{"total":2694,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863,"area":"diffusion"},{"id":"2108.10257","title":"SwinIR: Image Restoration Using Swin Transformer","created":"2021-08-23","cited_by_count":1887,"area":null},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295,"area":null},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099,"area":"wm"},{"id":"2101.01169","title":"Transformers in Vision: A Survey","created":"2021-01-04","cited_by_count":1013,"area":null},{"id":"2103.17249","title":"StyleCLIP: Text-Driven Manipulation of StyleGAN Imagery","created":"2021-03-31","cited_by_count":991,"area":null},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970,"area":null},{"id":"2109.07161","title":"Resolution-robust Large Mask Inpainting with Fourier Convolutions","created":"2021-09-15","cited_by_count":738,"area":null},{"id":"2203.01941","title":"Autoregressive Image Generation using Residual Quantization","created":"2022-03-03","cited_by_count":722,"area":null},{"id":"2110.04627","title":"Vector-quantized Image Modeling with Improved VQGAN","created":"2021-10-09","cited_by_count":658,"area":null},{"id":"2309.17080","title":"GAIA-1: A Generative World Model for Autonomous Driving","created":"2023-09-29","cited_by_count":637,"area":"wm"},{"id":"2210.02399","title":"Phenaki: Variable Length Video Generation From Open Domain Textual Description","created":"2022-10-05","cited_by_count":484,"area":null},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466,"area":"diffusion"},{"id":"2101.05278","title":"GAN Inversion: A Survey","created":"2021-01-14","cited_by_count":367,"area":null},{"id":"2111.05849","title":"Advances in Neural Rendering","created":"2021-11-10","cited_by_count":365,"area":null},{"id":"2101.04061","title":"Towards Real-World Blind Face Restoration with Generative Facial Prior","created":"2021-01-11","cited_by_count":349,"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":"2112.05814","title":"Deep ViT Features as Dense Visual Descriptors","created":"2021-12-10","cited_by_count":330,"area":null},{"id":"2209.00588","title":"Transformers are Sample-Efficient World Models","created":"2022-09-01","cited_by_count":328,"area":"wm"},{"id":"2108.05054","title":"Rethinking Coarse-to-Fine Approach in Single Image Deblurring","created":"2021-08-11","cited_by_count":326,"area":null},{"id":"2212.06135","title":"Rodin: A Generative Model for Sculpting 3D Digital Avatars Using Diffusion","created":"2022-12-12","cited_by_count":309,"area":"diffusion"},{"id":"2312.06662","title":"Photorealistic Video Generation with Diffusion Models","created":"2023-12-11","cited_by_count":306,"area":"diffusion"},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302,"area":null},{"id":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301,"area":null},{"id":"2303.09833","title":"FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model","created":"2023-03-17","cited_by_count":294,"area":"diffusion"},{"id":"2112.09127","title":"ICON: Implicit Clothed humans Obtained from Normals","created":"2021-12-16","cited_by_count":283,"area":null},{"id":"2304.14772","title":"Multisample Flow Matching: Straightening Flows with Minibatch Couplings","created":"2023-04-28","cited_by_count":278,"area":"diffusion"},{"id":"2204.03883","title":"Vision Transformers for Single Image Dehazing","created":"2022-04-08","cited_by_count":260,"area":null},{"id":"2101.04702","title":"Cross-Modal Contrastive Learning for Text-to-Image Generation","created":"2021-01-12","cited_by_count":259,"area":null},{"id":"2104.11280","title":"Motion Representations for Articulated Animation","created":"2021-04-22","cited_by_count":255,"area":null},{"id":"2308.14469","title":"Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization","created":"2023-08-28","cited_by_count":254,"area":"diffusion"},{"id":"2209.00647","title":"Visual Prompting via Image Inpainting","created":"2022-09-01","cited_by_count":250,"area":null},{"id":"2406.08177","title":"One-Step Effective Diffusion Network for Real-World Image Super-Resolution","created":"2024-06-12","cited_by_count":246,"area":"diffusion"},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244,"area":null},{"id":"2304.06790","title":"Inpaint Anything: Segment Anything Meets Image Inpainting","created":"2023-04-13","cited_by_count":233,"area":null},{"id":"2206.11253","title":"Towards Robust Blind Face Restoration with Codebook Lookup Transformer","created":"2022-06-22","cited_by_count":231,"area":null},{"id":"2112.05637","title":"HeadNeRF: A Real-time