{"list":"other","total":64,"rows":[{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"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":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"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":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"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":"1703.06868","title":"Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization","created":"2017-03-20","cited_by_count":2010},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"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":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2102.02766","title":"Designing an Encoder for StyleGAN Image Manipulation","created":"2021-02-04","cited_by_count":544},{"id":"2302.03027","title":"Zero-shot Image-to-Image Translation","created":"2023-02-06","cited_by_count":505},{"id":"2112.03126","title":"Label-Efficient Semantic Segmentation with Diffusion Models","created":"2021-12-06","cited_by_count":499},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2303.11331","title":"EVA-02: A Visual Representation for Neon Genesis","created":"2023-03-20","cited_by_count":381},{"id":"1705.08086","title":"Universal Style Transfer via Feature Transforms","created":"2017-05-23","cited_by_count":354},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"1708.06500","title":"Sparsity Invariant CNNs","created":"2017-08-22","cited_by_count":326},{"id":"2212.02499","title":"Images Speak in Images: A Generalist Painter for In-Context Visual Learning","created":"2022-12-05","cited_by_count":318},{"id":"1711.11586","title":"Toward Multimodal Image-to-Image Translation","created":"2017-11-30","cited_by_count":296},{"id":"1808.00948","title":"Diverse Image-to-Image Translation via Disentangled Representations","created":"2018-08-02","cited_by_count":296},{"id":"2306.14435","title":"DragDiffusion: Harnessing Diffusion Models for Interactive Point-based Image Editing","created":"2023-06-26","cited_by_count":294},{"id":"2211.13203","title":"Inversion-Based Style Transfer with Diffusion Models","created":"2022-11-23","cited_by_count":291},{"id":"2309.15807","title":"Emu: Enhancing Image Generation Models Using Photogenic Needles in a Haystack","created":"2023-09-27","cited_by_count":279},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"1905.01270","title":"DRIT++: Diverse Image-to-Image Translation via Disentangled Representations","created":"2019-05-02","cited_by_count":244},{"id":"1907.02544","title":"Large Scale Adversarial Representation Learning","created":"2019-07-04","cited_by_count":239},{"id":"2203.08382","title":"Dual Diffusion Implicit Bridges for Image-to-Image Translation","created":"2022-03-16","cited_by_count":213},{"id":"2004.04727","title":"3D Photography using Context-aware Layered Depth Inpainting","created":"2020-04-09","cited_by_count":206},{"id":"1903.05628","title":"Mode Seeking Generative Adversarial Networks for Diverse Image Synthesis","created":"2019-03-13","cited_by_count":138},{"id":"2308.12469","title":"Diffuse, Attend, and Segment: Unsupervised Zero-Shot Segmentation using Stable Diffusion","created":"2023-08-23","cited_by_count":131},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"2305.01115","title":"In-Context Learning Unlocked for Diffusion Models","created":"2023-05-01","cited_by_count":104},{"id":"2103.04379","title":"Repurposing GANs for One-shot Semantic Part Segmentation","created":"2021-03-07","cited_by_count":88},{"id":"2007.10379","title":"Generative Hierarchical Features from Synthesizing Images","created":"2020-07-20","cited_by_count":83},{"id":"2211.13319","title":"Make-A-Story: Visual Memory Conditioned Consistent Story Generation","created":"2022-11-23","cited_by_count":76},{"id":"1704.04131","title":"Neural Face Editing with Intrinsic Image Disentangling","created":"2017-04-13","cited_by_count":70},{"id":"2306.00987","title":"StyleGAN knows Normal, Depth, Albedo, and More","created":"2023-06-01","cited_by_count":44},{"id":"2208.12675","title":"Adaptively-Realistic Image Generation from Stroke and Sketch with Diffusion Model","created":"2022-08-26","cited_by_count":39},{"id":"2307.02138","title":"Prompting Diffusion Representations for Cross-Domain Semantic Segmentation","created":"2023-07-05","cited_by_count":30},{"id":"2203.16670","title":"PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition","created":"2022-03-30","cited_by_count":26},{"id":"2307.14331","title":"Visual Instruction Inversion: Image Editing via Visual Prompting","created":"2023-07-26","cited_by_count":26},{"id":"2104.00487","title":"Linear Semantics in Generative Adversarial Networks","created":"2021-04-01","cited_by_count":25},{"id":"2207.00757","title":"PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes","created":"2022-07-02","cited_by_count":22},{"id":"2307.03190","title":"Text-Guided Synthesis of Eulerian Cinemagraphs","created":"2023-07-06","cited_by_count":22},{"id":"2207.13286","title":"Vector Quantized Image-to-Image Translation","created":"2022-07-27","cited_by_count":16}],"next_cursor":null}