Stars
Framework for processing and filtering datasets
State-of-the-Art Text Embeddings
Official Repository for "Diffusion HPC: Generate Synthetic Data for Human Mesh Recovery in Challenging Domains" (3DV 2024 Spotlight)
Image Aesthetics Toolkit - includes Fisher Vector implementation, AVA (Image Aesthetic Visual Analysis) dataset and fast multi-threaded downloader
[ICLR 2024] Controlling Vision-Language Models for Universal Image Restoration. 5th place in the NTIRE 2024 Restore Any Image Model in the Wild Challenge.
Stable Diffusion WebUI extension for fast and easy automatic creation of detailed character art.
[3DV 2024 Oral] DeDoDe 🎶 Detect, Don't Describe --- Describe, Don't Detect, for Local Feature Matching
[NeurIPS 2023] RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions
[NeurIPS2024] PLIP: Language-Image Pre-training for Person Representation Learning
Kandinsky 2 — multilingual text2image latent diffusion model
Lightweight models for real-time semantic segmentationon PyTorch (include SQNet, LinkNet, SegNet, UNet, ENet, ERFNet, EDANet, ESPNet, ESPNetv2, LEDNet, ESNet, FSSNet, CGNet, DABNet, Fast-SCNN, Cont…
The implementation of various lightweight networks by using PyTorch. such as：MobileNetV2，MobileNeXt，GhostNet，ParNet，MobileViT、AdderNet，ShuffleNetV1-V2，LCNet，ConvNeXt，etc. ⭐⭐⭐⭐⭐
📸 PyTorch implementation of MobileNetV3 for real-time semantic segmentation, with pretrained weights & state-of-the-art performance
SOTA Semantic Segmentation Models in PyTorch
FashionCLIP is a CLIP-like model fine-tuned for the fashion domain.
Milvus is a high-performance, cloud-native vector database built for scalable vector ANN search
Efficient Deep Learning Systems course materials (HSE, YSDA)
Semi Supervised Learning for Medical Image Segmentation, a collection of literature reviews and code implementations.
Prototype-based Incremental Few-Shot Semantic Segmentation
TinyNeuralNetwork is an efficient and easy-to-use deep learning model compression framework.
🔥🔥🔥🔥 (Earlier YOLOv7 not official one) YOLO with Transformers and Instance Segmentation, with TensorRT acceleration! 🔥🔥🔥
High-efficiency floating-point neural network inference operators for mobile, server, and Web
A latent text-to-image diffusion model
Generate images from texts. In Russian
Implementation of NÜWA, state of the art attention network for text to video synthesis, in Pytorch
Implementation of DALL-E 2, OpenAI's updated text-to-image synthesis neural network, in Pytorch
[ICCV 2021]: IIVI: Internal Video Inpainting by Implicit Long-range Propagation
GLIDE: a diffusion-based text-conditional image synthesis model