AI Agent Skills

[ICCV 2023] Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior

Segment-Anything + 3D. Let's lift anything to 3D.

Segment Anything in 3D with NeRFs (NeurIPS 2023 & IJCV 2025)

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

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.

A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.

Algorithms and Publications on 3D Object Tracking

Real-time 3D full-body reconstruction from a single camera, Multiperson BVH output, Pure C++ runtime, ONNX + ggml, 70-joint skeleton with hands.

An open survey on 3D Gaussian Splatting compression methods

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…