↖ 　click there to get TOC

Awesome-Papers-Are-All-You-Need

Record papers I have read or reproduced since 2020 which were beneficial to my work.

My paper notes: 2021 2022

My Xmind notes:

AI Art (TalkingHead/Text2Image/Text2Video etc.)

Hand Mocap

Recommend:

hmr-survey by tinatiansjz

Hand3DResearch by SeanChenxy

Human-Video-Generation by yule-li.

HelloFace by becauseofAI

awesome-NeRF by koolo233

awesome-ai-painting by hua1995116

Awesome-Face-Restoration by TaoWangzj

---

3D Face Reconstruction

Year	Name	Paper	Codes
2018	3DDFA	Face Alignment in Full Pose Range: A 3D Total Solution	official
2019	Deep3DFaceRecon	Accurate 3D Face Reconstruction with Weakly-Supervised Learning: From Single Image to Image Set	unofficial
2020	3DDFA_V2	Towards Fast, Accurate and Stable 3D Dense Face Alignment	official
2020	Detailed3DFace	FaceScape: a Large-scale High Quality 3D Face Dataset and Detailed Riggable 3D Face Prediction	official
2021	DECA	Detailed Expression Capture and Animation	official
	Imperial College London
2019	GANFit	Generative Adversarial Network Fitting for High Fidelity 3D Face Reconstruction	official
2021	TBGAN	Synthesizing Coupled 3D Face Modalities by Trunk-Branch Generative Adversarial Networks	official
2021	OSTeC	One-Shot Texture Completion	official
2021	Fast-GANFit	Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction
2021	AvatarMe	AvatarMe: Realistically Renderable 3D Facial Reconstruction "in-the-wild"	official
2021	AvatarMe++	AvatarMe++: Facial Shape and BRDF Inference with Photorealistic Rendering-Aware GANs

---

3D Human Digitization

Year	Name	Paper	Codes
2019	speech2gesture	Learning Individual Styles of Conversational Gesture	official
2020	Monoport	Monoport: Monocular Volumetric Human Teleportation	official
2020	PiFuHD	PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization	Meta
2021	iPERCore	Liquid Warping GAN with Attention: A Unified Framework for Human Image Synthesis	official
2021	ContactHumanDynamics	Contact and Human Dynamics from Monocular Video	Stanford
2021	HuMoR	HuMoR: 3D Human Motion Model for Robust Pose Estimation	Stanford
2021	MeTRAbs	MeTRAbs: Metric-Scale Truncation-Robust Heatmaps for Absolute 3D Human Pose Estimation	official
2022	DeepMotion		official

Motion Capture & Driven

Year	Name	Paper	Codes
2021	ParameterizedMotion	Learning a family of motor skills from a single motion clip	official
2021	1165048017 Blog		official
2021	TDPT		official
2021	IK/FABRIK/CCDIK		UE4 doc

Human Kp Estimation

Year	Name	Paper	Codes
	2D Kp
2018	AlphaPose	RMPE: Regional Multi-Person Pose Estimation	official
	3D Kp
2019	mvpose	Fast and Robust Multi-Person 3D Pose Estimation from Multiple Views	ZJU3DV
2022	PoseTriplet	Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision	official
	combine
2021	MediaPipe		official
2021	mmpose		official

