audio2photoreal
Code and dataset for photorealistic Codec Avatars driven from audio
AI summary
Avatar generation
Generating photorealistic avatars from audio
- stars
- 2.7K
- forks
- 261
- watching
- 31
Similar projects
Found by comparing what the projects do, not just their names.
Embedding space
An AI framework that combines data from multiple sources into a single embedding space, enabling various applications such as cross-modal retrieval and generation.
Character animation engine
A deep learning framework for data-driven character animation in Unity3D
Animation generator
An open-source framework for generating photorealistic animations driven by audio and reference images.
Visual feature learner
A PyTorch implementation of a self-supervised learning method for learning robust visual features without supervision.
3D data processor
A deep learning library for 3D data processing and computer vision research using PyTorch
Speaker Diarization Toolkit
A toolkit for speaker diarization using PyTorch and speech activity detection.
Video Segmentation Framework
A software framework for video segmentation in images and videos using AI models
Avatar generator
A Python implementation of a neural network architecture for image avatar body generation
Audio generator
A deep learning library for generating high-quality audio
Robotics toolkit
A platform providing pre-trained models, datasets, and tools for robotics with focus on imitation learning and reinforcement learning.
Human Pose Data
Provides pseudo-GT 3D human pose data and pre-trained models for training 3D pose estimation algorithms
nvidia/vid2vid8.6K
Video translator
A PyTorch implementation of a video-to-video translation method for generating photorealistic videos from semantic label maps or other input data.
Audio analysis library
A comprehensive Python library for feature extraction, classification, segmentation, and applications of audio data.
pytorch/audio2.6K
Audio toolkit
A PyTorch module providing tools and functions for audio signal processing
Speech generator
Generates high-quality speech from mel-spectrograms using a flow-based network architecture
