{"total":223,"rows":[{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937,"area":null},{"id":"2110.02711","title":"DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation","created":"2021-10-06","cited_by_count":642,"area":"diffusion"},{"id":"2302.10174","title":"Towards Universal Fake Image Detectors that Generalize Across Generative Models","created":"2023-02-20","cited_by_count":490,"area":null},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349,"area":null},{"id":"2305.14334","title":"Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence","created":"2023-05-23","cited_by_count":214,"area":"diffusion"},{"id":"2111.12710","title":"PeCo: Perceptual Codebook for BERT Pre-training of Vision Transformers","created":"2021-11-24","cited_by_count":204,"area":null},{"id":"2210.06998","title":"DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models","created":"2022-10-13","cited_by_count":168,"area":"diffusion"},{"id":"2308.12964","title":"Dense Text-to-Image Generation with Attention Modulation","created":"2023-08-24","cited_by_count":163,"area":"diffusion"},{"id":"2404.12385","title":"MeshLRM: Large Reconstruction Model for High-Quality Meshes","created":"2024-04-18","cited_by_count":139,"area":null},{"id":"2104.05358","title":"UNIT-DDPM: UNpaired Image Translation with Denoising Diffusion Probabilistic Models","created":"2021-04-12","cited_by_count":133,"area":"diffusion"},{"id":"2207.00050","title":"Semantic Image Synthesis via Diffusion Models","created":"2022-06-30","cited_by_count":132,"area":"diffusion"},{"id":"2110.12951","title":"Seeing biodiversity: perspectives in machine learning for wildlife conservation","created":"2021-10-25","cited_by_count":130,"area":null},{"id":"2204.08906","title":"Photorealistic Monocular 3D Reconstruction of Humans Wearing Clothing","created":"2022-04-19","cited_by_count":126,"area":null},{"id":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122,"area":null},{"id":"2109.05070","title":"Instance-Conditioned GAN","created":"2021-09-10","cited_by_count":121,"area":null},{"id":"2408.09647","title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection","created":"2024-08-19","cited_by_count":113,"area":null},{"id":"2105.04932","title":"One Shot Face Swapping on Megapixels","created":"2021-05-11","cited_by_count":105,"area":null},{"id":"2411.15633","title":"Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection","created":"2024-11-23","cited_by_count":105,"area":null},{"id":"2106.06819","title":"D2C: Diffusion-Denoising Models for Few-shot Conditional Generation","created":"2021-06-12","cited_by_count":96,"area":null},{"id":"2402.19091","title":"Leveraging Representations from Intermediate Encoder-blocks for Synthetic Image Detection","created":"2024-02-29","cited_by_count":89,"area":null},{"id":"2203.13964","title":"Fusing Global and Local Features for Generalized AI-Synthesized Image Detection","created":"2022-03-26","cited_by_count":88,"area":null},{"id":"2112.09130","title":"Ensembling Off-the-shelf Models for GAN Training","created":"2021-12-16","cited_by_count":86,"area":null},{"id":"2203.12691","title":"Learning to generate line drawings that convey geometry and semantics","created":"2022-03-23","cited_by_count":83,"area":null},{"id":"2108.05892","title":"PixelSynth: Generating a 3D-Consistent Experience from a Single Image","created":"2021-08-12","cited_by_count":82,"area":null},{"id":"2101.06543","title":"GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving","created":"2021-01-16","cited_by_count":75,"area":null},{"id":"2105.04619","title":"Enhancing Photorealism Enhancement","created":"2021-05-10","cited_by_count":74,"area":null},{"id":"2404.00815","title":"Towards Realistic Scene Generation with LiDAR