DarrenPan/Awesome-NeurIPS2022-Low-Level-Vision

A Collection of Papers and Codes in NeurIPS2022/2021 related to Low-Level Vision

Awesome-NeurIPS2022-Low-Level-Vision

A Collection of Papers and Codes in NeurIPS2022 related to Low-Level Vision

Related collections for low-level vision

• Awesome-NeurIPS2021-Low-Level-Vision
• Awesome-CVPR2023/2022-Low-Level-Vision
• Awesome-ECCV2022-Low-Level-Vision
• Awesome-AAAI2022-Low-Level-Vision
• Awesome-ICCV2021-Low-Level-Vision
• Awesome-CVPR2021/2020-Low-Level-Vision
• Awesome-ECCV2020-Low-Level-Vision

Catalogue

• Image Restoration

  • Video Restoration

• Super Resolution

  • Image Super Resolution
  • Video Super Resolution

• Denoising

  • Image Denoising

• Deraining

• Image Completion/Inpainting

• Image Compression

• Image Generation/Synthesis/ Image-to-Image Translation

  • Video Generation

Image Restoration - 图像恢复

Cross Aggregation Transformer for Image Restoration

• Paper: https://github.com/zhengchen1999/CAT
• Code: https://arxiv.org/abs/2211.13654

Stochastic Window Transformer for Image Restoration

• Paper: https://openreview.net/forum?id=0ucMtEKCihU
• Code: https://github.com/jiexiaou/Stoformer

Denoising Diffusion Restoration Models

• Paper: https://arxiv.org/abs/2201.11793
• Code: https://github.com/bahjat-kawar/ddrm
• Tags: Diffusion Model

Towards Robust Blind Face Restoration with Codebook Lookup Transformer

• Paper：https://arxiv.org/abs/2206.11253
• Code: https://github.com/sczhou/CodeFormer

Self-Supervised Image Restoration with Blurry and Noisy Pairs

• Paper: https://arxiv.org/abs/2211.07317
• Code: https://github.com/cszhilu1998/SelfIR

Deep Fourier Up-Sampling

• Paper: https://openreview.net/forum?id=NIrbtCdxfBl

Video Restoration

Recurrent Video Restoration Transformer with Guided Deformable Attention

• Paper: https://openreview.net/forum?id=GKfNB4BegL
• Code: https://github.com/JingyunLiang/RVRT

Super Resolution - 超分辨率

Image Super Resolution

ShuffleMixer: An Efficient ConvNet for Image Super-Resolution

• Paper: https://openreview.net/forum?id=ZK6lzx0jqdZ

Video Super Resolution

AnimeSR: Learning Real-World Super-Resolution Models for Animation Videos

• Paper: https://openreview.net/forum?id=4kjQZTNz-NH

Rethinking Alignment in Video Super-Resolution Transformers

• Paper: https://arxiv.org/abs/2207.08494
• Code: https://github.com/XPixelGroup/RethinkVSRAlignment

Denoising - 去噪

Image Denoising

Multi-Scale Adaptive Network for Single Image Denoising

• Paper: https://openreview.net/forum?id=HFm7AxNa9Wo
• Code: https://github.com/XLearning-SCU/2022-NeurIPS-MSANet

Deraining - 去雨

Generative Status Estimation and Information Decoupling for Image Rain Removal

• Paper: https://openreview.net/forum?id=C2o5DeL_8L1

Image Completion/Inpainting - 图像修复

Cross-Image Context for Single Image Inpainting

• Paper: https://openreview.net/forum?id=QfI_usBXNCM

Visual Prompting via Image Inpainting

• Paper: https://arxiv.org/abs/2209.00647
• Code: https://github.com/amirbar/visual_prompting

Improving Diffusion Models for Inverse Problems using Manifold Constraints

• Paper: https://arxiv.org/abs/2206.00941
• Code: https://github.com/HJ-harry/MCG_diffusion
• Tags: image inpainting, colorization, and sparse-view computed tomography

Image Compression - 图像压缩

Selective compression learning of latent representations for variable-rate image compression

• Paper: https://openreview.net/forum?id=xI5660uFUr

Multi-Sample Training for Neural Image Compression

• Paper: https://openreview.net/forum?id=wjSHd5nDeo

Flexible Neural Image Compression via Code Editing

• Paper: https://openreview.net/forum?id=uV_VYGB3FCi

VCT: A Video Compression Transformer

• Paper: https://arxiv.org/abs/2206.07307
• Code: https://github.com/google-research/google-research/tree/master/vct

Image Generation/Synthesis / Image-to-Image Translation - 图像生成/合成/转换

Text-to-Image / Text Guided / Multi-Modal

CogView2: Faster and Better Text-to-Image Generation via Hierarchical Transformers

• Paper: https://arxiv.org/abs/2204.14217
• Code: https://github.com/THUDM/CogView2

Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding

• Paper: https://openreview.net/forum?id=08Yk-n5l2Al

NUWA-Infinity: Autoregressive over Autoregressive Generation for Infinite Visual Synthesis

• Paper: https://arxiv.org/abs/2207.09814
• Code: https://github.com/microsoft/NUWA

Image-to-Image / Image Guided

QC-StyleGAN - Quality Controllable Image Generation and Manipulation

• Paper: https://openreview.net/forum?id=AWeZdGJ89lC

Unsupervised Image-to-Image Translation with Density Changing Regularization

• Paper: https://openreview.net/forum?id=RNZ8JOmNaV4
• Code: https://github.com/Mid-Push/Decent

EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations

• Paper: https://arxiv.org/abs/2207.06635
• Code: https://github.com/ML-GSAI/EGSDE

