AI Agent Skills

Official implementation of the CVPR 2022 Paper "Neural RGB-D Surface Reconstruction"

Dense 3D reconstruction from stereo (using LIBELAS)

Official implementation of "Neuralangelo: High-Fidelity Neural Surface Reconstruction" (CVPR 2023)

NVIDIA-accelerated 3D scene reconstruction and Nav2 local costmap provider using nvblox

[CVPR 2023 Highlight] Neural Kernel Surface Reconstruction

[Siggraph Asia 2013] Large-Scale, Real-Time 3D Reconstruction

Code for "Neural 3D Scene Reconstruction with the Manhattan-world Assumption" CVPR 2022 Oral

[CVPR'24, Demo Track Honourable Mention] SuperPrimitive: Scene Reconstruction at a Primitive Level

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

An open-source impl. of Large Reconstruction Models

Codex skill for 750px image-to-code reconstruction and transparent PNG slicing

Real-time 3D face tracking and reconstruction from 2D video

A pipeline for online 3D reconstruction of objects only using visual data from RGB-D camera (Kinect V2).

Implementation of TiTok, proposed by Bytedance in "An Image is Worth 32 Tokens for Reconstruction and Generation"

MonoNav: MAV Navigation via Monocular Depth Estimation and Reconstruction