Human Motion Estimation

inverse dynamics

Year	Name	Paper	Codes
	Tricks
2020	6D rotation	On the Continuity of Rotation Representations in Neural Networks	official
	Body Model
2015	SMPL	SMPL: A Skinned Multi-Person Linear Model	official
2019	SMPL-X	SMPL-X: A new joint 3D model of the human body, face and hands together	official
	Image Based
2017	VNect	VNect: Real-time 3D Human Pose Estimation with a Single RGB Camera	Max Planck
2019	SPIN	Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop	official
2021	PyMAF	PyMAF: 3D Human Pose and Shape Regression with Pyramidal Mesh Alignment Feedback Loop	official
2021	MeshGraphormer	Mesh Graphormer	microsoft
2021	ROMP	Monocular, One-stage, Regression of Multiple 3D People	official
2021	DynaBOA	Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation	official
2021	PARE	PARE: Part Attention Regressor for 3D Human Body Estimation	Max Planck
2021	PoseTriplet	PoseTriplet: Co-evolving 3D Human Pose Estimation, Imitation, and Hallucination under Self-supervision	official
2020	PhysCap	PhysCap: Physically Plausible Monocular 3D Motion Capture in Real Time	Max Planck
2021	HybrIK	HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation	official
2021	Physics-based Human Motion Estimation	Physics-based Human Motion Estimation and Synthesis from Videos	Nvidia
2021	SimPoE	SimPoE: Simulated Character Control for 3D Human Pose Estimation	Meta
2021	imGHUM	imGHUM: Implicit Generative Models of 3D Human Shape and Articulated Pose	Google
2021	PoseAug	PoseAug: A Differentiable Pose Augmentation Framework for 3D Human Pose Estimation	official
2022	MuJoCo		deepmind
	Temporal Based
2020	VIBE	VIBE: Video Inference for Human Body Pose and Shape Estimation	official
2021	TCMR	TCMR: Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video	official
2021	maed	MAED: Encoder-decoder with Multi-level Attention for 3D Human Shape and Pose Estimation	official
	Full Body
2021	FrankMocap	A Strong and Easy-to-use Single View 3D Hand+Body Pose Estimator	Meta
2021	PIXIE	Collaborative Regression of Expressive Bodies using Moderation	official
2022	Hand4Whole	Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation	official
	Multi Views
2020	3D Human Pose Estimation	3D Human Pose Estimation using Multi Camera	official
2020	Learnable Triangulation	Learnable Triangulation of Human Pose	official
2020	Epipolar Transformers	Epipolar Transformers	official
2020	VoxelPose	VoxelPose: Towards Multi-Camera 3D Human Pose Estimation in Wild Environment	microsoft
2020	EasyMocap	Motion Capture from Internet Videos	ZJU3DV
2021	PlaneSweepPose	Multi-View Multi-Person 3D Pose Estimation with Plane Sweep Stereo	official
2021	freemocap		official
2022	Generalizable Human Pose Triangulation	Generalizable Human Pose Triangulation	official

Hand Estimation

Year	Name	Paper	Codes
2017	MANO	Embodied Hands: Modeling and Capturing Hands and Bodies Together	official
2020	Mediapipe	MediaPipe Hands: On-device Real-time Hand Tracking	Google
2021	MocapNETv3	Towards Holistic Real-time Human 3D Pose Estimation using MocapNETs	official
2021	S2HAND	S2HAND: Model-based 3D Hand Reconstruction via Self-Supervised Learning	Tencent

---

Classification

Year	Name	Paper	Codes
2021	MLP-Mixer	MLP-Mixer: An all-MLP Architecture for Vision	official
2021	Noisy Student	Self-training with Noisy Student improves ImageNet classification	official
2021	ImageNet-21K	ImageNet-21K Pretraining for the Masses	official
2021	MicroNet	MicroNet: Improving Image Recognition with Extremely Low FLOPs	official
2021	RepVGG	RepVGG: Making VGG-style ConvNets Great Again	official
2022	ConvNeXt	A ConvNet for the 2020s	official

---

Face Detection

Year	Name	Paper	Codes
2016	MTCNN	Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks	unofficial
2020	DSFD	DSFD: Dual Shot Face Detector	official
2021	SCRFD	Sample and Computation Redistribution for Efficient Face Detection	official

---

Face Swap

Year	Name	Paper	Codes
2019	FSGAN	FSGAN: Subject Agnostic Face Swapping and Reenactment	official
2020	Disney	High-Resolution Neural Face Swapping for Visual Effects	unofficial
2020	FaceShifter	FaceShifter: Towards High Fidelity And Occlusion Aware Face Swapping	unofficial
2021	SimSwap	SimSwap: An Efficient Framework For High Fidelity Face Swapping	official
2021	InfoSwap	Information Bottleneck Disentanglement for Identity Swapping	official
2021	ShapeEditer	ShapeEditer: a StyleGAN Encoder for Face Swapping
2021	HifiFace	HifiFace: 3D Shape and Semantic Prior Guided High Fidelity Face Swapping	unofficial
2022	MobileFaceSwap	MobileFaceSwap: A Lightweight Framework for Video Face Swapping	baidu
2022	Stitch it in Time	Stitch it in Time: GAN-Based Facial Editing of Real Videos	official

---

Image2Image Translation

Year	Name	Paper	Codes
2019	SPADE	Semantic Image Synthesis with Spatially-Adaptive Normalization	Nvidia
2021	OASIS	You Only Need Adversarial Supervision for Semantic Image Synthesis	official
2017	pix2pix	Image-to-Image Translation with Conditional Adversarial Networks	official
2018	pix2pixHD	High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs	nvidia
2018	vid2vid	Video-to-Video Synthesis	nvidia
	anime face
2019	TalkingHeadAnime		official
2021	TalkingHeadAnime2		official
2022	EasyVtuber		official

