[ECCV 2024] Official repository for "DataDream: Few-shot Guided Dataset Generation"

Code to accompany "A Method for Animating Children's Drawings of the Human Figure"

[ECCV 2024] Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models

Implementation of the multi-temporal UTAE for the task of satellite image time series semantic change detection (SITS-SCD)

Learning from synthetic data - code and models

This repo contains the code for our paper An Image is Worth 32 Tokens for Reconstruction and Generation

Official Pytorch implementation of NeuralWalker

(ICML 2024) PyTorch implementation of "Self-Attention through Kernel-Eigen Pair Sparse Variational Gaussian Processes"

[CVPR24] Official Implementation of 'A Video is Worth 256 Bases: Spatial-Temporal Expectation-Maximization Inversion for Zero-Shot Video Editing'

Code for Toon3D https://toon3d.studio/

Multi-level diagnosis of cataract from anterior images via deep learning

Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi Xie, Andrew Zisserman

The official Meta Llama 3 GitHub site

Historical Diagram Vectorization

[NeurIPS'23] Emergent Correspondence from Image Diffusion

[CVPR 2024] Depth-aware Test-Time Training for Zero-shot Video Object Segmentation

(CVPR 2024) Pytorch implementation of “SURE: SUrvey REcipes for building reliable and robust deep networks”

OpenDiT: An Easy, Fast and Memory-Efficient System for DiT Training and Inference

Transparent Image Layer Diffusion using Latent Transparency

Official implementation of MOST: Multiple object localization with self-supervised transformers published at ICCV 2023

[CVPR 2024] Alpha-CLIP: A CLIP Model Focusing on Wherever You Want

Focus on prompting and generating

Consistency Distilled Diff VAE

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

Approximating neural network loss landscapes in low-dimensional parameter subspaces for PyTorch

CLIP Surgery for Better Explainability with Enhancement in Open-Vocabulary Tasks