目标检测是当下应用最广的计算机视觉任务之一。本文整理了CVPR 2023 目标检测相关论文72篇,覆盖包括2D目标检测、3D目标检测、视频目标检测、人物交互检测、异常检测、伪装目标检测、关键点检测、显著性目标检测、车道线检测、边缘检测等10个细分任务。并且每篇论文都尽可能附了上对应的代码。
合集下载:点我跳转。
2D目标检测
[1]CapDet: Unifying Dense Captioning and Open-World Detection Pretraining
[代码]None
[2]Enhanced Training of Query-Based Object Detection via Selective Query Recollection
[代码]https://github.com/Fangyi-Chen/SQR
[3]DETRs with Hybrid Matching
[代码]https://github.com/HDETR
[4]YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
[代码]https://github.com/WongKinYiu/yolov7
[5]Object-Aware Distillation Pyramid for Open-Vocabulary Object Detection
[代码]https://github.com/LutingWang/OADP
[6]Detecting Everything in the Open World: Towards Universal Object Detection
[代码]https://github.com/zhenyuw16/UniDetector
[7]NeRF-RPN: A general framework for object detection in NeRFs
[代码]https://github.com/lyclyc52/NeRF_RPN
[8]What Can Human Sketches Do for Object Detection?
[代码]https://pinakinathc.github.io/sketch-detect
[9]Object Discovery from Motion-Guided Tokens
[代码]https://github.com/zpbao/motok
[10]Continual Detection Transformer for Incremental Object Detection
[代码]https://lyy.mpi-inf.mpg.de/CL-DETR/
[11]Multi-view Adversarial Discriminator: Mine the Non-causal Factors for Object Detection in Unseen Domains
[代码]https://github.com/K2OKOH/MAD
[12]Mapping Degeneration Meets Label Evolution: Learning Infrared Small Target Detection with Single Point Supervision
[代码]https://github.com/xinyiying/lesps
[13]Benchmarking the Physical-world Adversarial Robustness of Vehicle Detection
[代码]未开源
[14]DetCLIPv2: Scalable Open-Vocabulary Object Detection Pre-training via Word-Region Alignment
[代码]未开源
3D目标检测
[1]CAPE: Camera View Position Embedding for Multi-View 3D Object Detection
[代码]https://github.com/kaixinbear/CAPE
[2]Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency
[代码]https://github.com/weakmono3d/weakmono3d
[3]AeDet: Azimuth-invariant Multi-view 3D Object Detection
[代码]https://github.com/fcjian/AeDet
[4]Bi3D: Bi-domain Active Learning for Cross-domain 3D Object Detection
[代码]https://github.com/PJLab-ADG/3DTrans
[5]PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection
[代码]https://github.com/blvlab/pimae
[6]MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequences
[代码]https://github.com/skyhehe123/MSF
[7]Towards Domain Generalization for Multi-view 3D Object Detection in Bird-Eye-View
[代码]None
[8]X³KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection
[代码]None
[9]Virtual Sparse Convolution for Multimodal 3D Object Detection
[代码]https://github.com/hailanyi/VirConv
[10]MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection
[代码]https://github.com/SxJyJay/MSMDFusion
[11]Uni3D: A Unified Baseline for Multi-dataset 3D Object Detection
[代码]https://github.com/PJLab-ADG/3DTrans
[12]ConQueR: Query Contrast Voxel-DETR for 3D Object Detection
[代码]https://github.com/poodarchu/EFG
[13]LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion
[代码]https://github.com/sankin97/LoGoNet
[14]MonoATT: Online Monocular 3D Object Detection with Adaptive Token Transformer
[代码]未开源
[15]OcTr: Octree-based Transformer for 3D Object Detection
[代码]未开源
[16]VoxelNeXt: Fully Sparse VoxelNet for 3D Object Detection and Tracking
[代码]https://github.com/dvlab-research/VoxelNeXt
[17]Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving
[代码]https://github.com/kkkcx/3D_Corruptions_AD
[18]NS3D: Neuro-Symbolic Grounding of 3D Objects and Relations
[代码]未开源
[19]FrustumFormer: Adaptive Instance-aware Resampling for Multi-view 3D Detection
[代码]https://github.com/Robertwyq/Frustum
[20]Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild
[代码]https://github.com/facebookresearch/omni3d
[21]itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detection
[代码]https://github.com/hyeon-jo/interchange-transfer-KD
[22]Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scans
[代码]http://alexeybokhovkin.github.io/neural-part-priors/
[23]Viewpoint Equivariance for Multi-View 3D Object Detection
[代码]https://github.com/tri-ml/vedet
