{"total":222,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863,"area":"diffusion"},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511,"area":null},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300,"area":"diffusion"},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652,"area":null},{"id":"2306.09344","title":"DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data","created":"2023-06-15","cited_by_count":337,"area":null},{"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,"area":null},{"id":"2209.14860","title":"Bridging the Gap to Real-World Object-Centric Learning","created":"2022-09-29","cited_by_count":220,"area":null},{"id":"2111.01007","title":"Projected GANs Converge Faster","created":"2021-11-01","cited_by_count":208,"area":null},{"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":"2304.01247","title":"Generative Diffusion Prior for Unified Image Restoration and Enhancement","created":"2023-04-03","cited_by_count":199,"area":"diffusion"},{"id":"2209.06950","title":"Lossy Image Compression with Conditional Diffusion Models","created":"2022-09-14","cited_by_count":170,"area":"diffusion"},{"id":"2303.14535","title":"EfficientAD: Accurate Visual Anomaly Detection at Millisecond-Level Latencies","created":"2023-03-25","cited_by_count":160,"area":null},{"id":"2202.04901","title":"FILM: Frame Interpolation for Large Motion","created":"2022-02-10","cited_by_count":153,"area":null},{"id":"2108.08827","title":"ImageBART: Bidirectional Context with Multinomial Diffusion for Autoregressive Image Synthesis","created":"2021-08-19","cited_by_count":122,"area":null},{"id":"2103.05445","title":"Pixel-wise Anomaly Detection in Complex Driving Scenes","created":"2021-03-09","cited_by_count":109,"area":null},{"id":"2308.09388","title":"Diffusion Models for Image Restoration and Enhancement: A Comprehensive Survey","created":"2023-08-18","cited_by_count":109,"area":"diffusion"},{"id":"2201.00308","title":"DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents","created":"2022-01-02","cited_by_count":104,"area":"diffusion"},{"id":"2412.12091","title":"Wonderland: Navigating 3D Scenes from a Single Image","created":"2024-12-16","cited_by_count":99,"area":"diffusion"},{"id":"2502.03444","title":"Masked Autoencoders Are Effective Tokenizers for Diffusion Models","created":"2025-02-05","cited_by_count":96,"area":"diffusion"},{"id":"2112.02308","title":"MoFaNeRF: Morphable Facial Neural Radiance Field","created":"2021-12-04","cited_by_count":94,"area":null},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","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":"2202.06533","title":"An Introduction to Neural Data Compression","created":"2022-02-14","cited_by_count":79,"area":null},{"id":"2210.04142","title":"Deep Clustering: A Comprehensive Survey","created":"2022-10-09","cited_by_count":78,"area":null},{"id":"2405.05967","title":"Distilling Diffusion Models into Conditional GANs","created":"2024-05-09","cited_by_count":78,"area":"diffusion"},{"id":"2309.00398","title":"VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation","created":"2023-09-01","cited_by_count":74,"area":"diffusion"},{"id":"2309.01745","title":"Benchmarking Autoregressive Conditional Diffusion Models for Turbulent Flow Simulation","created":"2023-09-04","cited_by_count":71,"area":"diffusion"},{"id":"2404.00815","title":"Towards Realistic Scene Generation with LiDAR Diffusion Models","created":"2024-03-31","cited_by_count":69,"area":"wm"},{"id":"2104.00854","title":"The Spatially-Correlative Loss for Various Image Translation Tasks","created":"2021-04-02","cited_by_count":66,"area":null},{"id":"2112.09164","title":"High Fidelity Visualization of What Your Self-Supervised Representation Knows About","created":"2021-12-16","cited_by_count":66,"area":null},{"id":"2305.15956","title":"Anomaly Detection with Conditioned Denoising Diffusion Models","created":"2023-05-25","cited_by_count":56,"area":"diffusion"},{"id":"2412.10958","title":"SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer","created":"2024-12-14","cited_by_count":56,"area":null},{"id":"2411.13383","title":"Adversarial Diffusion Compression for Real-World Image Super-Resolution","created":"2024-11-20","cited_by_count":52,"area":null},{"id":"2104.11222","title":"On Aliased Resizing and Surprising Subtleties in GAN Evaluation","created":"2021-04-22","cited_by_count":51,"area":null},{"id":"2303.04743","title":"Vector Quantized Time Series Generation with a Bidirectional Prior Model","created":"2023-03-08","cited_by_count":50,"area":null},{"id":"2309.01700","title":"ControlMat: A Controlled Generative Approach to Material Capture","created":"2023-09-04","cited_by_count":50,"area":"diffusion"},{"id":"2105.04551","title":"Stochastic