{"list":"other","total":206,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1606.03498","title":"Improved Techniques for Training GANs","created":"2016-06-10","cited_by_count":2970},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1505.05770","title":"Variational Inference with Normalizing Flows","created":"2015-05-21","cited_by_count":2170},{"id":"1411.1784","title":"Conditional Generative Adversarial Nets","created":"2014-11-06","cited_by_count":2162},{"id":"1605.08803","title":"Density estimation using Real NVP","created":"2016-05-27","cited_by_count":2042},{"id":"2206.00927","title":"DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Steps","created":"2022-06-02","cited_by_count":1979},{"id":"1609.04802","title":"Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network","created":"2016-09-15","cited_by_count":1908},{"id":"1807.03039","title":"Glow: Generative Flow with Invertible 1x1 Convolutions","created":"2018-07-09","cited_by_count":1545},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1809.00219","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","created":"2018-09-01","cited_by_count":1254},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"2010.05646","title":"HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis","created":"2020-10-12","cited_by_count":1154},{"id":"2107.00630","title":"Variational Diffusion Models","created":"2021-07-01","cited_by_count":1153},{"id":"2209.04747","title":"Diffusion Models in Vision: A Survey","created":"2022-09-10","cited_by_count":1015},{"id":"2209.15571","title":"Building Normalizing Flows with Stochastic Interpolants","created":"2022-09-30","cited_by_count":995},{"id":"2201.11793","title":"Denoising Diffusion Restoration Models","created":"2022-01-27","cited_by_count":963},{"id":"1802.01436","title":"Variational image compression with a scale hyperprior","created":"2018-02-01","cited_by_count":935},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"2103.13630","title":"A Survey of Quantization Methods for Efficient Neural Network Inference","created":"2021-03-25","cited_by_count":815},{"id":"1611.01704","title":"End-to-end Optimized Image Compression","created":"2016-11-05","cited_by_count":696},{"id":"1809.02736","title":"Joint Autoregressive and Hierarchical Priors for Learned Image Compression","created":"2018-09-08","cited_by_count":664},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1810.01367","title":"FFJORD: Free-form Continuous Dynamics for Scalable Reversible Generative Models","created":"2018-10-02","cited_by_count":594},{"id":"2001.01568","title":"Learned Image Compression with Discretized Gaussian Mixture Likelihoods and Attention Modules","created":"2020-01-06","cited_by_count":590},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"1701.04862","title":"Towards Principled Methods for Training Generative Adversarial Networks","created":"2017-01-17","cited_by_count":464},{"id":"1509.00519","title":"Importance Weighted Autoencoders","created":"2015-09-01","cited_by_count":456},{"id":"2104.14951","title":"SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models","created":"2021-04-30","cited_by_count":415},{"id":"2005.09635","title":"InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANs","created":"2020-05-18","cited_by_count":394},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"2006.09965","title":"High-Fidelity Generative Image Compression","created":"2020-06-17","cited_by_count":338},{"id":"1812.00101","title":"DVC: An End-to-end Deep Video Compression Framework","created":"2018-11-30","cited_by_count":332},{"id":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2203.10886","title":"ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding","created":"2022-03-21","cited_by_count":301},{"id":"1808.00948","title":"Diverse Image-to-Image Translation via Disentangled Representations","created":"2018-08-02","cited_by_count":296},{"id":"2007.08739","title":"Channel-wise Autoregressive Entropy Models for Learned Image Compression","created":"2020-07-17","cited_by_count":264},{"id":"2011.10650","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","created":"2020-11-20","cited_by_count":264},{"id":"1906.02735","title":"Residual Flows for Invertible Generative Modeling","created":"2019-06-06","cited_by_count":257},{"id":"2303.09472","title":"DiffIR: Efficient Diffusion Model for Image Restoration","created":"2023-03-16","cited_by_count":255},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"2103.04922","title":"Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Models","created":"2021-03-08","cited_by_count":252},{"id":"2203.09481","title":"Diffusion Probabilistic Modeling for Video