CV计算机视觉每日开源代码Paper with code速览-2023.11.15

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.【基础网络架构：CNN】PadChannel: Improving CNN Performance through Explicit Padding Encoding

• 论文地址：https://arxiv.org//pdf/2311.07623

• 开源代码：GitHub - AussieSeaweed/pad-channel: Encoding padding statuses as an input channel for enhanced performance in convolutional neural networks

2.【语义分割】（ICLR2024）Test-Time Training for Semantic Segmentation with Output Contrastive Loss

• 论文地址：https://arxiv.org//pdf/2311.07877

• 开源代码：GitHub - dazhangyu123/OCL: Test-Time Training for Semantic Segmentation with Output Contrastive Loss

3.【医学图像分割：3D】Assessing Test-time Variability for Interactive 3D Medical Image Segmentation with Diverse Point Prompts

• 论文地址：https://arxiv.org//pdf/2311.07806

• 开源代码（即将开源）：GitHub - MedICL-VU/variability: Assessing Test-time Variability for Interactive 3D Medical Image Segmentation with Diverse Point Prompts

4.【多模态】Instant3D: Instant Text-to-3D Generation

• 论文地址：https://arxiv.org//pdf/2311.08403

• 工程主页：Instant3D: Instant Text-to-3D Generation

• 代码即将开源

5.【多模态】Towards Open-Ended Visual Recognition with Large Language Model

• 论文地址：https://arxiv.org//pdf/2311.08400

• 开源代码：GitHub - bytedance/OmniScient-Model: This repo contains the code for our paper Towards Open-Ended Visual Recognition with Large Language Model

6.【多模态】Improving Image Captioning via Predicting Structured Concepts

• 论文地址：https://arxiv.org//pdf/2311.08223

• 开源代码（即将开源）：GitHub - wangting0/SCP-WGCN: official code of "Improving Image Captioning via Predicting Structured Concepts"

7.【多模态】Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

• 论文地址：https://arxiv.org//pdf/2311.08046

• 开源代码：GitHub - PKU-YuanGroup/Chat-UniVi: Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

8.【多模态】One-2-3-45++: Fast Single Image to 3D Objects with Consistent Multi-View Generation and 3D Diffusion

• 论文地址：https://arxiv.org//pdf/2311.07885

• 工程主页：One-2-3-45++

• 开源代码（即将开源）：GitHub - SUDO-AI-3D/One2345plus

9.【多模态】Vision-Language Instruction Tuning: A Review and Analysis

• 论文地址：https://arxiv.org//pdf/2311.08172

• 开源代码（即将开源）：GitHub - palchenli/VL-Instruction-Tuning

10.【多模态】Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification

• 论文地址：https://arxiv.org//pdf/2311.07593

• 开源代码：GitHub - BatsResearch/fudd: Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification

11.【三维重建】DynamicSurf: Dynamic Neural RGB-D Surface Reconstruction with an Optimizable Feature Grid

• 论文地址：https://arxiv.org//pdf/2311.08159

• 工程主页：DynamicSurf: Dynamic Neural RGB-D Surface Reconstruction with an Optimizable Feature Grid.

• 代码即将开源

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-2023.11.14

CV计算机视觉每日开源代码Paper with code速览-2023.11.13

CV计算机视觉每日开源代码Paper with code速览-2023.11.10