CV计算机视觉每日开源代码Paper with code速览-2023.10.25

该博客推荐小白1个月系统学习CV核心知识的链接，提供显著目标检测、3D目标检测、医学图像分类等多篇CV论文的地址与开源代码情况。还设有CV计算机视觉交流群，群内涉及多领域大佬，会分享技术、面试和招聘信息，同时推荐了多篇CV相关阅读内容。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

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.【显著目标检测】Salient Object Detection in RGB-D Videos

论文地址：https://arxiv.org//pdf/2310.15482
开源代码：GitHub - kerenfu/RDVS

2.【3D目标检测】（NeurIPS 2023）Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection

论文地址：https://arxiv.org//pdf/2310.15670
开源代码（即将开源）：GitHub - OpenDriveLab/Birds-eye-view-Perception: Awesome BEV perception research and cookbook for all level audience in autonomous diriving

3.【医学图像分类】（MICCAI2023）Interpretable Medical Image Classification using Prototype Learning and Privileged Information

论文地址：https://arxiv.org//pdf/2310.15741
开源代码：GitHub - XRad-Ulm/Proto-Caps

4.【动作识别】IMD: 3D Action Representation Learning with Inter- and Intra-modal Mutual Distillation

论文地址：https://arxiv.org//pdf/2310.15568
开源代码（即将开源）：GitHub - maoyunyao/I2MD

5.【多模态】Woodpecker: Hallucination Correction for Multimodal Large Language Models

6.【多模态】Visual Cropping Improves Zero-Shot Question Answering of Multimodal Large Language Models

论文地址：https://arxiv.org//pdf/2310.16033
开源代码（即将开源）：https://github.com/saccharomycetes/visual_crop_zsvqa

7.【多模态】Vision-Language Pseudo-Labels for Single-Positive Multi-Label Learning

论文地址：https://arxiv.org//pdf/2310.15985
开源代码：GitHub - mvrl/VLPL: The official implementation of VLPL: Vision Language Pseudo Label for Multi-label Learning with Single Positive Labels

8.【多模态】（NeurIPS2023）Language-driven Scene Synthesis using Multi-conditional Diffusion Model

论文地址：https://arxiv.org//pdf/2310.15948
工程主页：Language-driven Scene Synthesis using Multi-conditional Diffusion Model
开源代码：GitHub - andvg3/LSDM: Dataset and Code for NeurIPS2023 paper "Language-driven Scene Synthesis using Multi-conditional Diffusion Model"

9.【多模态】Inject Semantic Concepts into Image Tagging for Open-Set Recognition

论文地址：https://arxiv.org//pdf/2310.15200
开源代码：GitHub - xinyu1205/recognize-anything: Open-source and strong fundamental image recognition models.

10.【单目3D目标检测】GUPNet++: Geometry Uncertainty Propagation Network for Monocular 3D Object Detection

论文地址：https://arxiv.org//pdf/2310.15624
开源代码（即将开源）：https://github.com/SuperMHP/GUPNet_Plus

11.【NeRF】（NeurIPS 2023）GNeSF: Generalizable Neural Semantic Fields

论文地址：https://arxiv.org//pdf/2310.15712
开源代码（即将开源）：GitHub - HLinChen/GNeSF

12.【Video Question Answering】（EMNLP2023）Large Language Models are Temporal and Causal Reasoners for Video Question Answering

论文地址：https://arxiv.org//pdf/2310.15747
开源代码（即将开源）：GitHub - mlvlab/Flipped-VQA: Large Language Models are Temporal and Causal Reasoners for Video Question Answering (EMNLP 2023)

13.【图像合成】Integrating View Conditions for Image Synthesis

论文地址：https://arxiv.org//pdf/2310.16002
开源代码（即将开源）：GitHub - viiika/ViewControl: This is the official implementation of the paper "Intergrating View Conditions for Image Synthesis".

14.【单目深度估计】G2-MonoDepth: A General Framework of Generalized Depth Inference from Monocular RGB+X Data

论文地址：https://arxiv.org//pdf/2310.15422
开源代码：GitHub - Wang-xjtu/G2-MonoDepth

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-2023.10.23

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