Awesome
Awesome-ICCV2021-Low-Level-Vision
A Collection of Papers and Codes for ICCV2021 Low Level Vision and Image Generation
整理汇总下2021年ICCV中图像生成(Image Generation)和底层视觉(Low-Level Vision)任务相关的论文和代码,包括图像生成,图像编辑,图像风格迁移,图像翻译,图像修复,图像超分及其他底层视觉任务。大家如果觉得有帮助,欢迎star~~
参考或转载请注明出处,文中有不足或者需要补充的地方也欢迎PR
ICCV2021官网:https://iccv2021.thecvf.com/
ICCV2021完整论文列表:https://openaccess.thecvf.com/ICCV2021
开会时间:2021年10月11日-10月17日
【Contents】
- 1.图像生成(Image Generation)
- 2.图像编辑(Image Manipulation/Image Editing)
- 3.图像风格迁移(Image Transfer)
- 4.图像翻译(Image to Image Translation)
- 5.图像修复(Image Inpaiting/Image Completion)
- 6.图像超分辨率(Image Super-Resolution)
- 7.图像去雨(Image Deraining)
- 8.图像去雾(Image Dehazing)
- 9.图像去模糊(Image Deblurring)
- 10.图像去噪(Image Denoising)
- 11.图像恢复(Image Restoration)
- 12.图像增强(Image Enhancement)
- 13.图像质量评价(Image Quality Assessment)
- 14.插帧(Frame Interpolation)
- 15.视频/图像压缩(Video/Image Compression)
- 16.其他底层视觉任务(Other Low Level Vision)
<a name="1.图像生成"></a>
1.图像生成(Image Generation)
Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts
- Paper:https://arxiv.org/abs/2104.00887
- Code:https://github.com/clovaai/mxfont
- 小样本字体生成
PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering
Toward Spatially Unbiased Generative Models
Disentangled Lifespan Face Synthesis
Handwriting Transformers
Diagonal Attention and Style-based GAN for Content-Style Disentanglement in Image Generation and Translation
ReStyle: A Residual-Based StyleGAN Encoder via Iterative Refinement
Paint Transformer: Feed Forward Neural Painting with Stroke Prediction
GAN Inversion for Out-of-Range Images with Geometric Transformations
The Animation Transformer: Visual Correspondence via Segment Matching
- Paper:https://arxiv.org/abs/2109.02614
- 手绘图变动画
Image Synthesis via Semantic Composition
- Paper:https://shepnerd.github.io/scg/resources/01145.pdf
- Code:https://github.com/dvlab-research/SCGAN
Detail Me More: Improving GAN's Photo-Realism of Complex Scenes
De-Rendering Stylized Texts
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Shimoda_De-Rendering_Stylized_Texts_ICCV_2021_paper.html
- Code:https://github.com/dvlab-research/SCGAN
<a name="2.图像编辑"></a>
2.图像编辑(Image Manipulation/Image Editing)
EigenGAN: Layer-Wise Eigen-Learning for GANs
From Continuity to Editability: Inverting GANs with Consecutive Images
- Paper:https://arxiv.org/abs/2107.13812
- Code:https://github.com/cnnlstm/InvertingGANs_with_ConsecutiveImgs
HeadGAN: One-shot Neural Head Synthesis and Editing
Orthogonal Jacobian Regularization for Unsupervised Disentanglement in Image Generation
Sketch Your Own GAN
A Latent Transformer for Disentangled Face Editing in Images and Videos
Learning Facial Representations from the Cycle-consistency of Face
StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery
Talk-to-Edit: Fine-Grained Facial Editing via Dialog
Dressing in Order: Recurrent Person Image Generation for Pose Transfer, Virtual Try-on and Outfit Editing
- Paper:https://cuiaiyu.github.io/dressing-in-order/Cui_Dressing_in_Order.pdf
- Code:https://github.com/cuiaiyu/dressing-in-order
GAN-Control: Explicitly Controllable GANs
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Shoshan_GAN-Control_Explicitly_Controllable_GANs_ICCV_2021_paper.html
- Code:https://github.com/cuiaiyu/dressing-in-order
Explaining in Style: Training a GAN To Explain a Classifier in StyleSpace
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Lang_Explaining_in_Style_Training_a_GAN_To_Explain_a_Classifier_ICCV_2021_paper.html