NeRF-based Parametric Head Model","created":"2021-12-10","cited_by_count":228,"area":null},{"id":"2104.09367","title":"Contrastive Learning for Compact Single Image Dehazing","created":"2021-04-19","cited_by_count":219,"area":null},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218,"area":null},{"id":"2112.01554","title":"Neural Head Avatars from Monocular RGB Videos","created":"2021-12-02","cited_by_count":213,"area":null},{"id":"2112.05744","title":"More Control for Free! Image Synthesis with Semantic Diffusion Guidance","created":"2021-12-10","cited_by_count":212,"area":"diffusion"},{"id":"2203.14367","title":"Thin-Plate Spline Motion Model for Image Animation","created":"2022-03-27","cited_by_count":210,"area":null},{"id":"2111.01007","title":"Projected GANs Converge Faster","created":"2021-11-01","cited_by_count":208,"area":null},{"id":"2104.06820","title":"Few-shot Image Generation via Cross-domain Correspondence","created":"2021-04-13","cited_by_count":207,"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":"2109.08379","title":"PIRenderer: Controllable Portrait Image Generation via Semantic Neural Rendering","created":"2021-09-17","cited_by_count":203,"area":null},{"id":"2112.00374","title":"CLIPstyler: Image Style Transfer with a Single Text Condition","created":"2021-12-01","cited_by_count":203,"area":null},{"id":"2105.06070","title":"GAN Prior Embedded Network for Blind Face Restoration in the Wild","created":"2021-05-13","cited_by_count":197,"area":null},{"id":"2311.13600","title":"ZipLoRA: Any Subject in Any Style by Effectively Merging LoRAs","created":"2023-11-22","cited_by_count":194,"area":null},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189,"area":null},{"id":"2105.14576","title":"StyTr$^2$: Image Style Transfer with Transformers","created":"2021-05-30","cited_by_count":187,"area":null},{"id":"2109.02934","title":"Fishr: Invariant Gradient Variances for Out-of-Distribution Generalization","created":"2021-09-07","cited_by_count":186,"area":null},{"id":"2503.20523","title":"GAIA-2: A Controllable Multi-View Generative World Model for Autonomous Driving","created":"2025-03-26","cited_by_count":185,"area":"wm"},{"id":"2212.08377","title":"PointAvatar: Deformable Point-based Head Avatars from Videos","created":"2022-12-16","cited_by_count":184,"area":null},{"id":"2202.05830","title":"Learning Fast Samplers for Diffusion Models by Differentiating Through Sample Quality","created":"2022-02-11","cited_by_count":182,"area":"diffusion"},{"id":"2303.13744","title":"Conditional Image-to-Video Generation with Latent Flow Diffusion Models","created":"2023-03-24","cited_by_count":181,"area":"diffusion"},{"id":"2108.03647","title":"AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer","created":"2021-08-08","cited_by_count":178,"area":null},{"id":"2203.06605","title":"Depth-Aware Generative Adversarial Network for Talking Head Video Generation","created":"2022-03-13","cited_by_count":178,"area":null},{"id":"2203.09043","title":"Latent Image Animator: Learning to Animate Images via Latent Space Navigation","created":"2022-03-17","cited_by_count":175,"area":null},{"id":"2108.07845","title":"ARCH++: Animation-Ready Clothed Human Reconstruction Revisited","created":"2021-08-17","cited_by_count":174,"area":null},{"id":"2203.04036","title":"StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN","created":"2022-03-08","cited_by_count":169,"area":null},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167,"area":"diffusion"},{"id":"2108.00946","title":"StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators","created":"2021-08-02","cited_by_count":164,"area":null},{"id":"2104.15069","title":"A Good Image Generator Is What You Need for High-Resolution Video Synthesis","created":"2021-04-30","cited_by_count":163,"area":null},{"id":"2204.08532","title":"Dress Code: High-Resolution Multi-Category Virtual Try-On","created":"2022-04-18","cited_by_count":162,"area":null},{"id":"2503.01774","title":"Difix3D+: Improving 3D Reconstructions with Single-Step Diffusion Models","created":"2025-03-03","cited_by_count":161,"area":"diffusion"},{"id":"2205.12952","title":"Pretraining is All You Need for Image-to-Image Translation","created":"2022-05-25","cited_by_count":160,"area":"diffusion"},{"id":"2311.16424","title":"Manifold Preserving Guided Diffusion","created":"2023-11-28","cited_by_count":157,"area":"diffusion"},{"id":"2308.07863","title":"StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models","created":"2023-08-15","cited_by_count":155,"area":"diffusion"},{"id":"2305.13501","title":"LaDI-VTON: