Robust and Ultrafast Square-Root Filter-based 3D Motion Tracking

SAM 3D Objects

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…

OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer

Depth Anything 3

Meet G-CUT3R: a feed-forward model for 3D that actually uses your sensors. Unlike existing RGB-only models, it can leverage camera calibrations, poses, and depth for cleaner, more complete 3D scene…

2DGS-SLAM: Globally Consistent RGB-D SLAM with 2D Gaussian Splatting

A Comprehensive Framework for Visual SLAM Systems and Datasets

[3DV 2026] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

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

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

Collect some World Models for Autonomous Driving (and Robotic) papers.

A simple state update rule to enhance length generalization for CUT3R

Source code for [TRO2025] VINGS-Mono: Visual Inertial Gaussian Splatting Monocular SLAM in Large Scenes.

ARTDECO unifies 3D foundation priors with structured scene representations, enabling robust and generalizable 3D reconstruction of diverse real-world scenes using only monocular video.

[CoRL '25] Pseudo-Simulation for Autonomous Driving; [NeurIPS '24] NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

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

Drive-Pi0 and DriveMoE on End-to-end Autonomous Driving

VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction

SLAM-Former: Putting SLAM into One Transformer

LIV-Eye: A Low-Cost LiDAR-Inertial-Visual Fusion 3D Sensor for Robotics and Embodied AI.

Official Repo of "SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization"

This repository contains the official implementation of the research papers, "MobileCLIP" CVPR 2024 and "MobileCLIP2" TMLR August 2025