paper: Learning Camera Movement Control from Real-World Drone Videos

Learning to Solve Hard Minimal Problems

A repository for paper "Efficient Solution of Point-Line Absolute Pose" by P.Hruby, T.Duff, and M. Pollefeys, presented at CVPR 2024.

[NeurIPS 2025 D&B] Open-source Multi-agent Poster Generation from Papers

Ray tracing and hybrid rasterization of Gaussian particles

SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single Images

SfM for sphere images in the ERP format within the framework of ColMap

[CVPR 2025 Highlight] Matrix3D: Large Photogrammetry Model All-in-One

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

[Official Implementation] Improving Editability in Image Generation with Layer-wise Memory, CVPR 2025

[Official Implementation] Subject-driven Video Generation via Disentangled Identity and Motion

Upload 360° photos to Google Maps without using Google's app

[NeurIPS 2025] SpatialLM: Training Large Language Models for Structured Indoor Modeling

Python scripts and functions to work with COLMAP

This code is for align lidar points with COLMAP sparse point cloud. The code is an official implementation of GauUScene.

Some information about parameters and options available in COLMAP - SfM & MVS software. https://colmap.github.io

PE3R: Perception-Efficient 3D Reconstruction. Take 2 - 3 photos with your phone, upload them, wait a few minutes, and then start exploring your 3D world via text!

[CVPR 2024 Highlight] Map-Relative Pose Regression for Visual Re-Localization

Ultra fast 3D reconstruction and novel view synthesis.

Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task

[CVPR 2022] Official PyTorch implementation of "Official Self-Supervised Equivariant Learning for Oriented Keypoint Detection"

[CVPR 2025] MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)