{"total":127,"rows":[{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181,"area":"diffusion"},{"id":"2401.12945","title":"Lumiere: A Space-Time Diffusion Model for Video Generation","created":"2024-01-23","cited_by_count":455,"area":"diffusion"},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455,"area":"diffusion"},{"id":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432,"area":"diffusion"},{"id":"2312.02981","title":"ReconFusion: 3D Reconstruction with Diffusion Priors","created":"2023-12-05","cited_by_count":318,"area":"diffusion"},{"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":"2311.09217","title":"DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model","created":"2023-11-15","cited_by_count":214,"area":null},{"id":"2402.17525","title":"Diffusion Model-Based Image Editing: A Survey","created":"2024-02-27","cited_by_count":212,"area":"diffusion"},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185,"area":null},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156,"area":"diffusion"},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154,"area":"diffusion"},{"id":"2401.04092","title":"GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation","created":"2024-01-08","cited_by_count":153,"area":"alignment"},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136,"area":"wm"},{"id":"2312.00206","title":"SparseGS: Sparse View Synthesis using 3D Gaussian Splatting","created":"2023-11-30","cited_by_count":134,"area":null},{"id":"2311.17009","title":"Space-Time Diffusion Features for Zero-Shot Text-Driven Motion Transfer","created":"2023-11-28","cited_by_count":124,"area":null},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","cited_by_count":117,"area":"diffusion"},{"id":"2411.14430","title":"Stable Flow: Vital Layers for Training-Free Image Editing","created":"2024-11-21","cited_by_count":113,"area":"diffusion"},{"id":"2406.17763","title":"DiffusionPDE: Generative PDE-Solving Under Partial Observation","created":"2024-06-25","cited_by_count":108,"area":"diffusion"},{"id":"2312.02256","title":"EMDM: Efficient Motion Diffusion Model for Fast and High-Quality Motion Generation","created":"2023-12-04","cited_by_count":89,"area":"diffusion"},{"id":"2401.17053","title":"BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation","created":"2024-01-30","cited_by_count":83,"area":null},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77,"area":null},{"id":"2406.11138","title":"Diffusion Models in Low-Level Vision: A Survey","created":"2024-06-17","cited_by_count":74,"area":"diffusion"},{"id":"2312.12274","title":"Intrinsic Image Diffusion for Indoor Single-view Material Estimation","created":"2023-12-19","cited_by_count":73,"area":null},{"id":"2404.07771","title":"An Overview of Diffusion Models: Applications, Guided Generation, Statistical Rates and Optimization","created":"2024-04-11","cited_by_count":73,"area":"diffusion"},{"id":"2312.02432","title":"Orthogonal Adaptation for Modular Customization of Diffusion Models","created":"2023-12-05","cited_by_count":70,"area":"diffusion"},{"id":"2312.11417","title":"PolyDiff: Generating 3D Polygonal Meshes with Diffusion Models","created":"2023-12-18","cited_by_count":66,"area":"diffusion"},{"id":"2311.10093","title":"The Chosen One: Consistent Characters in Text-to-Image Diffusion Models","created":"2023-11-16","cited_by_count":63,"area":"diffusion"},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63,"area":null},{"id":"2311.17057","title":"ReMoS: 3D Motion-Conditioned Reaction Synthesis for Two-Person Interactions","created":"2023-11-28","cited_by_count":62,"area":null},{"id":"2312.04560","title":"NeRFiller: Completing Scenes via Generative 3D Inpainting","created":"2023-12-07","cited_by_count":62,"area":null},{"id":"2311.17857","title":"Gaussian Shell Maps for Efficient 3D Human Generation","created":"2023-11-29","cited_by_count":61,"area":null},{"id":"2410.03665","title":"Estimating