CV计算机视觉每日开源代码Paper with code速览-2023.10.24_zero123++: a single image to consistent multi-view-优快云博客

本文链接：https://blog.youkuaiyun.com/zhangkai950121/article/details/134050400

精华置顶

墙裂推荐！小白如何1个月系统学习CV核心知识：链接

点击@CV计算机视觉，关注更多CV干货

论文已打包，点击进入—>下载界面

点击加入—>CV计算机视觉交流群

1.【目标检测】The Importance of Anti-Aliasing in Tiny Object Detection

论文地址：https://arxiv.org//pdf/2310.14221
开源代码（即将开源）：https://github.com/freshn/Anti-aliasing-Tiny-Object-Detection

2.【异常检测】Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection

论文地址：https://arxiv.org//pdf/2310.14228
开源代码：https://github.com/RuiyingLu/HVQ-Trans

3.【图像分割】（NeurIPS2023）FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

论文地址：https://arxiv.org//pdf/2310.15160
开源代码：https://github.com/LiheYoung/FreeMask

4.【语义分割】A Survey on Continual Semantic Segmentation: Theory, Challenge, Method and Application

论文地址：https://arxiv.org//pdf/2310.14277
开源代码：https://github.com/YBIO/SurveyCSS

5.【人脸识别】（ICCV2023）Invariant Feature Regularization for Fair Face Recognition

论文地址：https://arxiv.org//pdf/2310.14652
开源代码（即将开源）：https://github.com/milliema/InvReg

6.【医学图像处理】A comprehensive survey on deep active learning and its applications in medical image analysis

7.【医学图像分割：3D】SAM-Med3D

论文地址：https://arxiv.org//pdf/2310.15161
开源代码：https://github.com/uni-medical/SAM-Med3D

8.【多模态】（NeurIPS2023）Large Language Models are Visual Reasoning Coordinators

论文地址：https://arxiv.org//pdf/2310.15166
开源代码：https://github.com/cliangyu/Cola

9.【多模态】DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design

论文地址：https://arxiv.org//pdf/2310.15144
工程主页：DEsignBench: Exploring and Benchmarking DALL-E 3 for Imagining Visual Design
开源代码（即将开源）：https://github.com/microsoft/design-bench

10.【多模态】Large Language Models can Share Images, Too!

论文地址：https://arxiv.org//pdf/2310.14804
开源代码（即将开源）：https://github.com/passing2961/LLM-Share-Image

11.【多模态】HallusionBench: You See What You Think? Or You Think What You See? An Image-Context Reasoning Benchmark Challenging for GPT-4V(ision), LLaVA-1.5, and Other Multi-modality Models

论文地址：https://arxiv.org//pdf/2310.14566
开源代码（即将开源）：https://github.com/tianyi-lab/HallusionBench

12.【多模态】The BLA Benchmark: Investigating Basic Language Abilities of Pre-Trained Multimodal Models

论文地址：https://arxiv.org//pdf/2310.15061
开源代码：https://github.com/shin-ee-chen/BLA

13.【多模态】（EMNLP2023）Can Language Models Laugh at YouTube Short-form Videos?

论文地址：https://arxiv.org//pdf/2310.14159
开源代码：https://github.com/dayoon-ko/ExFunTube

14.【数字人】（NeurIPS2023）Learning Motion Refinement for Unsupervised Face Animation

论文地址：https://arxiv.org//pdf/2310.13912
开源代码（即将开源）：GitHub - JialeTao/MRFA: [NeurIPS 2023] Learning Motion Refinement for Unsupervised Face Animation

15.【深度估计】RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

论文地址：https://arxiv.org//pdf/2310.15171
开源代码：GitHub - ldkong1205/RoboDepth: [NeurIPS'23] RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

16.【自动驾驶：多模态感知】（CoRL 2023）BM2CP: Efficient Collaborative Perception with LiDAR-Camera Modalities

论文地址：https://arxiv.org//pdf/2310.14702
开源代码（即将开源）：https://github.com/byzhaoAI/BM2CP

17.【Diffusion】FreeNoise: Tuning-Free Longer Video Diffusion Via Noise Rescheduling

论文地址：https://arxiv.org//pdf/2310.15169
工程主页：FreeNoise
开源代码：https://github.com/arthur-qiu/LongerCrafter

18.【Diffusion】Zero123++: a Single Image to Consistent Multi-view Diffusion Base Model

论文地址：https://arxiv.org//pdf/2310.15110
开源代码：https://github.com/SUDO-AI-3D/zero123plus

19.【三维重建】Ghost on the Shell: An Expressive Representation of General 3D Shapes

论文地址：https://arxiv.org//pdf/2310.15168
工程主页：G-Shell
开源代码（即将开源）：https://github.com/lzzcd001/GShell/

20.【三维重建】Wonder3D: Single Image to 3D using Cross-Domain Diffusion

论文地址：https://arxiv.org//pdf/2310.15008
工程主页：Wonder3D: Single Image to 3D using Cross-Domain Diffusion
开源代码（即将开源）：https://github.com/xxlong0/Wonder3D

21.【运动合成】MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion

论文地址：https://arxiv.org//pdf/2310.14729
工程主页：MAS: Multi-view Ancestral Sampling for 3D motion generation using 2D diffusion
开源代码（即将开源）：https://github.com/roykapon/MAS

22.【Few-Shot Learning】FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning

论文地址：https://arxiv.org//pdf/2310.15105
开源代码：https://github.com/skingorz/FD-Align

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-2023.10.20

CV计算机视觉每日开源代码Paper with code速览-2023.10.19

CV计算机视觉每日开源代码Paper with code速览-2023.10.18

CV计算机视觉每日开源代码Paper with code速览-2023.10.17

CV计算机视觉每日开源代码Paper with code速览-2023.10.16