Generation","created":"2022-03-16","cited_by_count":238},{"id":"1903.10082","title":"Residual Non-local Attention Networks for Image Restoration","created":"2019-03-24","cited_by_count":236},{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233},{"id":"2109.15047","title":"Deep Contextual Video Compression","created":"2021-09-30","cited_by_count":221},{"id":"1804.02958","title":"Generative Adversarial Networks for Extreme Learned Image Compression","created":"2018-04-09","cited_by_count":219},{"id":"2303.16491","title":"Implicit Diffusion Models for Continuous Super-Resolution","created":"2023-03-29","cited_by_count":218},{"id":"2207.14626","title":"Restoring Vision in Adverse Weather Conditions with Patch-Based Denoising Diffusion Models","created":"2022-07-29","cited_by_count":215},{"id":"1901.07821","title":"Rethinking Lossy Compression: The Rate-Distortion-Perception Tradeoff","created":"2019-01-23","cited_by_count":211},{"id":"2303.14978","title":"Learned Image Compression with Mixed Transformer-CNN Architectures","created":"2023-03-27","cited_by_count":211},{"id":"2110.02037","title":"Autoregressive Diffusion Models","created":"2021-10-05","cited_by_count":210},{"id":"1702.02463","title":"Video Frame Synthesis using Deep Voxel Flow","created":"2017-02-08","cited_by_count":209},{"id":"1701.05957","title":"Image De-raining Using a Conditional Generative Adversarial Network","created":"2017-01-21","cited_by_count":197},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170},{"id":"2302.14402","title":"Neural Video Compression with Diverse Contexts","created":"2023-02-28","cited_by_count":165},{"id":"2112.04267","title":"Implicit Neural Representations for Image Compression","created":"2021-12-08","cited_by_count":162},{"id":"1803.10967","title":"Context-aware Synthesis for Video Frame Interpolation","created":"2018-03-29","cited_by_count":153},{"id":"2105.09600","title":"FVC: A New Framework towards Deep Video Compression in Feature Space","created":"2021-05-20","cited_by_count":153},{"id":"1704.00648","title":"Soft-to-Hard Vector Quantization for End-to-End Learning Compressible Representations","created":"2017-04-03","cited_by_count":152},{"id":"1804.06919","title":"Video Compression through Image Interpolation","created":"2018-04-18","cited_by_count":143},{"id":"1801.03558","title":"Inference Suboptimality in Variational Autoencoders","created":"2018-01-10","cited_by_count":132},{"id":"2207.00050","title":"Semantic Image Synthesis via Diffusion Models","created":"2022-06-30","cited_by_count":132},{"id":"2012.04781","title":"You Only Need Adversarial Supervision for Semantic Image Synthesis","created":"2020-12-08","cited_by_count":129},{"id":"2207.05894","title":"Hybrid Spatial-Temporal Entropy Modelling for Neural Video Compression","created":"2022-07-13","cited_by_count":128},{"id":"2103.16206","title":"XVFI: eXtreme Video Frame Interpolation","created":"2021-03-30","cited_by_count":126},{"id":"2007.12622","title":"BMBC:Bilateral Motion Estimation with Bilateral Cost Volume for Video Interpolation","created":"2020-07-17","cited_by_count":118},{"id":"2305.09515","title":"AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation","created":"2023-05-16","cited_by_count":118},{"id":"2111.13850","title":"Temporal Context Mining for Learned Video Compression","created":"2021-11-27","cited_by_count":117},{"id":"2101.08629","title":"Image-to-Image Translation: Methods and Applications","created":"2021-01-21","cited_by_count":116},{"id":"1909.04802","title":"Variable Rate Deep Image Compression With a Conditional Autoencoder","created":"2019-09-11","cited_by_count":114},{"id":"2205.14620","title":"IFRNet: Intermediate Feature Refine Network for Efficient Frame Interpolation","created":"2022-05-29","cited_by_count":109},{"id":"2308.09388","title":"Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey","created":"2023-08-18","cited_by_count":109},{"id":"2004.10290","title":"M-LVC: Multiple Frames Prediction for Learned Video Compression","created":"2020-04-21","cited_by_count":107},{"id":"2108.03690","title":"Enhanced Invertible Encoding for Learned Image Compression","created":"2021-08-08","cited_by_count":105},{"id":"1908.05717","title":"Video Compression With Rate-Distortion Autoencoders","created":"2019-08-14","cited_by_count":97},{"id":"2003.01966","title":"Learning for Video Compression with Hierarchical Quality and Recurrent Enhancement","created":"2020-03-04","cited_by_count":90},{"id":"2206.08889","title":"Lossy Compression with Gaussian Diffusion","created":"2022-06-17","cited_by_count":90},{"id":"1811.06981","title":"Learned Video Compression","created":"2018-11-16","cited_by_count":89}],"next_cursor":"100"}