CHIMLE: Conditional Hierarchical IMLE for Multimodal Conditional Image Synthesis

• Paper: https://arxiv.org/abs/2211.14286
• Code: https://github.com/niopeng/CHIMLE/tree/main/code
• Tags: Colourization, SR, Decompression, Night-to-Day

Others for image generation

Draft-and-Revise: Effective Image Generation with Contextual RQ-Transformer

• Paper: https://openreview.net/forum?id=R5yl-ySZR0U

Few-shot Image Generation via Adaptation-Aware Kernel Modulation

• Paper: https://arxiv.org/abs/2210.16559
• Code: https://github.com/yunqing-me/AdAM

MoVQ: Modulating Quantized Vectors for High-Fidelity Image Generation

• Paper: https://openreview.net/forum?id=NYF6jNTAui

Locally Hierarchical Auto-Regressive Modeling for Image Generation

• Paper: https://openreview.net/forum?id=Qb-AoSw4Jnm

Improving GANs with A Dynamic Discriminator

• Paper: https://arxiv.org/abs/2209.09897
• Code: https://github.com/genforce/dynamicd

Instability and Local Minima in GAN Training with Kernel Discriminators

• Paper: https://openreview.net/forum?id=GyWsthkJ1E2

FreGAN: Exploiting Frequency Components for Training GANs under Limited Data

• Paper: https://openreview.net/forum?id=tWBMPooTayE
• Code: https://github.com/kobeshegu/FreGAN_NeurIPS2022

DigGAN: Discriminator gradIent Gap Regularization for GAN Training with Limited Data

• Paper: https://openreview.net/forum?id=azBVn74t_2
• Code: https://github.com/AilsaF/DigGAN

UniGAN: Reducing Mode Collapse in GANs using a Uniform Generator

• Paper: https://openreview.net/forum?id=IPcgkUgw3t1

Efficient Spatially Sparse Inference for Conditional GANs and Diffusion Models

• Paper: https://arxiv.org/abs/2211.02048
• Code: https://github.com/lmxyy/sige

HyperDomainNet: Universal Domain Adaptation for Generative Adversarial Networks

• Paper: https://arxiv.org/abs/2210.08884
• Code: https://github.com/MACderRu/HyperDomainNet

Information-Theoretic GAN Compression with Variational Energy-based Model

• Paper: https://openreview.net/forum?id=sRKNkpUMQNr

Masked Generative Adversarial Networks are Data-Efficient Generation Learners

• Paper: https://openreview.net/forum?id=js2ssA77fX

Improving Generative Adversarial Networks via Adversarial Learning in Latent Space

• Paper: https://openreview.net/forum?id=Magl9CSHB87

MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators

• Paper: https://openreview.net/forum?id=CQaqJDWUGJ

Diffusion models as plug-and-play priors

• Paper: https://arxiv.org/abs/2206.09012
• Code: https://github.com/AlexGraikos/diffusion_priors

On Analyzing Generative and Denoising Capabilities of Diffusion-based Deep Generative Models

• Paper: https://openreview.net/forum?id=nxl-IjnDCRo

Maximum Likelihood Training of Implicit Nonlinear Diffusion Model

• Paper: https://arxiv.org/abs/2205.13699
• Code: https://github.com/byeonghu-na/INDM

Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models

• Paper: https://arxiv.org/abs/2212.12990
• Code: https://github.com/ckczzj/PDAE

Deep Equilibrium Approaches to Diffusion Models

• Paper: https://arxiv.org/abs/2210.12867
• Code: https://github.com/locuslab/deq-ddim

Retrieval-Augmented Diffusion Models

• Paper: https://openreview.net/forum?id=Bqk9c0wBNrZ
• Code: https://github.com/CompVis/retrieval-augmented-diffusion-models

DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps

• Paper: https://github.com/LuChengTHU/dpm-solver
• Code: https://arxiv.org/abs/2206.00927

GENIE: Higher-Order Denoising Diffusion Solvers

• Paper: https://arxiv.org/abs/2210.05475
• Code: https://github.com/nv-tlabs/GENIE

Elucidating the Design Space of Diffusion-Based Generative Models

• Paper: https://arxiv.org/abs/2206.00364
• Code: https://github.com/NVlabs/edm

Wavelet Score-Based Generative Modeling

• Paper: https://openreview.net/forum?id=xZmjH3Pm2BK

Poisson Flow Generative Models

• Paper: https://arxiv.org/abs/2209.11178
• Code: https://github.com/Newbeeer/Poisson_flow

Invertible Monotone Operators for Normalizing Flows

• Paper: https://arxiv.org/abs/2210.08176
• Code: https://github.com/mlvlab/MonotoneFlows

Flowification: Everything is a normalizing flow

• Paper: https://openreview.net/forum?id=-jnE7sxuMm

Video Generation

MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation

• Paper: https://arxiv.org/abs/2205.09853
• Code: https://github.com/voletiv/mcvd-pytorch

Video Diffusion Models

• Paper: https://openreview.net/forum?id=f3zNgKga_ep

Flexible Diffusion Modeling of Long Videos

• Paper: https://openreview.net/forum?id=0RTJcuvHtIu

Audio-Driven Co-Speech Gesture Video Generation

• Paper: https://arxiv.org/abs/2212.02350
• Code: https://github.com/alvinliu0/ANGIE

Generating Long Videos of Dynamic Scenes

• Paper: https://arxiv.org/abs/2206.03429
• Code: https://github.com/NVlabs/long-video-gan

Others

Conditional Diffusion Process for Inverse Halftoning

• Paper: https://openreview.net/forum?id=EEcFW47sktI
• Tags: Inverse halftoning