README.md

Weekly Group Meeting Paper List (2021)

paper reading每周日下午两点开始。

组1：许家乐，钱一成，黄彬彬；
组2：胡俊豪，赵子伯，智轶浩；
组3：肖宇廷，周康，李晶；
组4：钟子明，刘壮华，严新豪；

Date	Speaker	Slides/Paper	Publisher	Website / Code
2021-08-08	许家乐	Self-Supervised 3D Mesh Reconstruction From Single Images	CVPR2021	Code
2021-08-08	钱一成	Unsupervised Learning of Action Classes With Continuous Temporal Embedding	CVPR2019	Code
2021-06-20	黄彬彬	UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for Multi-View Reconstruction	arXiv	Code
2021-05-30	许家乐	3D Reconstruction of Novel Object Shapes from Single Images	arXiv	Code
2021-03-28	钱深瀚	HumanGPS: Geodesic PreServing Feature for Dense Human Correspondences	arXiv
2021-04-25	廉东泽	ViT/DeiT/DeepViT/Swin Transformer	ICLR2021/Arxiv/CVPR2021/Arxiv	ViT-Pytorch/Swin Transformer
2021-04-19	胡俊豪	BoxInst: High-Performance Instance Segmentation with Box Annotations	arXiv	Code
2021-04-19	黄彬彬	End-to-End Video Instance Segmentation with Transformers	arXiv	Code
2021-04-11	许家乐	Local Deep Implicit Functions for 3D Shape	CVPR2020 (oral)	Code
2021-04-11	钱一成	Is Space-Time Attention All You Need for Video Understanding?	arXiv	Code
2021-03-28	钱深瀚	PatchmatchNet: Learned Multi-View Patchmatch Stereo	CVPR2021	Code
2021-03-21	李晶	DataMix: Efficient Privacy-Preserving Edge-Cloud Inference	ECCV2020	Code
2021-01-15	许家乐	RepVGG: Making VGG-style ConvNets Great Again	CVPR2021	Code
2021-01-01	钱深瀚	A Morphable Model For The Synthesis Of 3D Faces	SIGGRAPH '99	N/A
2020-12-25	李晶	DO 2D GANS KNOW 3D SHAPE? UNSUPERVISED 3DSHAPE RECONSTRUCTION FROM 2D IMAGE GANS	arXiv	N/A
2020-12-18	廉东泽	Nerf++: Analyzing and Improving Neural Radiance Fields	arXiv	code
2020-12-11	涂治	Dynamic Neural Radiance Fields for Monocular 4D Facial Avatar Reconstruction	arXiv	Project Homepage
2020-12-11	刘闻	pi-GAN: Periodic Implicit Generative Adversarial Networks for 3D-Aware Image Synthesis	arXiv	Project Homepage
2020-12-04	许家乐	Geo-PIFu: Geometry and Pixel Aligned Implicit Functions for Single-view Human Reconstruction	NIPS2020	code
2020-10-31	李晶	Test-time training with self-supervision for generalization under distribution shifts	ICML2020	code
2020-10-23	许家乐	CoReNet: Coherent 3D scene reconstruction from a single RGB image	ECCV2020	code
2020-10-16	周康	Synthesize then Compare: Detecting Failures and Anomalies for Semantic Segmentation	ECCV2020	N/A
2020-10-09	廉东泽	Are Labels Necessary for Neural Architecture Search?	ECCV2020 (Spotlight)	code
2020-10-09	赵子伯	Image Inpainting In CVPR2020&ECCV2020	CVPR2020&ECCV2020	N/A
2020-09-25	刘闻	DeepCap	CVPR 2020
2020-09-25	涂治	Wav2Lip: Accurately Lip-sync Videos to Any Speech	ACM MM 2020	code
2020-08-28	钱深瀚	Learning to Dress 3D People in Generative Clothing	CVPR2020
2020-08-07	朴智新	NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis	ECCV2020	code
2020-07-24	许家乐	PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization	ICCV2019	Code
2020-07-24	许家乐	PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization	CVPR2020	Code
2020-07-24	金磊	Learning Feature Descriptors using Camera Pose Supervision	ECCV2020	N/A
2020-07-17	周康	Conditional Gaussian Distribution Learning for Open Set Recognition	CVPR2020	N/A
2020-07-17	钱深瀚	Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation	CVPR2019	code
2020-07-10	李晶	Learning to Structure an Image with Few Colors	CVPR2020	N/A
2020-06-26	涂治	Controllable Person Image Synthesis with Attribute-Decomposed GAN	CVPR2020	Code
2020-06-19	许家乐	Neural Pose Transfer by Spatially Adaptive Instance Normalization	CVPR2020	Code
2020-06-26	涂治	Controllable Person Image Synthesis with Attribute-Decomposed GAN	CVPR2020	Code
2020-05-15	许家乐	PointGroup: Dual-Set Point Grouping for 3D Instance Segmentation	CVPR2020	Code
2020-05-08	余泽浩	How Useful is Self-Supervised Pretraining for Visual Tasks?	CVPR2020	Code
2020-05-04	李晶	Multi-scale dense networks for resource efficient image classification Improved Techniques for Training Adaptive Deep Networks Resolution Adaptive Networks for Efficient Inference	ICLR2018(Oral) ICCV2019 CVPR2020	Code Code
2020-05-04	钱深瀚	Bridging the Gap Between Anchor-based and Anchor-free Detection via Adaptive Training Sample Selection	CVPR2020	Code
2020-04-24	章浩	DDPAE_NerualPS2018 CVP_ICCV2019	NerualPS2018 / ICCV2019	DDPAE_code CVP_code
2020-04-10	廉东泽	Designing Network Design Spaces	CVPR2020	code
2020-04-03	罗伟鑫	Knowledge as Priors: Cross-Modal Knowledge Generalization for Datasets without Superior Knowledge	CVPR2020	N/A
2020-03-13	李晶	An Empirical Study of Spatial Attention Mechanisms in Deep Networks	ICCV2019	code
2020-03-13	钱深瀚	Distribution-Aware Coordinate Representation for Human Pose Estimation	CVPR2020	code
2020-02-28	徐衍钰	MultiModel Embeddings	Original	N/A
2020-02-28	廉东泽	Deep Snake for Real-Time Instance Segmentation	CVPR2020	code
2020-02-28	章浩	Improved Conditional VRNNs for Video Prediction	ICCV2019	N/A
2020-02-21	罗伟鑫	Pseudo Loss in Videos	Original	N/A
2020-02-21	朴智新	few shot video to video synthesis	NIPS 2019	code
2020-02-21	刘闻	Deep Compressed Sensing with relationship to Generative Models	Original
2020-02-14	许家乐	General 3D Room Layout from a Single View by Render-and-Compare	ECCV2020	code
2020-01-11	李晶	PointRend: Image Segmentation as Rendering	arxiv