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.【目标检测】Zone Evaluation: Revealing Spatial Bias in Object Detection
论文地址:https://arxiv.org//pdf/2310.13215
开源代码:https://github.com/Zzh-tju/ZoneEval
2.【Referring Image Segmentation】Segment, Select, Correct: A Framework for Weakly-Supervised Referring Segmentation
论文地址:https://arxiv.org//pdf/2310.13479
开源代码(即将开源):https://github.com/fgirbal/segment-select-correct
3.【多模态】Benchmarking Sequential Visual Input Reasoning and Prediction in Multimodal Large Language Models
论文地址:https://arxiv.org//pdf/2310.13473
开源代码(即将开源):https://github.com/CoderJ-ONE/Giraffe-Bench
4.【多模态】OpenAnnotate3D: Open-Vocabulary Auto-Labeling System for Multi-modal 3D Data
论文地址:https://arxiv.org//pdf/2310.13398
开源代码(即将开源):https://github.com/Fudan-ProjectTitan/OpenAnnotate3D
5.【多模态】(EMNLP2023)Bridging the Gap between Synthetic and Authentic Images for Multimodal Machine Translation
论文地址:https://arxiv.org//pdf/2310.13361
开源代码(即将开源):https://github.com/ictnlp/SAMMT
6.【多模态】DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation
论文地址:https://arxiv.org//pdf/2310.13119
工程主页:DreamSpace: Dreaming Your Room Space with Text-Driven Panoramic Texture Propagation
开源代码(即将开源):https://github.com/ybbbbt/dreamspace
7.【自动驾驶:BEV】EarlyBird: Early-Fusion for Multi-View Tracking in the Bird's Eye View
论文地址:https://arxiv.org//pdf/2310.13350
开源代码(即将开源):https://github.com/tteepe/EarlyBird
8.【自动驾驶:多任务】LeTFuser: Light-weight End-to-end Transformer-Based Sensor Fusion for Autonomous Driving with Multi-Task Learning
论文地址:https://arxiv.org//pdf/2310.13135
开源代码:https://github.com/pagand/e2etransfuser/tree/cvpr-w
9.【Diffusion】(NeurIPS 2023)CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation
论文地址:https://arxiv.org//pdf/2310.13165
开源代码:https://github.com/sled-group/CycleNet
10.【姿态估计】CylinderTag: An Accurate and Flexible Marker for Cylinder-Shape Objects Pose Estimation Based on Projective Invariants
论文地址:https://arxiv.org//pdf/2310.13320
开源代码:https://github.com/wsakobe/CylinderTag
11.【NeRF】(BMVC2023)ManifoldNeRF: View-dependent Image Feature Supervision for Few-shot Neural Radiance Fields
论文地址:https://arxiv.org//pdf/2310.13670
开源代码(即将开源):https://github.com/haganelego/ManifoldNeRF_BMVC2023
12.【NeRF】Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos
论文地址:https://arxiv.org//pdf/2310.13356
工程主页:Sync-NeRF
开源代码:https://github.com/seoha-kim/Sync-NeRF
13.【NeRF】Spec-NeRF: Multi-spectral Neural Radiance Fields
论文地址:https://arxiv.org//pdf/2310.12987
开源代码:https://github.com/CPREgroup/SpecNeRF-v2
14.【Video Question Answering】(EMNLP2023)A Simple Baseline for Knowledge-Based Visual Question Answering
论文地址:https://arxiv.org//pdf/2310.13570
开源代码(即将开源):https://github.com/alexandrosXe/A-Simple-Baseline-For-Knowledge-Based-VQA
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-2023.10.20
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
CV计算机视觉每日开源代码Paper with code速览-2023.10.16
使用目标之间的先验关系提升目标检测器性能
港科大提出适用于夜间场景语义分割的无监督域自适应新方法
HSN:微调预训练ViT用于目标检测和语义分割,华南理工和阿里巴巴联合提出
EViT:借鉴鹰眼视觉结构,南开大学等提出ViT新骨干架构,在多个任务上涨点
如何优雅地读取网络的中间特征?