Image-to-Video Synthesis using cINNs","created":"2021-05-10","cited_by_count":49,"area":null},{"id":"2203.12979","title":"Is Geometry Enough for Matching in Visual Localization?","created":"2022-03-24","cited_by_count":48,"area":null},{"id":"2207.13686","title":"Shift-tolerant Perceptual Similarity Metric","created":"2022-07-27","cited_by_count":44,"area":null},{"id":"2107.02790","title":"iPOKE: Poking a Still Image for Controlled Stochastic Video Synthesis","created":"2021-07-06","cited_by_count":42,"area":null},{"id":"2503.14324","title":"DualToken: Towards Unifying Visual Understanding and Generation with Dual Visual Vocabularies","created":"2025-03-18","cited_by_count":42,"area":null},{"id":"2410.14171","title":"Heavy-Tailed Diffusion Models","created":"2024-10-18","cited_by_count":40,"area":"diffusion"},{"id":"2308.11408","title":"MatFuse: Controllable Material Generation with Diffusion Models","created":"2023-08-22","cited_by_count":39,"area":"diffusion"},{"id":"2211.02843","title":"Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift","created":"2022-11-05","cited_by_count":38,"area":null},{"id":"2406.17998","title":"Changen2: Multi-Temporal Remote Sensing Generative Change Foundation Model","created":"2024-06-26","cited_by_count":37,"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":"2403.00025","title":"On the Challenges and Opportunities in Generative AI","created":"2024-02-28","cited_by_count":31,"area":null},{"id":"2103.15295","title":"Best-Buddy GANs for Highly Detailed Image Super-Resolution","created":"2021-03-29","cited_by_count":30,"area":null},{"id":"2303.12343","title":"LD-ZNet: A Latent Diffusion Approach for Text-Based Image Segmentation","created":"2023-03-22","cited_by_count":29,"area":"diffusion"},{"id":"2212.09102","title":"Face Generation and Editing with StyleGAN: A Survey","created":"2022-12-18","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":"2503.06744","title":"CoDa-4DGS: Dynamic Gaussian Splatting with Context and Deformation Awareness for Autonomous Driving","created":"2025-03-09","cited_by_count":25,"area":"driving"},{"id":"2503.18446","title":"Latent Space Super-Resolution for Higher-Resolution Image Generation with Diffusion Models","created":"2025-03-24","cited_by_count":25,"area":"diffusion"},{"id":"2102.09351","title":"A Comprehensive Review of Deep Learning-based Single Image Super-resolution","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2203.09333","title":"Modulated Contrast for Versatile Image Synthesis","created":"2022-03-17","cited_by_count":23,"area":null},{"id":"2103.01071","title":"A survey on Variational Autoencoders from a GreenAI perspective","created":"2021-03-01","cited_by_count":22,"area":null},{"id":"2205.00690","title":"From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Model","created":"2022-05-02","cited_by_count":22,"area":null},{"id":"2304.11603","title":"LaMD: Latent Motion Diffusion for Image-Conditional Video Generation","created":"2023-04-23","cited_by_count":22,"area":"diffusion"},{"id":"2309.17031","title":"Scalable Multi-Temporal Remote Sensing Change Data Generation via Simulating Stochastic Change Process","created":"2023-09-29","cited_by_count":22,"area":null},{"id":"2103.11135","title":"High Resolution Face Editing with Masked GAN Latent Code Optimization","created":"2021-03-20","cited_by_count":21,"area":null},{"id":"2403.09683","title":"Counterfactual Image Editing","created":"2024-02-07","cited_by_count":20,"area":null},{"id":"2502.14801","title":"AVD2: Accident Video Diffusion for Accident Video Description","created":"2025-02-20","cited_by_count":20,"area":null},{"id":"2103.05086","title":"How Privacy-Preserving are Line Clouds? Recovering Scene Details from 3D Lines","created":"2021-03-08","cited_by_count":19,"area":null},{"id":"2201.05120","title":"SeamlessGAN: Self-Supervised Synthesis of Tileable Texture Maps","created":"2022-01-13","cited_by_count":19,"area":null},{"id":"2204.10090","title":"Learn from Unpaired Data for Image Restoration: A Variational Bayes Approach","created":"2022-04-21","cited_by_count":18,"area":null},{"id":"2308.04020","title":"Synthetic Augmentation with Large-scale Unconditional Pre-training","created":"2023-08-08","cited_by_count":18,"area":null},{"id":"2505.21473","title":"DetailFlow: 1D Coarse-to-Fine Autoregressive Image Generation via Next-Detail Prediction","created":"2025-05-27","cited_by_count":18,"area":null},{"id":"2107.04619","title":"Diverse Video Generation using a Gaussian Process Trigger","created":"2021-07-09","cited_by_count":17,"area":null},{"id":"2205.10636","title":"AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints","created":"2022-05-21","cited_by_count":17,"area":null},{"id":"2211.03796","title":"Astronomia ex