CV计算机视觉每日开源代码Paper with code速览-2023.11.6

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.【点云3D目标检测】（NeurIPS2023）Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

• 论文地址：https://arxiv.org//pdf/2311.01682

• 开源代码：GitHub - haibao-yu/FFNet-VIC3D

​

2.【多模态】（NeurIPS2023）FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation

• 论文地址：https://arxiv.org//pdf/2311.01813

• 开源代码：GitHub - llyx97/FETV: [NeurIPS 2023 Datasets and Benchmarks] "FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation", Yuanxin Liu, Lei Li, Shuhuai Ren, Rundong Gao, Shicheng Li, Sishuo Chen, Xu Sun, Lu Hou

​

3.【多模态】MixCon3D: Synergizing Multi-View and Cross-Modal Contrastive Learning for Enhancing 3D Representation

• 论文地址：https://arxiv.org//pdf/2311.01734

• 开源代码：GitHub - UCSC-VLAA/MixCon3D: The official implementation of paper "MixCon3D: Synergizing Multi-View and Cross-Modal Contrastive Learning for Enhancing 3D Representation"

​

4.【多模态】（SIGGRAPH Asia 2023）EXIM: A Hybrid Explicit-Implicit Representation for Text-Guided 3D Shape Generation

• 论文地址：https://arxiv.org//pdf/2311.01714

• 开源代码：GitHub - liuzhengzhe/EXIM: SIGGRAPH Asia 2023 & TOG

​

5.【多模态】（WACV2024）Improving Fairness using Vision-Language Driven Image Augmentation

• 论文地址：https://arxiv.org//pdf/2311.01573

• 开源代码（即将开源）：GitHub - Moreno98/Vision-Language-Bias-Control: Official implementation of the paper "Improving Fairness using Vision-Language Driven Image Augmentation" accepted at WACV 24.

​

6.【多模态】What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning

• 论文地址：https://arxiv.org//pdf/2311.01487

• 开源代码：GitHub - RUCAIBox/ComVint: The official GitHub page for ''What Makes for Good Visual Instructions? Synthesizing Complex Visual Reasoning Instructions for Visual Instruction Tuning''

​

7.【多模态】FAITHSCORE: Evaluating Hallucinations in Large Vision-Language Models

• 论文地址：https://arxiv.org//pdf/2311.01477

• 开源代码（即将开源）：GitHub - bcdnlp/FAITHSCORE

​

8.【视频理解】VQPy: An Object-Oriented Approach to Modern Video Analytics

• 论文地址：https://arxiv.org//pdf/2311.01623

• 开源代码：GitHub - vqpy/vqpy: VQPy: An object-oriented approach to modern video analytics

​

9.【姿态估计】（ICLR2023）Modeling the Uncertainty with Maximum Discrepant Students for Semi-supervised 2D Pose Estimation

• 论文地址：https://arxiv.org//pdf/2311.01770

• 开源代码：GitHub - Qi2019KB/MDSs at master

​

10.【NeRF】EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

• 论文地址：https://arxiv.org//pdf/2311.02077

• 工程主页：EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

• 开源代码：GitHub - NVlabs/EmerNeRF: PyTorch Implementation of EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

​

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。

推荐阅读：

CV计算机视觉每日开源代码Paper with code速览-2023.11.3

CV计算机视觉每日开源代码Paper with code速览-2023.11.2

CV计算机视觉每日开源代码Paper with code速览-2023.11.1

CV计算机视觉每日开源代码Paper with code速览-2023.10.31