Diffusion Models","created":"2024-03-31","cited_by_count":69,"area":"wm"},{"id":"2103.17195","title":"A Closer Look at Fourier Spectrum Discrepancies for CNN-generated Images Detection","created":"2021-03-31","cited_by_count":68,"area":null},{"id":"2303.14412","title":"Freestyle Layout-to-Image Synthesis","created":"2023-03-25","cited_by_count":67,"area":"diffusion"},{"id":"2104.00854","title":"The Spatially-Correlative Loss for Various Image Translation Tasks","created":"2021-04-02","cited_by_count":66,"area":null},{"id":"2104.07689","title":"Dual Contrastive Learning for Unsupervised Image-to-Image Translation","created":"2021-04-15","cited_by_count":66,"area":null},{"id":"2211.15662","title":"High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization","created":"2022-11-28","cited_by_count":65,"area":null},{"id":"2103.01456","title":"Image-to-image Translation via Hierarchical Style Disentanglement","created":"2021-03-02","cited_by_count":63,"area":null},{"id":"2205.11733","title":"Single-View View Synthesis in the Wild with Learned Adaptive Multiplane Images","created":"2022-05-24","cited_by_count":59,"area":null},{"id":"2112.02236","title":"SemanticStyleGAN: Learning Compositional Generative Priors for Controllable Image Synthesis and Editing","created":"2021-12-04","cited_by_count":58,"area":null},{"id":"2103.00218","title":"Countering Malicious DeepFakes: Survey, Battleground, and Horizon","created":"2021-02-27","cited_by_count":56,"area":null},{"id":"2109.06671","title":"High-Resolution Image Harmonization via Collaborative Dual Transformations","created":"2021-09-14","cited_by_count":55,"area":null},{"id":"2203.09457","title":"Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image","created":"2022-03-17","cited_by_count":55,"area":null},{"id":"2101.09983","title":"Adversarial Text-to-Image Synthesis: A Review","created":"2021-01-25","cited_by_count":52,"area":null},{"id":"2112.13592","title":"Multimodal Image Synthesis and Editing: The Generative AI Era","created":"2021-12-27","cited_by_count":52,"area":null},{"id":"2211.12131","title":"DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models","created":"2022-11-22","cited_by_count":51,"area":"wm"},{"id":"2406.09398","title":"Real-Time Deepfake Detection in the Real-World","created":"2024-06-13","cited_by_count":51,"area":null},{"id":"2411.04125","title":"Community Forensics: Using Thousands of Generators to Train Fake Image Detectors","created":"2024-11-06","cited_by_count":50,"area":null},{"id":"2103.06878","title":"Diverse Semantic Image Synthesis via Probability Distribution Modeling","created":"2021-03-11","cited_by_count":49,"area":null},{"id":"2207.12280","title":"ArtFID: Quantitative Evaluation of Neural Style Transfer","created":"2022-07-25","cited_by_count":49,"area":null},{"id":"2305.13800","title":"Generalizable Synthetic Image Detection via Language-guided Contrastive Learning","created":"2023-05-23","cited_by_count":49,"area":"diffusion"},{"id":"2304.12205","title":"Synthetic Datasets for Autonomous Driving: A Survey","created":"2023-04-24","cited_by_count":48,"area":null},{"id":"2108.04547","title":"Instance-wise Hard Negative Example Generation for Contrastive Learning in Unpaired Image-to-Image Translation","created":"2021-08-10","cited_by_count":45,"area":null},{"id":"2109.07053","title":"Image Synthesis via Semantic Composition","created":"2021-09-15","cited_by_count":45,"area":null},{"id":"2205.05467","title":"A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials","created":"2022-05-11","cited_by_count":45,"area":null},{"id":"2404.04584","title":"D$^3$: Scaling Up Deepfake Detection by Learning from Discrepancy","created":"2024-04-06","cited_by_count":45,"area":null},{"id":"2211.11742","title":"SceneComposer: Any-Level Semantic Image Synthesis","created":"2022-11-21","cited_by_count":43,"area":null},{"id":"2304.14573","title":"SceneGenie: Scene Graph Guided Diffusion Models for Image Synthesis","created":"2023-04-28","cited_by_count":41,"area":"diffusion"},{"id":"2203.08483","title":"QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation","created":"2022-03-16","cited_by_count":39,"area":null},{"id":"2211.03456","title":"A Unified Pyramid Recurrent Network for Video Frame Interpolation","created":"2022-11-07","cited_by_count":39,"area":null},{"id":"2104.08277","title":"Divide-and-Conquer for Lane-Aware Diverse Trajectory Prediction","created":"2021-04-16","cited_by_count":37,"area":null},{"id":"2201.10494","title":"What's Wrong with Deep Learning in Tree Search for Combinatorial Optimization","created":"2022-01-25","cited_by_count":37,"area":null},{"id":"2104.06397","title":"Shape and Material Capture at Home","created":"2021-04-13","cited_by_count":36,"area":null},{"id":"2105.14211","title":"M6-UFC: Unifying Multi-Modal Controls for Conditional Image Synthesis via Non-Autoregressive Generative Transformers","created":"2021-05-29","cited_by_count":36,"area":null},{"id":"2312.08880","title":"GenDet: Towards Good Generalizations for AI-Generated Image Detection","created":"2023-12-12","cited_by_count":36,"area":null},{"id":"2205.02837","title":"BlobGAN: Spatially Disentangled Scene Representations","created":"2022-05-05","cited_by_count":35,"area":null},{"id":"2203.04946","title":"Do better ImageNet classifiers assess perceptual similarity better?","created":"2022-03-09","cited_by_count":34,"area":null},{"id":"2209.01749","title":"4D LUT: Learnable Context-Aware 4D Lookup Table for Image Enhancement","created":"2022-09-05","cited_by_count":34,"area":null},{"id":"2202.01356","title":"Direct Molecular Conformation Generation","created":"2022-02-03","cited_by_count":30,"area":null},{"id":"2207.09935","title":"Towards Efficient and Scale-Robust Ultra-High-Definition Image Demoireing","created":"2022-07-20","cited_by_count":30,"area":null},{"id":"2105.12405","title":"Unsupervised Part Segmentation through Disentangling Appearance and Shape","created":"2021-05-26","cited_by_count":29,"area":null},{"id":"2104.06757","title":"VTGAN: Semi-supervised Retinal Image Synthesis and Disease Prediction using Vision Transformers","created":"2021-04-14","cited_by_count":28,"area":null},{"id":"2106.02782","title":"On Perceptual Lossy Compression: The Cost of Perceptual Reconstruction and An Optimal Training Framework","created":"2021-06-05","cited_by_count":27,"area":null},{"id":"2303.08120","title":"Blind Video Deflickering by Neural Filtering with a Flawed Atlas","created":"2023-03-14","cited_by_count":27,"area":null},{"id":"2103.15910","title":"Sign Language Production: A Review","created":"2021-03-29","cited_by_count":26,"area":null},{"id":"2111.08960","title":"Compositional Transformers for Scene Generation","created":"2021-11-17","cited_by_count":24,"area":null},{"id":"2410.06231","title":"RelitLRM: Generative Relightable Radiance for Large Reconstruction Models","created":"2024-10-08","cited_by_count":23,"area":null},{"id":"2209.11047","title":"MIDMs: Matching Interleaved Diffusion Models for Exemplar-based Image Translation","created":"2022-09-22","cited_by_count":22,"area":"diffusion"},{"id":"2404.04883","title":"Mixture of Low-rank Experts for Transferable AI-Generated Image Detection","created":"2024-04-07","cited_by_count":21,"area":null},{"id":"2106.08749","title":"Learning to Disentangle GAN Fingerprint for Fake Image Attribution","created":"2021-06-16","cited_by_count":20,"area":null},{"id":"2403.01852","title":"PLACE: Adaptive Layout-Semantic Fusion for Semantic