Latent Diffusion Textual-Inversion Enhanced Virtual Try-On","created":"2023-05-22","cited_by_count":152,"area":"diffusion"},{"id":"2205.15278","title":"EAMM: One-Shot Emotional Talking Face via Audio-Based Emotion-Aware Motion Model","created":"2022-05-30","cited_by_count":151,"area":null},{"id":"2112.01517","title":"Efficient Neural Radiance Fields for Interactive Free-viewpoint Video","created":"2021-12-02","cited_by_count":150,"area":null},{"id":"2405.15223","title":"iVideoGPT: Interactive VideoGPTs are Scalable World Models","created":"2024-05-24","cited_by_count":146,"area":"wm"},{"id":"2103.04559","title":"Parser-Free Virtual Try-on via Distilling Appearance Flows","created":"2021-03-08","cited_by_count":143,"area":"distill"},{"id":"2306.08276","title":"TryOnDiffusion: A Tale of Two UNets","created":"2023-06-14","cited_by_count":141,"area":null},{"id":"2205.12183","title":"StylizedNeRF: Consistent 3D Scene Stylization as Stylized NeRF via 2D-3D Mutual Learning","created":"2022-05-24","cited_by_count":140,"area":null},{"id":"2403.14572","title":"Implicit Style-Content Separation using B-LoRA","created":"2024-03-21","cited_by_count":135,"area":null},{"id":"2104.13015","title":"Underwater Image Enhancement via Medium Transmission-Guided Multi-Color Space Embedding","created":"2021-04-27","cited_by_count":134,"area":null},{"id":"2111.12704","title":"Investigating Tradeoffs in Real-World Video Super-Resolution","created":"2021-11-24","cited_by_count":134,"area":null},{"id":"2207.07621","title":"MegaPortraits: One-shot Megapixel Neural Head Avatars","created":"2022-07-15","cited_by_count":131,"area":null},{"id":"2306.00306","title":"Low-Light Image Enhancement with Wavelet-based Diffusion Models","created":"2023-06-01","cited_by_count":127,"area":"diffusion"},{"id":"2201.12220","title":"Neural Optimal Transport","created":"2022-01-28","cited_by_count":126,"area":null},{"id":"2212.08070","title":"NeRF-Art: Text-Driven Neural Radiance Fields Stylization","created":"2022-12-15","cited_by_count":126,"area":null},{"id":"2107.07436","title":"FastSHAP: Real-Time Shapley Value Estimation","created":"2021-07-15","cited_by_count":125,"area":null},{"id":"2308.06101","title":"Taming the Power of Diffusion Models for High-Quality Virtual Try-On with Appearance Flow","created":"2023-08-11","cited_by_count":124,"area":"diffusion"},{"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":"2303.13756","title":"GP-VTON: Towards General Purpose Virtual Try-on via Collaborative Local-Flow Global-Parsing Learning","created":"2023-03-24","cited_by_count":120,"area":null},{"id":"2206.08343","title":"Realistic One-shot Mesh-based Head Avatars","created":"2022-06-16","cited_by_count":119,"area":null},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118,"area":"wm"},{"id":"2101.08629","title":"Image-to-Image Translation: Methods and Applications","created":"2021-01-21","cited_by_count":116,"area":null},{"id":"2205.06803","title":"VQFR: Blind Face Restoration with Vector-Quantized Dictionary and Parallel Decoder","created":"2022-05-13","cited_by_count":116,"area":null},{"id":"2212.08698","title":"Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models","created":"2022-12-16","cited_by_count":116,"area":"diffusion"},{"id":"2304.10530","title":"Collaborative Diffusion for Multi-Modal Face Generation and Editing","created":"2023-04-20","cited_by_count":116,"area":"diffusion"},{"id":"2403.10516","title":"FeatUp: A Model-Agnostic Framework for Features at Any Resolution","created":"2024-03-15","cited_by_count":116,"area":null},{"id":"2403.12036","title":"One-Step Image Translation with Text-to-Image Models","created":"2024-03-18","cited_by_count":116,"area":"diffusion"},{"id":"2203.09195","title":"Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution","created":"2022-03-17","cited_by_count":114,"area":null},{"id":"2206.11894","title":"MaskViT: Masked Visual Pre-Training for Video Prediction","created":"2022-06-23","cited_by_count":114,"area":null},{"id":"2103.16877","title":"ArtFlow: Unbiased Image Style Transfer via Reversible Neural Flows","created":"2021-03-31","cited_by_count":113,"area":null},{"id":"2204.00895","title":"Class-Incremental Learning by Knowledge Distillation with Adaptive Feature Consolidation","created":"2022-04-02","cited_by_count":113,"area":"distill"},{"id":"2206.03429","title":"Generating Long Videos of Dynamic Scenes","created":"2022-06-07","cited_by_count":113,"area":null}],"next_cursor":"100"}