CV计算机视觉每日开源代码Paper with code速览-2023.11.29

点击@CV计算机视觉，关注更多CV干货

1.【基础网络架构】Adapter is All You Need for Tuning Visual Tasks

论文地址：https://arxiv.org//pdf/2311.15010
开源代码：GitHub - Leiyi-Hu/mona: The official implementation of "Adapter is All You Need for Tuning Visual Tasks".

2.【基础网络架构：Transformer】Advancing Vision Transformers with Group-Mix Attention

论文地址：https://arxiv.org//pdf/2311.15157
开源代码：GitHub - AILab-CVC/GroupMixFormer: GroupMixAttention and GroupMixFormer

扫描二维码关注公众号，回复： 17319914 查看本文章

3.【基础网络架构：CNN】UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition

4.【图像分类】SpliceMix: A Cross-scale and Semantic Blending Augmentation Strategy for Multi-label Image Classification

论文地址：https://arxiv.org//pdf/2311.15200
开源代码：GitHub - zuiran/SpliceMix

5.【旋转目标检测】Point2RBox: Combine Knowledge from Synthetic Visual Patterns for End-to-end Oriented Object Detection with Single Point Supervision

论文地址：https://arxiv.org//pdf/2311.14758
开源代码（即将开源）：GitHub - open-mmlab/mmrotate: OpenMMLab Rotated Object Detection Toolbox and Benchmark

6.【旋转目标检测】PointOBB: Learning Oriented Object Detection via Single Point Supervision

论文地址：https://arxiv.org//pdf/2311.14757
开源代码：GitHub - Luo-Z13/pointobb: The source code of PointOBB

7.【3D异常检测】Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network

论文地址：https://arxiv.org//pdf/2311.14897
开源代码（即将开源）：GitHub - Chopper-233/Anomaly-ShapeNet: Official Anomaly-ShapeNet

8.【视频异常检测】BatchNorm-based Weakly Supervised Video Anomaly Detection

9.【Open-Vocabulary Segmentation】SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation

论文地址：https://arxiv.org//pdf/2311.15537
开源代码：GitHub - xb534/SED: Official Pytorch Implementation of SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation.

10.【超分辨率重建】SinSR: Diffusion-Based Image Super-Resolution in a Single Step

论文地址：https://arxiv.org//pdf/2311.14760
开源代码（即将开源）：GitHub - wyf0912/SinSR: SinSR: Diffusion-Based Image Super-Resolution in a Single Step

11.【行人重识别】（TIFS2023）Video-based Visible-Infrared Person Re-Identification with Auxiliary Samples

论文地址：https://arxiv.org//pdf/2311.15571
开源代码：GitHub - dyhBUPT/BUPTCampus: [TIFS 2023] Video-based Visible-Infrared Person Re-Identification with Auxiliary Samples

12.【多模态】Mug-STAN: Adapting Image-Language Pretrained Models for General Video Understanding

13.【多模态】Benchmarking Robustness of Text-Image Composed Retrieval

论文地址：https://arxiv.org//pdf/2311.14837
开源代码（即将开源）：GitHub - SunTongtongtong/Benchmark-Robustness-Text-Image-Compose-Retrieval

14.【数字人】HAVE-FUN: Human Avatar Reconstruction from Few-Shot Unconstrained Images

论文地址：https://arxiv.org//pdf/2311.15672
工程主页：HAVE-FUN
代码即将开源

15.【数字人】GAIA: Zero-shot Talking Avatar Generation

论文地址：https://arxiv.org//pdf/2311.15230
工程主页：GAIA
代码即将开源

16.【Diffusion】Regularization by Texts for Latent Diffusion Inverse Solvers

论文地址：https://arxiv.org//pdf/2311.15658
开源代码（即将开源）：GitHub - TReg-inverse/TReg

17.【Diffusion】Enhancing Diffusion Models with Text-Encoder Reinforcement Learning

论文地址：https://arxiv.org//pdf/2311.15657
开源代码：GitHub - chaofengc/TexForce: Official PyTorch codes for "Enhancing Diffusion Models with Text-Encoder Reinforcement Learning"

18.【Diffusion】Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets

论文地址：https://arxiv.org//pdf/2311.15127
开源代码：GitHub - Stability-AI/generative-models: Generative Models by Stability AI

19.【姿态估计】SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation

论文地址：https://arxiv.org//pdf/2311.15707
开源代码（即将开源）：GitHub - JiehongLin/SAM-6D: Code for "SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation".

20.【NeRF】Obj-NeRF: Extract Object NeRFs from Multi-view Images

论文地址：https://arxiv.org//pdf/2311.15291
工程主页：Obj-NeRF: Extracting Object NeRFs from Multi-view Images
代码即将开源

21.【人体重建】HumanRecon: Neural Reconstruction of Dynamic Human Using Geometric Cues and Physical Priors

论文地址：https://arxiv.org//pdf/2311.15171
开源代码：GitHub - PRIS-CV/HumanRecon

22.【三维重建】PaintNeSF: Artistic Creation of Stylized Scenes with Vectorized 3D Strokes

论文地址：https://arxiv.org//pdf/2311.15637
工程主页：PaintNeSF
代码即将开源

23.【数据蒸馏】Efficient Dataset Distillation via Minimax Diffusion

论文地址：https://arxiv.org//pdf/2311.15529
开源代码：GitHub - vimar-gu/MinimaxDiffusion: Efficient Dataset Distillation via Minimax Diffusion

24.【Zero-Shot Learning】Attribute-Aware Representation Rectification for Generalized Zero-Shot Learning

论文地址：https://arxiv.org//pdf/2311.14750
开源代码（即将开源）：zjrao/AARR · GitHub

25.【Continual Learning】CUCL: Codebook for Unsupervised Continual Learning

论文地址：https://arxiv.org//pdf/2311.14911
开源代码（即将开源）：zackschen/CUCL · GitHub

26.【Continual Learning】Class Gradient Projection For Continual Learning

论文地址：https://arxiv.org//pdf/2311.14905
开源代码：GitHub - zackschen/CGP

27.【Video Question Answering】AutoEval-Video: An Automatic Benchmark for Assessing Large Vision Language Models in Open-Ended Video Question Answering

论文地址：https://arxiv.org//pdf/2311.14906
开源代码（即将开源）：GitHub - Xiuyuan-Chen/AutoEval-Video

论文已打包，下载链接

CV计算机视觉交流群

群内包含目标检测、图像分割、目标跟踪、Transformer、多模态、NeRF、GAN、缺陷检测、显著目标检测、关键点检测、超分辨率重建、SLAM、人脸、OCR、生物医学图像、三维重建、姿态估计、自动驾驶感知、深度估计、视频理解、行为识别、图像去雾、图像去雨、图像修复、图像检索、车道线检测、点云目标检测、点云分割、图像压缩、运动预测、神经网络量化、网络部署等多个领域的大佬，不定期分享技术知识、面试技巧和内推招聘信息。

想进群的同学请添加微信号联系管理员：PingShanHai666。添加好友时请备注：学校/公司+研究方向+昵称。

CV计算机视觉每日开源代码Paper with code速览-2023.11.27

CV计算机视觉每日开源代码Paper with code速览-2023.11.23