{"list":"other","total":63,"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":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"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":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2008.00951","title":"Encoding in Style: a StyleGAN Encoder for Image-to-Image Translation","created":"2020-08-03","cited_by_count":727},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642},{"id":"2211.13227","title":"Paint by Example: Exemplar-based Image Editing with Diffusion Models","created":"2022-11-23","cited_by_count":489},{"id":"2305.14720","title":"BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing","created":"2023-05-24","cited_by_count":442},{"id":"2206.02779","title":"Blended Latent Diffusion","created":"2022-06-06","cited_by_count":432},{"id":"2307.09481","title":"AnyDoor: Zero-shot Object-level Image Customization","created":"2023-07-18","cited_by_count":412},{"id":"2304.03411","title":"InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning","created":"2023-04-06","cited_by_count":345},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337},{"id":"2212.05034","title":"SmartBrush: Text and Shape Guided Object Inpainting with Diffusion Model","created":"2022-12-09","cited_by_count":278},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212},{"id":"2304.00186","title":"Subject-driven Text-to-Image Generation via Apprenticeship Learning","created":"2023-04-01","cited_by_count":212},{"id":"2111.15666","title":"HyperStyle: StyleGAN Inversion with HyperNetworks for Real Image Editing","created":"2021-11-30","cited_by_count":208},{"id":"2307.12493","title":"TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition","created":"2023-07-24","cited_by_count":182},{"id":"2005.07727","title":"Semantic Photo Manipulation with a Generative Image Prior","created":"2020-05-15","cited_by_count":178},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160},{"id":"2111.03186","title":"EditGAN: High-Precision Semantic Image Editing","created":"2021-11-04","cited_by_count":156},{"id":"1703.03872","title":"Deep Image Matting","created":"2017-03-10","cited_by_count":150},{"id":"2003.05863","title":"Towards Photo-Realistic Virtual Try-On by Adaptively Generating$\\leftrightarrow$Preserving Image Content","created":"2020-03-12","cited_by_count":149},{"id":"2304.02642","title":"Taming Encoder for Zero Fine-tuning Image Customization with Text-to-Image Diffusion Models","created":"2023-04-05","cited_by_count":117},{"id":"1807.07428","title":"Modeling Visual Context is Key to Augmenting Object Detection Datasets","created":"2018-07-19","cited_by_count":106},{"id":"1908.07801","title":"InstaBoost: Boosting Instance Segmentation via Probability Map Guided Copy-Pasting","created":"2019-08-21","cited_by_count":95},{"id":"1803.01837","title":"ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing","created":"2018-03-05","cited_by_count":90},{"id":"1912.11565","title":"Rendering Synthetic Objects into Legacy Photographs","created":"2019-12-24","cited_by_count":72},{"id":"1812.05840","title":"Spatial Fusion GAN for Image Synthesis","created":"2018-12-14","cited_by_count":68},{"id":"2403.10701","title":"IMPRINT: Generative Object Compositing by Learning Identity-Preserving Representation","created":"2024-03-15","cited_by_count":64},{"id":"1905.10346","title":"Mask-Guided Portrait Editing with Conditional GANs","created":"2019-05-24","cited_by_count":61},{"id":"2304.14406","title":"Putting People in Their Place: Affordance-Aware Human Insertion into Scenes","created":"2023-04-27","cited_by_count":53},{"id":"1904.05475","title":"Learning to Generate Synthetic Data via Compositing","created":"2019-04-10","cited_by_count":52},{"id":"2203.11947","title":"CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training","created":"2022-03-22","cited_by_count":49},{"id":"1811.10515","title":"Deep Network Interpolation for Continuous Imagery Effect Transition","created":"2018-11-26","cited_by_count":47},{"id":"2207.04788","title":"DCCF: Deep Comprehensible Color Filter Learning Framework for High-Resolution Image Harmonization","created":"2022-07-11","cited_by_count":46},{"id":"2308.10040","title":"ControlCom: Controllable Image Composition using Diffusion Model","created":"2023-08-19","cited_by_count":43},{"id":"1803.06414","title":"Learning to Segment via Cut-and-Paste","created":"2018-03-16","cited_by_count":42},{"id":"1812.02350","title":"Context-Aware Synthesis and Placement of Object Instances","created":"2018-12-06","cited_by_count":41},{"id":"2306.12624","title":"DreamEdit: Subject-driven Image Editing","created":"2023-06-22","cited_by_count":37},{"id":"2212.00932","title":"ObjectStitch: Generative Object Compositing","created":"2022-12-02","cited_by_count":36},{"id":"2107.01889","title":"OPA: Object Placement Assessment Dataset","created":"2021-07-05","cited_by_count":28},{"id":"2310.19784","title":"CustomNet: Zero-shot Object Customization with Variable-Viewpoints in Text-to-Image Diffusion Models","created":"2023-10-30","cited_by_count":25},{"id":"2207.04614","title":"Instance Shadow Detection with A Single-Stage Detector","created":"2022-07-11","cited_by_count":22},{"id":"1706.01021","title":"Where and Who? Automatic Semantic-Aware Person Composition","created":"2017-06-04","cited_by_count":21},{"id":"2306.07596","title":"Paste, Inpaint and Harmonize via Denoising: Subject-Driven Image Editing with Pre-Trained Diffusion Model","created":"2023-06-13","cited_by_count":21},{"id":"2207.11464","title":"Learning Object Placement via Dual-path Graph Completion","created":"2022-07-23","cited_by_count":20},{"id":"1809.02492","title":"On the Importance of Visual Context for Data Augmentation in Scene Understanding","created":"2018-09-06","cited_by_count":19},{"id":"2304.09748","title":"Reference-based Image Composition with Sketch via Structure-aware Diffusion Model","created":"2023-03-31","cited_by_count":17},{"id":"2309.15508","title":"DreamCom: Finetuning Text-guided Inpainting Model for Image Composition","created":"2023-09-27","cited_by_count":17},{"id":"2304.03372","title":"TopNet: Transformer-based Object Placement Network for Image Compositing","created":"2023-04-06","cited_by_count":16},{"id":"1811.09783","title":"What and Where: A Context-based Recommendation System for Object Insertion","created":"2018-11-24","cited_by_count":14},{"id":"2205.14280","title":"Fast Object Placement Assessment","created":"2022-05-28","cited_by_count":12},{"id":"2401.13795","title":"Diffuse to Choose: Enriching Image Conditioned Inpainting in Latent Diffusion Models for Virtual Try-All","created":"2024-01-24","cited_by_count":11}],"next_cursor":null}