Official PyTorch Implementation of "Diffusion Autoencoders are Scalable Image Tokenizers"

[CVPR 2024] Code release for TransNeXt model

This repo contains the code for 1D tokenizer and generator

TextGrad: Automatic ''Differentiation'' via Text -- using large language models to backpropagate textual gradients.

MambaOut: Do We Really Need Mamba for Vision? (CVPR 2025)

[ICLR2024] The official implementation of paper "VDT: General-purpose Video Diffusion Transformers via Mask Modeling", by Haoyu Lu, Guoxing Yang, Nanyi Fei, Yuqi Huo, Zhiwu Lu, Ping Luo, Mingyu Ding.

Beyond the Imitation Game collaborative benchmark for measuring and extrapolating the capabilities of language models

Open reproduction of MUSE for fast text2image generation.

Open-vocabulary Semantic Segmentation

This is an official implementation of our CVPR 2023 paper "Human Pose as Compositional Tokens" (https://arxiv.org/pdf/2303.11638.pdf)

text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)

Code release for "Omni3D A Large Benchmark and Model for 3D Object Detection in the Wild"

This is an official implementation for "SimMIM: A Simple Framework for Masked Image Modeling".

Semi-Supervised Learning, Object Detection, ICCV2021

EsViT: Efficient self-supervised Vision Transformers

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Object Detection and Instance Segmentation.

This is an official implementation for "Swin Transformer: Hierarchical Vision Transformer using Shifted Windows" on Semantic Segmentation.

This is an official implementation for "Self-Supervised Learning with Swin Transformers".

Group-Free 3D Object Detection via Transformers

Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation, ECCV 2020 Oral

在我们开发项目的时候，无论项目规模大小，在所难免会写一些工具型函数来解决一些问题，随着项目开发和维护的时间越来越长，这些工具型函数会越来越多，同时还会穿插在各个项目的各模块或者文件当中，使得项目变的越来越臃肿，也不方便复用和维护。这时我们就会提取出一个类似的工具库或者基础库作为项目基础依赖，在项目中重复利用起来。 为了这样的工具库或类库更易扩展、易维护、易复用和更加稳定，我们就需要更好的去管…

Parallel Faster R-CNN implementation with MXNet.