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:Transformer】White-Box Transformers via Sparse Rate Reduction: Compression Is All There Is?
-
论文地址:https://arxiv.org//pdf/2311.13110
-
工程主页:White-Box Transformers via Sparse Rate Reduction
-
开源代码:https://github.com/Ma-Lab-Berkeley/CRATE
2.【旋转目标检测】Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection
-
论文地址:https://arxiv.org//pdf/2311.12956
-
开源代码:https://github.com/SashaMatsun/LSKDiffDet
3.【图像分割】Visual In-Context Prompting
-
论文地址:https://arxiv.org//pdf/2311.13601
-
开源代码(即将开源):https://github.com/UX-Decoder/DINOv
4.【医学图像分割】SegVol: Universal and Interactive Volumetric Medical Image Segmentation
-
论文地址:https://arxiv.org//pdf/2311.13385
-
开源代码:https://github.com/BAAI-DCAI/SegVol
5.【域自适应】DA-STC: Domain Adaptive Video Semantic Segmentation via Spatio-Temporal Consistency
-
论文地址:https://arxiv.org//pdf/2311.13254
-
开源代码:https://github.com/ZHE-SAPI/DA-STC
6.【多模态】Soulstyler: Using Large Language Model to Guide Image Style Transfer for Target Object
-
论文地址:https://arxiv.org//pdf/2311.13562
-
开源代码(即将开源):https://github.com/yisuanwang/Soulstyler
7.【多模态】PG-Video-LLaVA: Pixel Grounding Large Video-Language Models
-
论文地址:https://arxiv.org//pdf/2311.13435
-
开源代码(即将开源):https://github.com/mbzuai-oryx/Video-LLaVA
8.【多模态】FusionFrames: Efficient Architectural Aspects for Text-to-Video Generation Pipeline
-
论文地址:https://arxiv.org//pdf/2311.13073
-
开源代码:https://github.com/ai-forever/KandinskyVideo
9.【多模态】LiveChat: Video Comment Generation from Audio-Visual Multimodal Contexts
-
论文地址:https://arxiv.org//pdf/2311.12826
-
开源代码:https://github.com/yy1lab/LiveChat
10.【数字人】XAGen: 3D Expressive Human Avatars Generation
-
论文地址:https://arxiv.org//pdf/2311.13574
-
工程主页:XAGen - Project Page
-
开源代码(即将开源):https://github.com/magic-research/xagen
11.【深度估计】Camera-Independent Single Image Depth Estimation from Defocus Blur
-
论文地址:https://arxiv.org//pdf/2311.13045
-
开源代码:https://github.com/sleekEagle/defocus_camind
12.【Diffusion】DiffusionMat: Alpha Matting as Sequential Refinement Learning
-
论文地址:https://arxiv.org//pdf/2311.13535
-
工程主页:DiffusionMat
-
开源代码(即将开源):https://github.com/cnnlstm/DiffusionMat
13.【目标计数】T-Rex: Counting by Visual Prompting
-
论文地址:https://arxiv.org//pdf/2311.13596
-
工程主页:T-Rex Counting
-
开源代码(即将开源):https://github.com/IDEA-Research/T-Rex
14.【NeRF】PIE-NeRF: Physics-based Interactive Elastodynamics with NeRF
-
论文地址:https://arxiv.org//pdf/2311.13099
-
工程主页:PIE-NeRF
-
代码即将开源
15.【图像合成】Diffusion360: Seamless 360 Degree Panoramic Image Generation based on Diffusion Models
-
论文地址:https://arxiv.org//pdf/2311.13141
-
开源代码:https://github.com/ArcherFMY/SD-T2I-360PanoImage
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-2023.11.22
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