AI Agent Skills

Laser Odometry and Mapping (Loam) is a realtime method for state estimation and mapping using a 3D lidar.

SOTA fast and robust ground segmentation using 3D point cloud (accepted in RA-L'21 w/ IROS'21)

The first 6-DoF spline-based recursive motion esimator for LiDAR-based odometry

Mobile Robot Localization in 3D Triangle Meshes & Geometric Scene Graphs

UMI-3D SLAM and Data Processing Pipeline: https://umi-3d.github.io/

Xtreme1 is an all-in-one data labeling and annotation platform for multimodal data training and supports 3D LiDAR point cloud, image, and LLM.

3D Computer Vision Framework

A flexible, high-performance 3D simulator for Embodied AI research.

Objectron is a dataset of short, object-centric video clips. In addition, the videos also contain AR session metadata including camera poses, sparse point-clouds and pla…

:man: Code for "Large Pose 3D Face Reconstruction from a Single Image via Direct Volumetric CNN Regression"

[ECCV 2022] This is the official implementation of BEVFormer, a camera-only framework for autonomous driving perception, e.g., 3D object detection and semantic map segme…

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

3D ResNets for Action Recognition (CVPR 2018)

The PyTorch improved version of TPAMI 2017 paper: Face Alignment in Full Pose Range: A 3D Total Solution.

The official PyTorch implementation of Towards Fast, Accurate and Stable 3D Dense Face Alignment, ECCV 2020.

SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)