Image Synthesis","created":"2024-03-04","cited_by_count":20,"area":null},{"id":"2405.20282","title":"SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow","created":"2024-05-30","cited_by_count":20,"area":"diffusion"},{"id":"2212.06820","title":"Structured 3D Features for Reconstructing Controllable Avatars","created":"2022-12-13","cited_by_count":19,"area":null},{"id":"2507.23277","title":"iLRM: An Iterative Large 3D Reconstruction Model","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2201.11632","title":"Deep Video Prior for Video Consistency and Propagation","created":"2022-01-27","cited_by_count":18,"area":null},{"id":"2207.11617","title":"Face Deblurring using Dual Camera Fusion on Mobile Phones","created":"2022-07-23","cited_by_count":18,"area":null},{"id":"2104.09498","title":"Comparing Correspondences: Video Prediction with Correspondence-wise Losses","created":"2021-04-19","cited_by_count":16,"area":null},{"id":"2108.03466","title":"Unsupervised Portrait Shadow Removal via Generative Priors","created":"2021-08-07","cited_by_count":16,"area":null},{"id":"2203.16898","title":"Semantic-shape Adaptive Feature Modulation for Semantic Image Synthesis","created":"2022-03-31","cited_by_count":16,"area":null},{"id":"2204.02854","title":"Retrieval-based Spatially Adaptive Normalization for Semantic Image Synthesis","created":"2022-04-06","cited_by_count":15,"area":null},{"id":"2408.13697","title":"ForgeLens: Data-Efficient Forgery Focus for Generalizable Forgery Image Detection","created":"2024-08-25","cited_by_count":15,"area":null},{"id":"2103.15407","title":"Self-Supervised Visibility Learning for Novel View Synthesis","created":"2021-03-29","cited_by_count":14,"area":null},{"id":"2302.05118","title":"Beyond In-Domain Scenarios: Robust Density-Aware Calibration","created":"2023-02-10","cited_by_count":14,"area":null},{"id":"2404.18552","title":"SIDBench: A Python Framework for Reliably Assessing Synthetic Image Detection Methods","created":"2024-04-29","cited_by_count":14,"area":null},{"id":"2506.18890","title":"4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time","created":"2025-06-23","cited_by_count":14,"area":null},{"id":"2106.00446","title":"PanoDR: Spherical Panorama Diminished Reality for Indoor Scenes","created":"2021-06-01","cited_by_count":13,"area":null},{"id":"2106.07140","title":"SinIR: Efficient General Image Manipulation with Single Image Reconstruction","created":"2021-06-14","cited_by_count":13,"area":null},{"id":"2204.04428","title":"ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-wise Semantic Alignment and Generation","created":"2022-04-09","cited_by_count":13,"area":null},{"id":"2206.10082","title":"Optimally Controllable Perceptual Lossy Compression","created":"2022-06-21","cited_by_count":13,"area":null},{"id":"2501.12910","title":"PreciseCam: Precise Camera Control for Text-to-Image Generation","created":"2025-01-22","cited_by_count":13,"area":null},{"id":"2111.06934","title":"Contrastive Feature Loss for Image Prediction","created":"2021-11-12","cited_by_count":12,"area":null},{"id":"2502.15176","title":"Methods and Trends in Detecting AI-Generated Images: A Comprehensive Review","created":"2025-02-21","cited_by_count":12,"area":"diffusion"},{"id":"2107.07260","title":"MCL-GAN: Generative Adversarial Networks with Multiple Specialized Discriminators","created":"2021-07-15","cited_by_count":11,"area":null},{"id":"2112.13889","title":"Free-Viewpoint RGB-D Human Performance Capture and Rendering","created":"2021-12-27","cited_by_count":11,"area":null},{"id":"2402.16506","title":"Stochastic Conditional Diffusion Models for Robust Semantic Image Synthesis","created":"2024-02-26","cited_by_count":11,"area":"diffusion"}],"next_cursor":"100"}