APRIL-AIGC

ADer. [ICCV ADFM'25] ADer is an open source visual anomaly detection toolbox based on PyTorch, which supports multiple popular AD datasets and approaches.

EMO. [ICCV 2023] Official PyTorch implementation of "Rethinking Mobile Block for Efficient Attention-based Models"

FReeNet. FReeNet: Multi-Identity Face Reenactment, CVPR'20

awesome-face-generation. Basic GAN frameworks and approaches for face swap, reenactment, and stylizing.

APB2FaceV2. An improved version of APB2Face: Real-Time Audio-Guided Multi-Face Reenactment

DTVNet. DTVNet: Dynamic Time-lapse Video Generation via Single Still Image, ECCV'20 Spotlight.

APB2Face. Official pytorch implementation for "APB2Face: Audio-guided face reenactment with auxiliary pose and blink signals", ICASSP'20

Soul. [CVPR 2026] Soul: Breathe Life into Digital Human for High-fidelity Long-term Multimodal Animation

EMOv2. [T-PAMI 2025] EMOv2: Pushing 5M Vision Model Frontier

OCR-GAN. [TIP 2023] Omni-frequency Channel-selection Representations for Unsupervised Anomaly Detection

T3-Video. [ICML 2026] Transform Trained Transformer for Accelerating Native 4K Video Generation

EATFormer. EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm

GPT-4V-AD. Code for "Exploring Grounding Potential of VQA-oriented GPT-4V for Zero-shot Anomaly Detection"

trackingImgLabel. TrackingImgLabel is an automatic graphical image annotation tool with a video as input, which uses tracking algorithm to track the object. You can only label the first frame of the video, then the tracking algorithm will automaticlly tracking the objects.

zhangzjn. Profile of vtzhang