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

点击@CV计算机视觉，关注更多CV干货

1.【图像分割】SEGIC: Unleashing the Emergent Correspondence for In-Context Segmentation

论文地址：https://arxiv.org//pdf/2311.14671
开源代码（即将开源）：GitHub - MengLcool/SEGIC

2.【图像分割】（WACV2024）IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather

论文地址：https://arxiv.org//pdf/2311.14459
工程主页：IDD-AW: A Benchmark for Safe and Robust Segmentation of Drive Scenes in Unstructured Traffic and Adverse Weather
代码即将开源

3.【点云分割】Low Latency Instance Segmentation by Continuous Clustering for Rotating LiDAR Sensors

论文地址：https://arxiv.org//pdf/2311.13976
开源代码：GitHub - UniBwTAS/continuous_clustering

4.【超分辨率重建】Image Super-Resolution with Text Prompt Diffusion

论文地址：https://arxiv.org//pdf/2311.14282
开源代码（即将开源）：GitHub - zhengchen1999/PromptSR: PyTorch code for our paper "Image Super-Resolution with Text Prompt Diffusion"

5.【领域泛化】Parameter Exchange for Robust Dynamic Domain Generalization

论文地址：https://arxiv.org//pdf/2311.13928
开源代码：GitHub - MetaVisionLab/PE: Parameter Exchange for Robust Dynamic Domain Generalization (ACM MM 2023)

6.【多模态】CatVersion: Concatenating Embeddings for Diffusion-Based Text-to-Image Personalization

论文地址：https://arxiv.org//pdf/2311.14631
工程主页：CatVersion: Concatenating Embeddings for Diffusion-Based Text-to-Image Personalization
代码即将开源

7.【多模态】Animate124: Animating One Image to 4D Dynamic Scene

论文地址：https://arxiv.org//pdf/2311.14603
工程主页：Animate124: Animating One Image to 4D Dynamic Scene
开源代码（即将开源）：GitHub - HeliosZhao/Animate124: Animate124: Animating One Image to 4D Dynamic Scene

8.【多模态】Large Language Models as Automated Aligners for benchmarking Vision-Language Models

论文地址：https://arxiv.org//pdf/2311.14580
工程主页：Large Language Models as Automated Aligners for benchmarking Vision-Language Models
代码即将开源

9.【多模态】Inferring Latent Class Statistics from Text for Robust Visual Few-Shot Learning

论文地址：https://arxiv.org//pdf/2311.14544
开源代码：GitHub - ybendou/fs-text2stats

10.【多模态】HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding

论文地址：https://arxiv.org//pdf/2311.14064
开源代码：GitHub - richard-peng-xia/HGCLIP: HGCLIP: Exploring Vision-Language Models with Graph Representations for Hierarchical Understanding

11.【多模态】（NeurIPS 2023）Hardware Resilience Properties of Text-Guided Image Classifiers

论文地址：https://arxiv.org//pdf/2311.14062
开源代码：GitHub - TalalWasim/TextGuidedResilience: Official repository for "Hardware Resilience Properties of Text-Guided Image Classifiers" [NeurIPS 2023]

12.【数字人】GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar

论文地址：https://arxiv.org//pdf/2311.13655
工程主页：GAN-Avatar: Controllable Personalized GAN-based Human Head Avatar
代码即将开源

13.【姿态估计】GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

论文地址：https://arxiv.org//pdf/2311.14155
开源代码（即将开源）：GitHub - nv-nguyen/gigapose: GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence

14.【NeRF】Compact 3D Gaussian Representation for Radiance Field

论文地址：https://arxiv.org//pdf/2311.13681
工程主页：Compact 3D Gaussian Representation for Radiance Field
开源代码：GitHub - maincold2/Compact-3DGS

15.【人体重建】Binarized 3D Whole-body Human Mesh Recovery

论文地址：https://arxiv.org//pdf/2311.14323
开源代码（即将开源）：GitHub - ZHITENGLI/BiDRN

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-2023.11.22

CV计算机视觉每日开源代码Paper with code速览-2023.11.21

CV计算机视觉每日开源代码Paper with code速览-2023.11.20

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

CV计算机视觉交流群

猜你喜欢