bravotty

stDiff

A novel method named stDiff investigates the potential of employing diffusion models for single-cell omics generation.

guided-diffusion

scDiffusion

A model developed for the generation of scRNA-seq data

scGPT

PIDM

Person Image Synthesis via Denoising Diffusion Model (CVPR 2023)

MHFAN

Cell localization and counting: 1) Exponential Distance Transform Maps for Cell Localization; 2) Multi-scale Hypergraph-based Feature Alignment Network for Cell Localization; 3) Lite-UNet: A lightweight and efficient network for cell localization

DoDNet

[CVPR2021] DoDNet: Learning to segment multi-organ and tumors from multiple partially labeled datasets

Open-Sora

Open-Sora: Democratizing Efficient Video Production for All

Multimodal-intersection-analysis-MIA-

Source code for MIA from Moncada et al Nature Biotechnology (2020)

SpatialDE

Test genes for Spatial Variation

scIGANs

Generative adversarial networks for single-cell RNA-seq imputation

scMoFormer

Single-Cell Multimodal Prediction via Transformer

modelscope

ModelScope: bring the notion of Model-as-a-Service to life.

pv3d

SPFlowNet

[CVPR 2023] Self-Supervised 3D Scene Flow Estimation Guided by Superpoints

Surface-Defect-Detection

📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

CoDeF

[CVPR 2024 Highlight] Official PyTorch implementation of CoDeF: Content Deformation Fields for Temporally Consistent Video Processing

Cones-V2

ScutThesis

华南理工大学博士学位论文Latex模板（修改自ThuThesis https://github.com/tuna/thuthesis）

NoisyTwins

[CVPR 2023] Source code for NoisyTwins: Class-consistent and Diverse Image Generation Through StyleGANs

learning_research

本人的科研经验

LightGlue

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

CLIP-PAE

Projection-augmentation embedding for CLIP-based latent manipulation methods

dynibar

Implementation of DynIBaR Neural Dynamic Image-Based Rendering (CVPR 2023)

CNeRF

Pytorch implementation of AAAI2023 Oral paper "Semantic 3D-aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field"

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

Inpaint-Anything

Inpaint anything using Segment Anything and inpainting models.

pytorch_morphological_dilation2d_erosion2d

An implementation for image (tensor) morphological dilation2d and erosion2d in pytorch

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

ivid

PyTorch implementation of the ICCV paper "3D-aware Image Generation using 2D Diffusion Models"