InternVL-U is a 4B-parameter unified multimodal model (UMM) that brings multimodal understanding, reasoning, image generation, image editing into a single framework.

MXNet implementation of SEC

Nitro-T is a family of text-to-image diffusion models focused on highly efficient training.

This repo provides a working re-implementation of Latent Adversarial Diffusion Distillation by AMD

A PyTorch implementation of the paper "All are Worth Words: A ViT Backbone for Diffusion Models".

PyTorch implementation of MAR+DiffLoss https://arxiv.org/abs/2406.11838

Visualization of DiT self attention features

A 3DMM fitting framework using Pytorch.

Crack LeetCode, not only how, but also why.

A Python implementation of the paper "Deformation Transfer for Triangle Meshes" with 3D views in the browser.

Reproduction of the paper "Deformation Transfer for Triangle Meshes" of Robert W.Sumner et al.

Virtural try-on under arbitrary poses

Look-into-Object: Self-supervised Structure Modeling for Object Recognition (CVPR 2020)

Daquexian's NNAPI Library. ONNX + Android NNAPI

dabnn is an accelerated binary neural networks inference framework for mobile platform

On the Consistency for E-commerce Product Summarization

CM-NAS: Cross-Modality Neural Architecture Search for Visible-Infrared Person Re-Identification (ICCV2021)

A PyTorch Toolbox for Face Recognition

Implementation of ‘Pose-Guided Tracking-by-Detection: Robust Multi-Person Pose Tracking’ [TMM 2020]

Monocular, One-stage, Regression of Multiple 3D People and their 3D positions & trajectories in camera & global coordinates. ROMP[ICCV21], BEV[CVPR22], TRACE[CVPR2023]

code for ICCV2021 paper: Neural Architecture Search for Joint Human Parsing and Pose Estimation

Cleaned test data list of DukeMTMC-reID, ICCV2021

Semi-supervised Knowledge Distillation

SOTA Re-identification Methods and Toolbox

This repo is implemented based on detectron2 and centernet

ACM MM 2020 Oral