[ECCV 2026 Oral] LoMa: Local Feature Matching Revisited

A feed-forward 3D foundation model for reconstructing scenes from streaming data

A curated list of papers, projects, code, and datasets for 4D Gaussian Splatting

Official Implementation of SIGGRAPH'26 paper "Immediate 3D Gaussian Splat Reconstruction of Unordered Input with Global Consistency"

✨ An advanced 3D Gaussian Splatting renderer for THREE.js

Modular set of functions for SGP4 and SDP4 propagation of TLE and OMM.

Official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction

Official implementation of R^3: 3D Reconstruction via Relative Regression.

[CVPR'25 Oral] MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision

Reimplementation of LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory

A Three.js-based framework written in Javascript/WebGL for visualizing 3D geospatial data

[CVPR 2026] Multi-view Pyramid Transformer: Look Coarser to See Broader

Addon to import different photogrammetry formats into Blender

Integrating Feed-Forward Visual Model with IMU, GNSS for High-Functionality SLAM.

Code repo for the SIGGRAPH paper "Monocular Online Reconstruction with Enhanced Detail Preservation". Project page https//poiw.github.io/MODP/index.html

[CVPR 2025] WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments

The repository provides code for running inference with the SAM 3D Body Model (3DB), links for downloading the trained model checkpoints and datasets, and example notebooks that show how to use the…

Depth Anything 3

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

Dataset and Code for CVSports at CVPR 2025 paper "AthletePose3D: A Benchmark Dataset for 3D Human Pose Estimation and Kinematic Validation in Athletic Movements"

PromptHMR: Promptable Human Mesh Recovery

Official Pytorch Implementation for the paper FastAvatar ..

ViPE: Video Pose Engine for Geometric 3D Perception

[NeurIPS 2025] Official code for Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos

[CVPR 2025 Highlight] Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

[ICCV 2025] SpatialTrackerV2: 3D Point Tracking Made Easy

UFM: A Unified Dense Image Correspondence Estimator for both Optical Flow & Wide Baseline Matching Tasks. Matches any pair of images. (NeurIPS 2025)