real time face swap and one-click video deepfake with only a single image

RAGFlow is an open-source RAG (Retrieval-Augmented Generation) engine based on deep document understanding.

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

Multi-platform auto-proxy client, supporting Sing-box, X-ray, TUIC, Hysteria, Reality, Trojan, SSH etc. It’s an open-source, secure and ad-free.

[CVPR'24]🦿GoMVS: Geometrically Consistent Cost Aggregation for Multi-View Stereo

GLOMAP - Global Structured-from-Motion Revisited

LLM101n: Let's build a Storyteller

Adaptive Region Aggregation for the Multi-View Stereo Matching using Deformable Convolutional Networks

APD-MVS is a MVS method which adopts adaptive patch deformation and an NCC-based matching metric.

Invert scroll direction for physical scroll wheels while maintaining "Natural" scrolling for trackpads on MacOS

A simple face detect and alignment method, which is easy and stable.

SPIGA: Shape Preserving Facial Landmarks with Graph Attention Networks.

Numerical linear algebra course in Skoltech 2020

Main articles I read or plan to read, as well as useful links.

Finale project of Deep Learning course

Towards Unpaired Depth Enhancement and Super-Resolution in the Wild paper code

Code and files for skoltech/lenta hackaton sept.2020

High-Resolution Image Synthesis with Latent Diffusion Models

Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch

Finetune glide-text2im from openai on your own data.

Tensor Robust Principal Component Analysis via t-SVD

Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo (TPAMI 2022)