machina: a history, primer, and outlook on neural networks in astronomy","created":"2022-11-07","cited_by_count":17,"area":null},{"id":"2306.12547","title":"DGC-GNN: Leveraging Geometry and Color Cues for Visual Descriptor-Free 2D-3D Matching","created":"2023-06-21","cited_by_count":17,"area":null},{"id":"2506.09040","title":"Autoregressive Semantic Visual Reconstruction Helps VLMs Understand Better","created":"2025-06-10","cited_by_count":17,"area":"mllm"},{"id":"2103.14616","title":"Training a Task-Specific Image Reconstruction Loss","created":"2021-03-26","cited_by_count":16,"area":null},{"id":"2106.05838","title":"Large-scale optimal transport map estimation using projection pursuit","created":"2021-06-09","cited_by_count":16,"area":null},{"id":"2108.02931","title":"Detailed Avatar Recovery from Single Image","created":"2021-08-06","cited_by_count":16,"area":null},{"id":"2104.04785","title":"Generating Physically-Consistent Satellite Imagery for Climate Visualizations","created":"2021-04-10","cited_by_count":13,"area":null},{"id":"2104.06797","title":"Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Network","created":"2021-04-14","cited_by_count":13,"area":null},{"id":"2107.09427","title":"RankSRGAN: Super Resolution Generative Adversarial Networks with Learning to Rank","created":"2021-07-20","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":"2408.10901","title":"A Gray-box Attack against Latent Diffusion Model-based Image Editing by Posterior Collapse","created":"2024-08-20","cited_by_count":13,"area":"diffusion"},{"id":"2207.05312","title":"Outpainting by Queries","created":"2022-07-12","cited_by_count":12,"area":null},{"id":"2209.12243","title":"Safety-compliant Generative Adversarial Networks for Human Trajectory Forecasting","created":"2022-09-25","cited_by_count":12,"area":null},{"id":"2503.14966","title":"Ultrasound Image-to-Video Synthesis via Latent Dynamic Diffusion Models","created":"2025-03-19","cited_by_count":12,"area":"diffusion"},{"id":"2103.00586","title":"A Kinematic Bottleneck Approach For Pose Regression of Flexible Surgical Instruments directly from Images","created":"2021-02-28","cited_by_count":11,"area":null},{"id":"2103.07470","title":"Understanding Invariance via Feedforward Inversion of Discriminatively Trained Classifiers","created":"2021-03-15","cited_by_count":11,"area":null},{"id":"2206.11939","title":"Measuring Representational Robustness of Neural Networks Through Shared Invariances","created":"2022-06-23","cited_by_count":11,"area":null},{"id":"2210.15107","title":"Boosting Point Clouds Rendering via Radiance Mapping","created":"2022-10-27","cited_by_count":11,"area":null},{"id":"2302.04032","title":"A Systematic Performance Analysis of Deep Perceptual Loss Networks: Breaking Transfer Learning Conventions","created":"2023-02-08","cited_by_count":11,"area":null},{"id":"2403.19140","title":"QNCD: Quantization Noise Correction for Diffusion Models","created":"2024-03-28","cited_by_count":11,"area":"diffusion"},{"id":"2411.10023","title":"Model Inversion Attacks: A Survey of Approaches and Countermeasures","created":"2024-11-15","cited_by_count":11,"area":null},{"id":"2101.06775","title":"Symmetric-Constrained Irregular Structure Inpainting for Brain MRI Registration with Tumor Pathology","created":"2021-01-17","cited_by_count":10,"area":null},{"id":"2305.08840","title":"Attacking Perceptual Similarity Metrics","created":"2023-05-15","cited_by_count":10,"area":null},{"id":"2308.11223","title":"LDP-Feat: Image Features with Local Differential Privacy","created":"2023-08-22","cited_by_count":10,"area":null},{"id":"2201.04898","title":"Flexible Style Image Super-Resolution using Conditional Objective","created":"2022-01-13","cited_by_count":9,"area":null},{"id":"2309.03048","title":"Exploring Semantic Consistency in Unpaired Image Translation to Generate Data for Surgical Applications","created":"2023-09-06","cited_by_count":9,"area":null},{"id":"2311.12090","title":"FrePolad: Frequency-Rectified Point Latent Diffusion for Point Cloud Generation","created":"2023-11-20","cited_by_count":9,"area":"diffusion"},{"id":"2103.13389","title":"Generating Novel Scene Compositions from Single Images and Videos","created":"2021-03-24","cited_by_count":8,"area":null},{"id":"2107.06304","title":"Privacy Vulnerability of Split Computing to Data-Free Model Inversion Attacks","created":"2021-07-13","cited_by_count":8,"area":null},{"id":"2109.14715","title":"USIS: Unsupervised Semantic Image Synthesis","created":"2021-09-29","cited_by_count":8,"area":null},{"id":"2311.17524","title":"Improving Feature Stability during Upsampling -- Spectral Artifacts and the Importance of Spatial Context","created":"2023-11-29","cited_by_count":8,"area":null}],"next_cursor":"100"}