- Code:https://github.com/google/explaining-in-style
<a name="3.图像风格迁移"></a>
3.图像风格迁移(Image Transfer)
ALADIN: All Layer Adaptive Instance Normalization for Fine-grained Style Similarity
Domain Aware Universal Style Transfer
- Paper:https://arxiv.org/abs/2108.04441
- Code:https://github.com/Kibeom-Hong/Domain-Aware-Style-Transfer
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
Diverse Image Style Transfer via Invertible Cross-Space Mapping
StyleFormer: Real-Time Arbitrary Style Transfer via Parametric Style Composition
<a name="4.图像翻译"></a>
4.图像翻译(Image to Image Translation)
SPatchGAN: A Statistical Feature Based Discriminator for Unsupervised Image-to-Image Translation
Scaling-up Disentanglement for Image Translation
Unaligned Image-to-Image Translation by Learning to Reweight
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Xie_Unaligned_Image-to-Image_Translation_by_Learning_to_Reweight_ICCV_2021_paper.html
- Code:https://github.com/Mid-Push/IrwGAN <a name="5.图像修复"></a>
5.图像修复(Image Inpaiting/Image Completion)
Implicit Internal Video Inpainting
Internal Video Inpainting by Implicit Long-range Propagation
Occlusion-Aware Video Object Inpainting
High-Fidelity Pluralistic Image Completion with Transformers
Image Inpainting via Conditional Texture and Structure Dual Generation
CR-Fill: Generative Image Inpainting with Auxiliary Contextual Reconstruction
FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Liu_FuseFormer_Fusing_Fine-Grained_Information_in_Transformers_for_Video_Inpainting_ICCV_2021_paper.html
- Code:https://github.com/ruiliu-ai/FuseFormer
<a name="6.图像超分辨率"></a>
6.图像超分辨率(Image Super-Resolution)
Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
Deep Blind Video Super-resolution
Omniscient Video Super-Resolution
Learning A Single Network for Scale-Arbitrary Super-Resolution
Deep Reparametrization of Multi-Frame Super-Resolution and Denoising
Lucas-Kanade Reloaded: End-to-End Super-Resolution from Raw Image Bursts
Attention-Based Multi-Reference Learning for Image Super-Resolution
Fourier Space Losses for Efficient Perceptual Image Super-Resolution
COMISR: Compression-Informed Video Super-Resolution
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Li_COMISR_Compression-Informed_Video_Super-Resolution_ICCV_2021_paper.html
- Code:https://github.com/google-research/google-research/tree/master/comisr
- 针对压缩后的视频超分
Designing a Practical Degradation Model for Deep Blind Image Super-Resolutio
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Zhang_Designing_a_Practical_Degradation_Model_for_Deep_Blind_Image_Super-Resolution_ICCV_2021_paper.html
- Code:https://github.com/cszn/BSRGAN
Event Stream Super-Resolution via Spatiotemporal Constraint Learning
Super-Resolving Cross-Domain Face Miniatures by Peeking at One-Shot Exemplar
Attention-based Multi-Reference Learning for Image Super-Resolution
- Paper:https://arxiv.org/abs/2108.13697
- Code:https://github.com/marcopesavento/Attention-based-Multi-Reference-Learning-for-Image-Super-Resolution
<a name="7.图像去雨"></a>
7.图像去雨(Image Deraining)
Structure-Preserving Deraining with Residue Channel Prior Guidance
Improving De-Raining Generalization via Neural Reorganization
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Xiao_Improving_De-Raining_Generalization_via_Neural_Reorganization_ICCV_2021_paper.html
- Code:https://github.com/cszn/BSRGAN
Unpaired Learning for Deep Image Deraining With Rain Direction Regularizer
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Liu_Unpaired_Learning_for_Deep_Image_Deraining_With_Rain_Direction_Regularizer_ICCV_2021_paper.html
