✨✨Latest Advances on Multimodal Large Language Models

A visual editor for manually annotating facial landmarks in images of human faces.

🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022

📖 A curated list of resources dedicated to talking face.

TRACER: Extreme Attention Guided Salient Object Tracing Network (AAAI 2022) implementation in PyTorch

A collection of datasets for the purpose of emotion recognition/detection in speech.

Code for Cross-Modality and Within-Modality Regularization for Audio-Visual DeepFake Detection

Foundational Models for State-of-the-Art Speech and Text Translation

Image Polygonal Annotation with Python (polygon, rectangle, circle, line, point and image-level flag annotation).

关键点标注工具 | Landmark-Annotation

Labeling tool with SAM(segment anything model),supports SAM, SAM2, sam-hq, MobileSAM EdgeSAM etc.交互式半自动图像标注工具

Download and preprocess voxceleb datasets.

[CVPR 2023] SadTalker：Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation

Code for UniS-MMC: Multimodal Classification via Unimodality-supervised Multimodal Contrastive Learning (ACL 2023)

A self-supervised learning framework for audio-visual speech

Pytorch implementation of paper "One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing"

iCartoonFace dataset, and baseline approaches, the project is supported by iQIYI

The source code for paper "Landmark Detection and 3D Face Reconstruction for Caricature using a Nonlinear Parametric Model".

Papers, repository and other data about anime or manga research. Please let me know if you have information that the list does not include.

Official implementation of "AnimeCeleb: Large-Scale Animation CelebHeads Dataset for Head Reenactment" (ECCV 2022)

GeneFace: Generalized and High-Fidelity 3D Talking Face Synthesis; ICLR 2023; Official code

An unofficial inversion code of eg3d.

[CVPR 2023] 3D-Aware Face Swapping

[CVPR 2023 Highlight] Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars

Code Repository for CVPR 2023 Paper "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360 degree"

用于从头预训练+SFT一个小参数量的中文LLaMa2的仓库；24G单卡即可运行得到一个具备简单中文问答能力的chat-llama2.

[arXiv22] Disentangled Representation Learning for Text-Video Retrieval