DiverGen (CVPR 2024) & BSGAL (ICML 2024)

Reserach for Person Re-ID using methods correalted with 3D or something about Multi-Modality (Multi View, Diffussion, Text-to-Image...)

Text-to-Image Vehicle Re-identification(TIVReid) or Text-based Vehicle Retrieval.

✨A curated list of papers on the uncertainty in multi-modal large language model (MLLM).

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

This repository provides the official PyTorch implementation of the paper: MaskFactory: Towards High-quality Synthetic Data Generation For Dichotomous Image Segmentation

Pytorch implementation of Learning Cross-view Geo-localization Embeddings via Dynamic Weighted Decorrelation Regularization https://arxiv.org/abs/2211.05296

[NeurIPS 2024] MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing

[ACM MM-2021] WePerson: learning a generalized re-identification model from all-weather virtual data

[AAAI 2025🚁] Game4Loc: A UAV Geo-Localization Benchmark from Game Data

AI for Science 论文解读合集（持续更新ing），论文/数据集/教程下载：hyper.ai

[CVPR 2024] Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models, a no lighting baked texture generative model

Official Implementation of Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis

对道路上的车辆进行检测和识别

Official PyTorch Code for Paper: PredFormer: Transformers Are Effective Spatial-Temporal Predictive Learners

A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks

Official code for our paper "Harnessing Uncertainty-aware Bounding Boxes for Unsupervised 3D Object Detection".

This is a seed project for distributed PyTorch training, which was built to customize your network quickly

(🛠️ *WIP*) Code snippets for understanding common techniques for virtual humans.

DreamScene: 3D Gaussian-based Text-to-3D Scene Generation via Formation Pattern Sampling

[NeurIPS2024] Cross-video Identity Correlating for Person Re-identification Pre-training

Official respository for "Towards Global Localization using Multi-Modal Object-Instance Re-Identification"

Noisy-Correspondence Learning for Text-to-Image Person Re-identification (CVPR 2024 Pytorch Code)

[RA-L] DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction

Official implementation of 'Camera-Tracklet-Aware Contrastive Learning for Unsupervised Vehicle Re-Identification'

Official repo for "Mini-Gemini: Mining the Potential of Multi-modality Vision Language Models"

[NeurIPS 2023] Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator

pytorch单精度、半精度、混合精度、单卡、多卡（DP / DDP）、FSDP、DeepSpeed模型训练代码，并对比不同方法的训练速度以及GPU内存的使用