点击@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】GIFT: Generative Interpretable Fine-Tuning Transformers

• 论文地址：https://arxiv.org//pdf/2312.00700

• 工程主页：GIFT: Generative Interpretable Fine-Tuning Transformers

• 开源代码（即将开源）：GitHub - savadikarc/gift

2.【图像分类】BCN: Batch Channel Normalization for Image Classification

• 论文地址：https://arxiv.org//pdf/2312.00596

• 开源代码：GitHub - AfifaKhaled/Batch-Channel-Normalization

3.【语义分割】Efficient Multimodal Semantic Segmentation via Dual-Prompt Learning

• 论文地址：https://arxiv.org//pdf/2312.00360

• 开源代码（即将开源）：GitHub - ShaohuaDong2021/DPLNet

4.【目标跟踪】Dense Optical Tracking: Connecting the Dots

• 论文地址：https://arxiv.org//pdf/2312.00786

• 工程主页：Dense Optical Tracking: Connecting the Dots

• 开源代码（即将开源）：GitHub - 16lemoing/dot

5.【目标跟踪】TrackDiffusion: Multi-object Tracking Data Generation via Diffusion Models

• 论文地址：https://arxiv.org//pdf/2312.00651

• 工程主页：TrackDiffusion: Multi-object Tracking Data Generation via Diffusion Models

• 开源代码（即将开源）：GitHub - pixeli99/TrackDiffusion: Multi-object Tracking Data Generation via Diffusion Models.

6.【人脸识别】Rethinking the Domain Gap in Near-infrared Face Recognition

• 论文地址：https://arxiv.org//pdf/2312.00627

• 开源代码（即将开源）：GitHub - michaeltrs/RethinkNIRVIS

7.【多模态】Making Large Multimodal Models Understand Arbitrary Visual Prompts

• 论文地址：https://arxiv.org//pdf/2312.00784

• 工程主页：ViP-LLaVA

• 开源代码：GitHub - mu-cai/ViP-LLaVA

8.【多模态】Merlin:Empowering Multimodal LLMs with Foresight Minds

• 论文地址：https://arxiv.org//pdf/2312.00589

• 工程主页：Merlin: Empowering Multimodal LLMs with Foresight Minds

• 开源代码（即将开源）：GitHub - Ahnsun/merlin: Merlin: Empowering Multimodal LLMs with Foresight Minds

9.【多模态】RTQ: Rethinking Video-language Understanding Based on Image-text Model

• 论文地址：https://arxiv.org//pdf/2312.00347

• 开源代码：GitHub - SCZwangxiao/RTQ-MM2023: ACM Multimedia 2023 (Oral) - RTQ: Rethinking Video-language Understanding Based on Image-text Model

10.【多模态】StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

• 论文地址：https://arxiv.org//pdf/2312.00330

• 工程主页：StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

• 开源代码：GitHub - GongyeLiu/StyleCrafter: StyleCrafter: Enhancing Stylized Text-to-Video Generation with Style Adapter

11.【多模态】OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition

• 论文地址：https://arxiv.org//pdf/2312.00096

• 工程主页：OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition

• 开源代码（即将开源）：GitHub - tomchen-ctj/OST: OST: Refining Text Knowledge with Optimal Spatio-Temporal Descriptor for General Video Recognition

12.【多模态】X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation

• 论文地址：https://arxiv.org//pdf/2312.00085

• 工程主页：X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation

• 开源代码（即将开源）：GitHub - xmu-xiaoma666/X-Dreamer: A pytorch implementation of “X-Dreamer: Creating High-quality 3D Content by Bridging the Domain Gap Between Text-to-2D and Text-to-3D Generation”

13.【多模态】Synthesize, Diagnose, and Optimize: Towards Fine-Grained Vision-Language Understanding

• 论文地址：https://arxiv.org//pdf/2312.00081

• 开源代码（即将开源）：GitHub - wjpoom/SPEC: The official implementation of paper "synthesize, diagnose, and optimize: towards fine-grained vision-language understanding"

14.【多模态】Probabilistic Copyright Protection Can Fail for Text-to-Image Generative Models

• 论文地址：https://arxiv.org//pdf/2312.00057

• 开源代码：GitHub - South7X/VA3: Probabilistic Copyright Protection Can Fail for Text-to-Image Generative Models

15.【自动驾驶：BEV】PointBeV: A Sparse Approach to BeV Predictions

• 论文地址：https://arxiv.org//pdf/2312.00703

• 开源代码（即将开源）：GitHub - valeoai/PointBeV: A new BeV paradigm focusing sparsity and efficiency

16.【自动驾驶：多模态】Dolphins: Multimodal Language Model for Driving

• 论文地址：https://arxiv.org//pdf/2312.00438

• 工程主页：VLM-Driver

• 开源代码（即将开源）：GitHub - vlm-driver/Dolphins

17.【Diffusion】Fast ODE-based Sampling for Diffusion Models in Around 5 Steps

• 论文地址：https://arxiv.org//pdf/2312.00094

• 开源代码（即将开源）：GitHub - zhyzhouu/amed-solver

18.【Diffusion】Unsupervised Keypoints from Pretrained Diffusion Models

• 论文地址：https://arxiv.org//pdf/2312.00065

• 工程主页：Unsupervised Keypoints from Pretrained Diffusion Models

• 开源代码：GitHub - ubc-vision/StableKeypoints

19.【深度补全】SparseDC: Depth Completion from sparse and non-uniform inputs

• 论文地址：https://arxiv.org//pdf/2312.00097

• 开源代码：GitHub - WHU-USI3DV/SparseDC: [ArXiv 2023] SparseDC: Depth Completion from sparse and non-uniform inputs

20.【人体运动生成】MoMask: Generative Masked Modeling of 3D Human Motions

• 论文地址：https://arxiv.org//pdf/2312.00063

• 工程主页：MoMask: Generative Masked Modeling of 3D Human Motions

• 开源代码（即将开源）：GitHub - EricGuo5513/momask-codes

21.【NeRF】EvE: Exploiting Generative Priors for Radiance Field Enrichment

• 论文地址：https://arxiv.org//pdf/2312.00639

• 工程主页：EvE: Exploiting Generative Priors for Radiance Field Enrichment | Karim Kassab, Antoine Schnepf, Jean-Yves Franceschi, Laurent Caraffa, Jeremie Mary, Valérie Gouet-Brunet

• 代码即将开源

22.【视频生成】VideoBooth: Diffusion-based Video Generation with Image Prompts

• 论文地址：https://arxiv.org//pdf/2312.00777

• 工程主页：VideoBooth

• 开源代码：GitHub - Vchitect/VideoBooth

23.【三维重建】MorpheuS: Neural Dynamic 360° Surface Reconstruction from Monocular RGB-D Video

• 论文地址：https://arxiv.org//pdf/2312.00778

• 工程主页：MorpheuS

• 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-2023.12.4

CV计算机视觉每日开源代码Paper with code速览-2023.12.1

CV计算机视觉每日开源代码Paper with code速览-2023.11.30