[24]Adaptive Sparse Convolutional Networks with Global Context Enhancement for Faster Object Detection on Drone Images
[代码]https://github.com/Cuogeihong/CEASC
[25]Learned Two-Plane Perspective Prior based Image Resampling for Efficient Object Detection
[代码]未开源
[26]Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving
[代码]未开源
[27]Hierarchical Supervision and Shuffle Data Augmentation for 3D Semi-Supervised Object Detection
[代码]https://github.com/azhuantou/hssda
[28]Curricular Object Manipulation in LiDAR-based Object Detection
[代码]https://github.com/ZZY816/COM
视频目标检测
[1]SCOTCH and SODA: A Transformer Video Shadow Detection Framework
[项目]https://lihaoliu-cambridge.github.io/scotch_and_soda/
[2]3D Video Object Detection with Learnable Object-Centric Global Optimization
[代码]https://github.com/jiaweihe1996/BA-Det
[3]Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies
[代码]https://github.com/tencentyouturesearch/highlightdetection-clc
[4]Real-time Multi-person Eyeblink Detection in the Wild for Untrimmed Video
[代码]https://github.com/wenzhengzeng/MPEblink
人物交互检测
[1]Detecting Human-Object Contact in Images
[项目]https://hot.is.tue.mpg.de/
[2]Category Query Learning for Human-Object Interaction Classification
[代码]https://github.com/charles-xie/CQL
[3]Instant-NVR: Instant Neural Volumetric Rendering for Human-object Interactions from Monocular RGBD Stream
[代码]https://nowheretrix.github.io/Instant-NVR/
[4]Relational Context Learning for Human-Object Interaction Detection
[代码]http://cvlab.postech.ac.kr/research/MUREN
伪装目标检测
[1]Feature Shrinkage Pyramid for Camouflaged Object Detection with Transformers
[代码]https://github.com/ZhouHuang23/FSPNet
显著性目标检测
[1]Texture-guided Saliency Distilling for Unsupervised Salient Object Detection
[代码]https://github.com/moothes/A2S-v2
[2]Sketch2Saliency: Learning to Detect Salient Objects from Human Drawings
[代码]https://ayankumarbhunia.github.io/Sketch2Saliency/
关键点检测
[1]Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling
[代码]https://ryohachiuma.github.io/
[2]Few-shot Geometry-Aware Keypoint Localization
[代码]https://xingzhehe.github.io/FewShot3DKP/
车道线检测
[1]BEV-LaneDet: a Simple and Effective 3D Lane Detection Baseline
[代码]https://github.com/gigo-team/bev_lane_det
边缘检测
[1]Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections
[代码]https://github.com/alexander-g/INBD
[2]The Treasure Beneath Multiple Annotations: An Uncertainty-aware Edge Detector
[代码]https://github.com/ZhouCX117/UAED
异常检测
[1]DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection
[代码]None
[2]Diversity-Measurable Anomaly Detection
[代码]None
[3]Block Selection Method for Using Feature Norm in Out-of-distribution Detection
[代码]https://github.com/gist-ailab/block-selection-for-OOD-detection
[4]Lossy Compression for Robust Unsupervised Time-Series Anomaly Detection
[代码]None
[5]Multimodal Industrial Anomaly Detection via Hybrid Fusion
[代码]https://github.com/nomewang/M3DM
[6]Hierarchical Semantic Contrast for Scene-aware Video Anomaly Detection
[代码]未开源
[7]Normalizing Flow based Feature Synthesis for Outlier-Aware Object Detection
[代码]未开源
[8]SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection
[代码]https://github.com/tiangexiang/SQUID
[9]Prompt-Guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features
[代码]未开源
[10]SimpleNet: A Simple Network for Image Anomaly Detection and Localization
[代码]https://github.com/DonaldRR/SimpleNet
[11]WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation
[代码]未开源
[12]OpenMix: Exploring Outlier Samples for Misclassification Detection
[代码]https://github.com/Impression2805/OpenMix
[13]Robust Outlier Rejection for 3D Registration with Variational Bayes
[代码]https://github.com/Jiang-HB/VBReg
[14]Video Event Restoration Based on Keyframes for Video Anomaly Detection
[代码]未开源
合集下载地址文章来源:https://www.toymoban.com/news/detail-496777.html
点击跳转下载地址文章来源地址https://www.toymoban.com/news/detail-496777.html
到了这里,关于CVPR2023 | 70+目标检测论文及代码整理的文章就介绍完了。如果您还想了解更多内容,请在右上角搜索TOY模板网以前的文章或继续浏览下面的相关文章,希望大家以后多多支持TOY模板网!