Educational framework exploring ergonomic, lightweight multi-agent orchestration. Managed by OpenAI Solution team.

Official repository of "TACO: Benchmarking Generalizable Bimanual Tool-ACtion-Object Understanding".

[ECCV 2024] Official Implementation of the paper "HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects"

InterHandGen: Two-Hand Interaction Generation via Cascaded Reverse Diffusion (CVPR 2024)

[ECCV'24] Parameterized Quasi-Physical Simulators for Dexterous Manipulations Transfer

Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba

This is the project page for paper "A Simple Baseline for Efficient Hand Mesh Reconstruction, CVPR2024"

HaMeR: Reconstructing Hands in 3D with Transformers

JointTransformer: Winner of the HANDS'2023 ARCTIC Challenge @ ICCV

Official implementation for "iTransformer: Inverted Transformers Are Effective for Time Series Forecasting" (ICLR 2024 Spotlight), https://openreview.net/forum?id=JePfAI8fah

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

A set of tools to visualize and interact with sequences of 3D data.

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

[CVPR 2024] HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields

CVPR2020. HOnnotate: A method for 3D Annotation of Hand and Object Poses

[TVCG2024] PGSR: Planar-based Gaussian Splatting for Efficient and High-Fidelity Surface Reconstruction

Code for "Cameras as Rays"

The repo for "Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image" and "Metric3Dv2: A Versatile Monocular Geometric Foundation Model..."

[NeurIPS 2024] Geometry-Aware Large Reconstruction Model for Efficient and High-Quality 3D Generation

Dynamic Gaussian Mesh: Consistent Mesh Reconstruction from Monocular Videos

GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?

GPT4V-level open-source multi-modal model based on Llama3-8B

"Neural 3D Mesh Renderer" (CVPR 2018) by H. Kato, Y. Ushiku, and T. Harada.

pytorch version of "End-to-end Recovery of Human Shape and Pose"