- Code:https://github.com/cszn/BSRGAN
<a name="8.图像去雾"></a>
8.图像去雾(Image Dehazing)
<a name="9.去模糊"></a>
9.图像去模糊(Image Deblurring)
Bringing Events into Video Deblurring with Non consecutively Blurry Frames
Rethinking Coarse-to-Fine Approach in Single Image Deblurring
Single Image Defocus Deblurring Using Kernel-Sharing Parallel Atrous Convolutions
<a name="10.去噪"></a>
10.图像去噪(Image Denoising)
C2N: Practical Generative Noise Modeling for Real-World Denoising
Self-Supervised Image Prior Learning With GMM From a Single Noisy Image
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Liu_Self-Supervised_Image_Prior_Learning_With_GMM_From_a_Single_Noisy_ICCV_2021_paper.html
- Code:https://github.com/HUST-Tan/SS-GMM
<a name="11.图像恢复"></a>
11.图像恢复(Image Restoration)
Spatially-Adaptive Image Restoration using Distortion-Guided Networks
Dynamic Attentive Graph Learning for Image Restoration
<a name="12.图像增强"></a>
12.图像增强(Image Enhancement)
StarEnhancer: Learning Real-Time and Style-Aware Image Enhancement
Real-time Image Enhancer via Learnable Spatial-aware 3D Lookup Tables
Representative Color Transform for Image Enhancement
Adaptive Unfolding Total Variation Network for Low-Light Image Enhancement
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Zheng_Adaptive_Unfolding_Total_Variation_Network_for_Low-Light_Image_Enhancement_ICCV_2021_paper.html
- Code:https://github.com/YU-Zhiyang/WEVI
<a name="13.图像质量评价"></a>
13.图像质量评价(Image Quality Assessment)
MUSIQ: Multi-scale Image Quality Transformer
<a name="14.插帧"></a>
14.插帧(Frame Interpolation)
XVFI: eXtreme Video Frame Interpolation
Asymmetric Bilateral Motion Estimation for Video Frame Interpolation
Training Weakly Supervised Video Frame Interpolation With Events
<a name="15.视频压缩"></a>
15.视频/图像压缩(Video/Image Compression)
Extending Neural P-frame Codecs for B-frame Coding
Variable-Rate Deep Image Compression through Spatially-Adaptive Feature Transform
Efficient Video Compression via Content-Adaptive Super-Resolution
- Paper:https://openaccess.thecvf.com/content/ICCV2021/papers/Khani_Efficient_Video_Compression_via_Content-Adaptive_Super-Resolution_ICCV_2021_paper.pdf
- Code:https://github.com/AdaptiveVC/SRVC
<a name="16.其他底层视觉任务"></a>
16.其他底层视觉任务(Other Low Level Vision)
Overfitting the Data: Compact Neural Video Delivery via Content-aware Feature Modulation
Focal Frequency Loss for Image Reconstruction and Synthesis
- Paper:https://arxiv.org/abs/2012.12821
- Code:https://github.com/EndlessSora/focal-frequency-loss
- 频域损失,补充空域损失的不足
ALL Snow Removed: Single Image Desnowing Algorithm Using Hierarchical Dual-tree Complex Wavelet Representation and Contradict Channel Loss
IICNet: A Generic Framework for Reversible Image Conversion
Self-Conditioned Probabilistic Learning of Video Rescaling
HDR Video Reconstruction: A Coarse-to-fine Network and A Real-world Benchmark Dataset
A New Journey from SDRTV to HDRTV
SSH: A Self-Supervised Framework for Image Harmonization
Towards Vivid and Diverse Image Colorization with Generative Color Prior
Towards Flexible Blind JPEG Artifacts Removal
- Paper:https://github.com/jiaxi-jiang/FBCNN/releases/download/v1.0/FBCNN_ICCV2021.pdf
- Code:https://github.com/jiaxi-jiang/FBCNN
Location-Aware Single Image Reflection Removal
- Paper:https://openaccess.thecvf.com/content/ICCV2021/html/Dong_Location-Aware_Single_Image_Reflection_Removal_ICCV_2021_paper.html
- Code:https://github.com/zdlarr/Location-aware-SIRR