{"list":"other","total":67,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1703.06870","title":"Mask R-CNN","created":"2017-03-20","cited_by_count":7277},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"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":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"id":"1711.11585","title":"High-Resolution Image Synthesis and Semantic Manipulation with Conditional GANs","created":"2017-11-30","cited_by_count":1179},{"id":"2112.03857","title":"Grounded Language-Image Pre-training","created":"2021-12-07","cited_by_count":1156},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"1612.03716","title":"COCO-Stuff: Thing and Stuff Classes in Context","created":"2016-12-12","cited_by_count":864},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"2111.14822","title":"Vector Quantized Diffusion Model for Text-to-Image Synthesis","created":"2021-11-29","cited_by_count":774},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"2202.09778","title":"Pseudo Numerical Methods for Diffusion Models on Manifolds","created":"2022-02-20","cited_by_count":700},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1612.03242","title":"StackGAN: Text to Photo-realistic Image Synthesis with Stacked Generative Adversarial Networks","created":"2016-12-10","cited_by_count":577},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"1911.12861","title":"SEAN: Image Synthesis with Semantic Region-Adaptive Normalization","created":"2019-11-28","cited_by_count":253},{"id":"2111.12417","title":"N\\\"UWA: Visual Synthesis Pre-training for Neural visUal World creAtion","created":"2021-11-24","cited_by_count":253},{"id":"1707.09405","title":"Photographic Image Synthesis with Cascaded Refinement Networks","created":"2017-07-28","cited_by_count":223},{"id":"2008.05865","title":"DF-GAN: A Simple and Effective Baseline for Text-to-Image Synthesis","created":"2020-08-13","cited_by_count":162},{"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":"1902.10740","title":"Object-driven Text-to-Image Synthesis via Adversarial Training","created":"2019-02-27","cited_by_count":117},{"id":"1610.02454","title":"Learning What and Where to Draw","created":"2016-10-08","cited_by_count":105},{"id":"1811.11389","title":"Image Generation from Layout","created":"2018-11-28","cited_by_count":105},{"id":"1801.05091","title":"Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis","created":"2018-01-16","cited_by_count":101},{"id":"1908.07500","title":"Image Synthesis From Reconfigurable Layout and Style","created":"2019-08-20","cited_by_count":85},{"id":"2007.10379","title":"Generative Hierarchical Features from Synthesizing Images","created":"2020-07-20","cited_by_count":83},{"id":"1909.05379","title":"Specifying Object Attributes and Relations in Interactive Scene Generation","created":"2019-09-11","cited_by_count":76},{"id":"2112.05130","title":"Multimodal Conditional Image Synthesis with Product-of-Experts GANs","created":"2021-12-09","cited_by_count":75},{"id":"2012.04644","title":"Efficient Semantic Image Synthesis via Class-Adaptive Normalization","created":"2020-12-08","cited_by_count":58},{"id":"2003.07449","title":"Object-Centric Image Generation from Layouts","created":"2020-03-16","cited_by_count":57},{"id":"2104.00567","title":"Text to Image Generation with Semantic-Spatial Aware GAN","created":"2021-04-01","cited_by_count":53},{"id":"2003.11571","title":"Learning Layout and Style Reconfigurable GANs for Controllable Image Synthesis","created":"2020-03-25","cited_by_count":49},{"id":"1901.00686","title":"Generating Multiple Objects at Spatially Distinct Locations","created":"2019-01-03","cited_by_count":41},{"id":"2103.11897","title":"Context-Aware Layout to Image Generation with Enhanced Object Appearance","created":"2021-03-22","cited_by_count":41},{"id":"2003.06221","title":"Semantic Pyramid for Image Generation","created":"2020-03-13","cited_by_count":34},{"id":"2003.11690","title":"BachGAN: High-Resolution Image Synthesis from Salient Object Layout","created":"2020-03-26","cited_by_count":22},{"id":"2203.02104","title":"Interactive Image Synthesis with Panoptic Layout Generation","created":"2022-03-04","cited_by_count":17},{"id":"2203.16898","title":"Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis","created":"2022-03-31","cited_by_count":16},{"id":"1912.03161","title":"Controlling Style and Semantics in Weakly-Supervised Image Generation","created":"2019-12-06","cited_by_count":11},{"id":"2002.05235","title":"Image-to-Image Translation with Text Guidance","created":"2020-02-12","cited_by_count":10},{"id":"2008.11932","title":"Attribute-guided image generation from layout","created":"2020-08-27","cited_by_count":10},{"id":"2107.04240","title":"Deep Image Synthesis from Intuitive User Input: A Review and Perspectives","created":"2021-07-09","cited_by_count":8},{"id":"2204.02035","title":"DT2I: Dense Text-to-Image Generation from Region Descriptions","created":"2022-04-05","cited_by_count":4}],"next_cursor":null}