ujemd
Follow
Stars
"Effective Whole-body Pose Estimation with Two-stages Distillation" (ICCV 2023, CV4Metaverse Workshop)
Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"
Notebook that explains self-supervised learning with exercises
A motion generation model learned from a single example [SIGGRAPH 2022]
ZeroEGGS: Zero-Shot Example-Based Gesture Generation from Speech
This is an implementation of Robots learn social skills: End-to-end learning of co-speech gesture generation for humanoid robots.
Robot kinematics implemented in pytorch
[ICCV 2021] The official repo for the paper "Speech Drives Templates: Co-Speech Gesture Synthesis with Learned Templates".
Expressive Body Capture: 3D Hands, Face, and Body from a Single Image
[SIGGRAPH 2022 Journal Track] AvatarCLIP: Zero-Shot Text-Driven Generation and Animation of 3D Avatars
A pre-trained YOLO based hand detection network.
Official implementation of Diffusion Autoencoders
Official project website for the CVPR 2020 paper (Oral Presentation) "Cascaded deep monocular 3D human pose estimation wth evolutionary training data"
RaveForce - An OpenAI Gym style toolkit for music generation experiments.
Code for ACCV 2020 "Speech2Video Synthesis with 3D Skeleton Regularization and Expressive Body Poses"
An end-to-end library for editing and rendering motion of 3D characters with deep learning [SIGGRAPH 2020]
official implementation of CVPR'20 oral paper: Generating 3D People in Scenes without People.: https://ps.is.tuebingen.mpg.de/publications/smpl-x-conditional-vae-prox-scene-constraints
Real-time face swap for PC streaming or video calls
FFCV: Fast Forward Computer Vision (and other ML workloads!)
Extracts human motion in video and save it as bvh mocap file.
Freeform Body Motion Generation from Speech
Official repository of OFA (ICML 2022). Paper: OFA: Unifying Architectures, Tasks, and Modalities Through a Simple Sequence-to-Sequence Learning Framework
Structured state space sequence models