Official PyTorch implementation of the paper "Chapter-Llama: Efficient Chaptering in Hour-Long Videos with LLMs"

Code for "Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation"

Reliability in Semantic Segmentation: Can We Use Synthetic Data? (ECCV 2024)

Implementation of "Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation" from CVPR Workshop on Human Motion Generation 2024.

High order Moment Models

[CVPR 2024] PyTorch implementation of GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

[ICCV 2023 R6D] PyTorch implementation of CNOS: A Strong Baseline for CAD-based Novel Object Segmentation based on Segmenting Anything and DINOv2

Official PyTorch implementation of the paper "CoVR: Learning Composed Video Retrieval from Web Video Captions".

[NeurIPS 2023] Code for "Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives"

Unify text-motion datasets (like BABEL, HumanML3D, KIT-ML) into a common motion-text representation.

Official PyTorch implementation of the paper "TMR: Text-to-Motion Retrieval Using Contrastive 3D Human Motion Synthesis" ICCV 2023

Official PyTorch implementation of the paper "SINC: Spatial Composition of 3D Human Motions for Simultaneous Action Generation" [ICCV 2023]

Toolbox for the Earth Parser Dataset, a dataset presented in the "Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans" paper

Official Pytorch implementation of the "Learnable Earth Parser: Discovering 3D Prototypes in Aerial Scans" paper

(IGARSS 2025) Prototype-based method for agricultural image time series classification.

A playbook for systematically maximizing the performance of deep learning models.

The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Estimation"

Code for "MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare", CoRL 2022.

A curated list of awesome System Design (A.K.A. Distributed Systems) resources.

Hackable and optimized Transformers building blocks, supporting a composable construction.

The official PyTorch implementation of the paper "Human Motion Diffusion Model"

Official repository of Human3.6M 3D WholeBody (H3WB) dataset

[3DV 2022 (Oral)] Pytorch implementation of "PIZZA: A Powerful Image-only Zero-Shot Zero-CAD Approach to 6 DoF Tracking" paper

utility functions for CIL

Feature Translation for Exemplar-Free Class-Incremental Learning

Code for SCAM! Transferring humans between images with Semantic Cross Attention Modulation. Also contains implementation for SPADE, CLADE, SEAN and INADE

GUI for visualization and interactive editing of SMPL-family body models ie. SMPL, SMPL-X, MANO, FLAME.

Robust Speech Recognition via Large-Scale Weak Supervision