#5G先锋# 近日，全球计算机视觉顶级会议IEEE CVPR落下帷幕，来自中兴通讯的视频算法团队参加了大会的三项核心赛事并分获第一、第二和第三的好成绩！其中，视频超分辨率的论文还被IEEE CVPR 2021 workshop收录。5G大视频正日益蓬勃发展，视频超分辨率、视频压缩和视频人像抠图三大关键基础技术将从根本上改变人们远程工作、视频会议等应用场景的体验。
几篇论文实现代码：
《Explore Image Deblurring via Encoded Blur Kernel Space》(CVPR 2021) GitHub:https:// github.com/VinAIResearch/blur-kernel-space-exploring [FIG7]
《VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation》(ICCV 2021) GitHub:https:// github.com/hzykent/VMNet [fig1]
《Greedy Gradient Ensemble for Robust Visual Question Answering》(ICCV 2021) GitHub:https:// github.com/GeraldHan/GGE
《Generalized Source-free Domain Adaptation》(ICCV 2021) GitHub:https:// github.com/Albert0147/G-SFDA
《Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP》(2021) GitHub:https:// github.com/timoschick/self-debiasing
《MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks》(NeurIPS 2021) GitHub:https:// github.com/alexrame/mixmo-pytorch [fig6]
《Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecture》(2021) GitHub:https:// github.com/CDInstitute/Building-Dataset-Generator [fig5]
《PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features》(2021) GitHub:https:// github.com/qq456cvb/SPRIN [fig2]
《Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecture》(2021) GitHub:https:// github.com/CDInstitute/Building-Dataset-Generator [fig4]
《PHASER: A Robust and Correspondence-Free Global Pointcloud Registration》(2021) GitHub:https:// github.com/ethz-asl/phaser [fig3]
《Text-Based Ideal Points》(ACL 2020) GitHub:https:// github.com/keyonvafa/tbip
《Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation》(ECCV 2020) GitHub:https:// github.com/TKKim93/APE
《Domain Adaptive Imitation Learning》(2020) GitHub:https:// github.com/ermongroup/dail
《Training Generative Adversarial Networks by Solving Ordinary Differential Equations》(2020) GitHub:https:// github.com/titu1994/pytorch_odegan
《SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning》(2020) GitHub:https:// github.com/cjrd/selfaugment
《Explore Image Deblurring via Encoded Blur Kernel Space》(CVPR 2021) GitHub:https:// github.com/VinAIResearch/blur-kernel-space-exploring [FIG7]
《VMNet: Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation》(ICCV 2021) GitHub:https:// github.com/hzykent/VMNet [fig1]
《Greedy Gradient Ensemble for Robust Visual Question Answering》(ICCV 2021) GitHub:https:// github.com/GeraldHan/GGE
《Generalized Source-free Domain Adaptation》(ICCV 2021) GitHub:https:// github.com/Albert0147/G-SFDA
《Self-Diagnosis and Self-Debiasing: A Proposal for Reducing Corpus-Based Bias in NLP》(2021) GitHub:https:// github.com/timoschick/self-debiasing
《MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks》(NeurIPS 2021) GitHub:https:// github.com/alexrame/mixmo-pytorch [fig6]
《Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecture》(2021) GitHub:https:// github.com/CDInstitute/Building-Dataset-Generator [fig5]
《PRIN/SPRIN: On Extracting Point-wise Rotation Invariant Features》(2021) GitHub:https:// github.com/qq456cvb/SPRIN [fig2]
《Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecture》(2021) GitHub:https:// github.com/CDInstitute/Building-Dataset-Generator [fig4]
《PHASER: A Robust and Correspondence-Free Global Pointcloud Registration》(2021) GitHub:https:// github.com/ethz-asl/phaser [fig3]
《Text-Based Ideal Points》(ACL 2020) GitHub:https:// github.com/keyonvafa/tbip
《Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation》(ECCV 2020) GitHub:https:// github.com/TKKim93/APE
《Domain Adaptive Imitation Learning》(2020) GitHub:https:// github.com/ermongroup/dail
《Training Generative Adversarial Networks by Solving Ordinary Differential Equations》(2020) GitHub:https:// github.com/titu1994/pytorch_odegan
《SelfAugment: Automatic Augmentation Policies for Self-Supervised Learning》(2020) GitHub:https:// github.com/cjrd/selfaugment
几篇论文实现代码：
《Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning》(CVPR 2021) GitHub:https:// github.com/zhukaii/SPPR [fig1]
《Colin Graber, Grace Tsai, Michael Firman, Gabriel Brostow, Alexander Schwing》(CVPR 2021) GitHub:https:// github.com/nianticlabs/panoptic-forecasting [fig3]
《Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning》(ACL 2021) GitHub:https:// github.com/lupantech/InterGPS [fig2]
《NPMs: Neural Parametric Models for 3D Deformable Shapes》(ICCV 2021) GitHub:https:// github.com/pablopalafox/npms [fig6]
《Long-Short Transformer: Efficient Transformers for Language and Vision》(2021) GitHub:https:// github.com/NVIDIA/transformer-ls [fig4]
《DPT: Deformable Patch-based Transformer for Visual Recognition》(2021) GitHub:https:// github.com/CASIA-IVA-Lab/DPT
《ManiSkill: Learning-from-Demonstrations Benchmark for Generalizable Manipulation Skills》(2021) GitHub:https:// github.com/haosulab/ManiSkill-Learn
《OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics》(2021) GitHub:https:// github.com/thu-coai/OpenMEVA
《Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis》(2021) GitHub:https:// github.com/mutiann/few-shot-transformer-tts
《Did You Ask a Good Question? A Cross-Domain Question IntentionClassification Benchmark for Text-to-SQL》(2020) GitHub:https:// github.com/chatc/TriageSQL
《Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification》(2020) GitHub:https:// github.com/Z-Zheng/FreeNet [fig5]
《Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning》(CVPR 2021) GitHub:https:// github.com/zhukaii/SPPR [fig1]
《Colin Graber, Grace Tsai, Michael Firman, Gabriel Brostow, Alexander Schwing》(CVPR 2021) GitHub:https:// github.com/nianticlabs/panoptic-forecasting [fig3]
《Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning》(ACL 2021) GitHub:https:// github.com/lupantech/InterGPS [fig2]
《NPMs: Neural Parametric Models for 3D Deformable Shapes》(ICCV 2021) GitHub:https:// github.com/pablopalafox/npms [fig6]
《Long-Short Transformer: Efficient Transformers for Language and Vision》(2021) GitHub:https:// github.com/NVIDIA/transformer-ls [fig4]
《DPT: Deformable Patch-based Transformer for Visual Recognition》(2021) GitHub:https:// github.com/CASIA-IVA-Lab/DPT
《ManiSkill: Learning-from-Demonstrations Benchmark for Generalizable Manipulation Skills》(2021) GitHub:https:// github.com/haosulab/ManiSkill-Learn
《OpenMEVA: A Benchmark for Evaluating Open-ended Story Generation Metrics》(2021) GitHub:https:// github.com/thu-coai/OpenMEVA
《Multilingual Byte2Speech Models for Scalable Low-resource Speech Synthesis》(2021) GitHub:https:// github.com/mutiann/few-shot-transformer-tts
《Did You Ask a Good Question? A Cross-Domain Question IntentionClassification Benchmark for Text-to-SQL》(2020) GitHub:https:// github.com/chatc/TriageSQL
《Fast Patch-Free Global Learning Framework for Fully End-to-End Hyperspectral Image Classification》(2020) GitHub:https:// github.com/Z-Zheng/FreeNet [fig5]
✋热门推荐