---

Image Generation

Year	Name	Paper	Codes
2020	ALAE	Adversarial Latent Autoencoders	official
2020	GANSpace	GANSpace: Discovering Interpretable GAN Controls	official
2021	Cartoon-StyleGAN	Fine-tuning StyleGAN2 for Cartoon Face Generation	official
2021	Barbershop	GAN-based Image Compositing using Segmentation Masks	official
2021	GANs N' Roses	GANs N' Roses: Stable, Controllable, Diverse Image to Image Translation	official
2021	PTI	PTI: Pivotal Tuning for Latent-based editing of Real Images	official
2021	sefa	Closed-Form Factorization of Latent Semantics in GANs	Genforce
2021	StyleMapGAN	StyleMapGAN: Exploiting Spatial Dimensions of Latent in GAN for Real-time Image Editing	NAVER AI
2021	SuperStyleNet	SuperStlyeNet: Deep Image Synthesis with Superpixel Based Style Encoder	official
2021	Chunkmogrify	Real Image Inversion via Segments	Adobe
2021	encoder4editing	Designing an Encoder for StyleGAN Image Manipulation	official
2021	Projected GANs	Projected GANs Converge Faster	official
2022	CLIPasso	Semantically-Aware Object Sketching	official

Nvidia

Year	Name	Paper	Codes
2019	StyleGan	A Style-Based Generator Architecture for Generative Adversarial Networks	Nvidia
2019	StyleGan2	Analyzing and Improving the Image Quality of StyleGAN	Nvidia
2021	stylegan2-ada	Training Generative Adversarial Networks with Limited Data	Nvidia
2021	StyleGan3	Alias-Free Generative Adversarial Networks	Nvidia
2021	SemanticGAN	Semantic Segmentation with Generative Models: Semi-Supervised Learning and Strong Out-of-Domain Generalization	Nvidia

---

Neural Head & Body

Year	Name	Paper	Codes
2020	FirstOrder	First Order Motion Model for Image Animation	official
2021	speech2gesture	NeuralRecon: Real-Time Coherent 3D Reconstruction from Monocular Video	ZJU3DV
2021	StyleGestures	Style-controllable speech-driven gesture synthesis using normalising flows	official
2021	face-vid2vid	One-Shot Free-View Neural Talking-Head Synthesis for Video Conferencing	Nvidia Project unofficial unofficial-2
2022	DaGAN	Depth-Aware Generative Adversarial Network for Talking Head Video Generation	official

NeRF

Year	Name	Paper	Codes
2020	NeRF	Representing Scenes as Neural Radiance Fields for View Synthesis	Berkeley
2021	Neural Body	Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans	ZJU3DV
2021	AD-Nerf	AD-NeRF: Audio Driven Neural Radiance Fields for Talking Head Synthesis	official

---

Object Detection

Year	Name	Paper	Codes
2020	100 Days of Hands	Understanding Human Hands in Contact at Internet Scale	official
2021	YOLOX	YOLOX: Exceeding YOLO Series in 2021	Megvii

---

Super Resolution

Year	Name	Paper	Codes
2018	ESRGAN	ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks	official
2020	DFDNet	Blind Face Restoration via Deep Multi-scale Component Dictionaries	official
2021	Real-ESRGAN	Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data	official
2021	GFPGAN	GFP-GAN: Towards Real-World Blind Face Restoration with Generative Facial Prior	official
2021	GPEN	GAN Prior Embedded Network for Blind Face Restoration in the Wild	official
2022	SwinIR	Image Restoration Using Swin Transformer	official
2022	VRT	A Video Restoration Transformer	official

---

ViT Transformer

Year	Name	Paper	Codes
2017	google Attention	Attention Is All You Need	official
2020	ViT	An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale	Google
2021	Token Labeling	All Tokens Matter: Token Labeling for Training Better Vision Transformers	official
2021	Tokens-to-Token ViT	Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet	official
2021	MAE	Masked Autoencoders Are Scalable Vision Learners	Meta

---

Metric

Year	Name	Paper	Codes
2017	AdaIN	Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization	official
2018	lpips	The Unreasonable Effectiveness of Deep Features as a Perceptual Metric	OpenAI
2020	IBA	Restricting the Flow: Information Bottlenecks for Attribution	official
2021	Focal Frequency Loss	Focal Frequency Loss for Image Reconstruction and Synthesis	official
2022	ffcv		MIT

---

Others

Year	Name	Paper	Codes
2020	3d photo inpainting	3D Photography using Context-aware Layered Depth Inpainting	official
2021	ParameterizedMotion	Learning a family of motor skills from a single motion clip	official
2021	AnimeInterp	Deep Animation Video Interpolation in the Wild	SenseTime
2021	DALLE	Zero-Shot Text-to-Image Generation	OpenAI