Body and Hand Motion in an Ego-sensed World","created":"2024-10-04","cited_by_count":58,"area":null},{"id":"2403.10615","title":"LightIt: Illumination Modeling and Control for Diffusion Models","created":"2024-03-15","cited_by_count":57,"area":"diffusion"},{"id":"2407.00783","title":"Diffusion Models and Representation Learning: A Survey","created":"2024-06-30","cited_by_count":54,"area":"diffusion"},{"id":"2408.13252","title":"LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation","created":"2024-08-23","cited_by_count":53,"area":null},{"id":"2411.18616","title":"Diffusion Self-Distillation for Zero-Shot Customized Image Generation","created":"2024-11-27","cited_by_count":47,"area":"diffusion"},{"id":"2411.19722","title":"JetFormer: An Autoregressive Generative Model of Raw Images and Text","created":"2024-11-29","cited_by_count":46,"area":"mllm"},{"id":"2412.10523","title":"The Language of Motion: Unifying Verbal and Non-verbal Language of 3D Human Motion","created":"2024-12-13","cited_by_count":46,"area":null},{"id":"2407.07111","title":"Diffusion Model-Based Video Editing: A Survey","created":"2024-06-26","cited_by_count":44,"area":"diffusion"},{"id":"2311.17737","title":"GenZI: Zero-Shot 3D Human-Scene Interaction Generation","created":"2023-11-29","cited_by_count":40,"area":null},{"id":"2407.13759","title":"Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion","created":"2024-07-18","cited_by_count":39,"area":"wm"},{"id":"2406.09413","title":"Interpreting the Weight Space of Customized Diffusion Models","created":"2024-06-13","cited_by_count":36,"area":"diffusion"},{"id":"2407.01866","title":"Image-GS: Content-Adaptive Image Representation via 2D Gaussians","created":"2024-07-02","cited_by_count":35,"area":null},{"id":"2312.01409","title":"Generative Rendering: Controllable 4D-Guided Video Generation with 2D Diffusion Models","created":"2023-12-03","cited_by_count":30,"area":"diffusion"},{"id":"2402.04930","title":"Blue noise for diffusion models","created":"2024-02-07","cited_by_count":29,"area":"diffusion"},{"id":"2405.05538","title":"A Survey on Personalized Content Synthesis with Diffusion Models","created":"2024-05-09","cited_by_count":29,"area":"diffusion"},{"id":"2409.19365","title":"Conditional Image Synthesis with Diffusion Models: A Survey","created":"2024-09-28","cited_by_count":29,"area":"diffusion"},{"id":"2403.15064","title":"Recent Trends in 3D Reconstruction of General Non-Rigid Scenes","created":"2024-03-22","cited_by_count":28,"area":null},{"id":"2401.07727","title":"HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation","created":"2024-01-15","cited_by_count":21,"area":null},{"id":"2512.10685","title":"Sharp Monocular View Synthesis in Less Than a Second","created":"2025-12-11","cited_by_count":20,"area":null},{"id":"2410.18974","title":"3D-Adapter: Geometry-Consistent Multi-View Diffusion for High-Quality 3D Generation","created":"2024-10-24","cited_by_count":19,"area":"diffusion"},{"id":"2403.11821","title":"A Survey on Quality Metrics for Text-to-Image Generation","created":"2024-03-18","cited_by_count":18,"area":null},{"id":"2501.10021","title":"X-Dyna: Expressive Dynamic Human Image Animation","created":"2025-01-17","cited_by_count":18,"area":null},{"id":"2501.03992","title":"NeuralSVG: An Implicit Representation for Text-to-Vector Generation","created":"2025-01-07","cited_by_count":17,"area":null},{"id":"2504.05304","title":"Gaussian Mixture Flow Matching Models","created":"2025-04-07","cited_by_count":17,"area":"diffusion"},{"id":"2312.00870","title":"3DiFACE: Diffusion-based Speech-driven 3D Facial Animation and Editing","created":"2023-12-01","cited_by_count":15,"area":"diffusion"},{"id":"2312.02149","title":"Generative Powers of Ten","created":"2023-12-04","cited_by_count":15,"area":null},{"id":"2505.03432","title":"Wasserstein Convergence of Score-based Generative Models under Semiconvexity and Discontinuous Gradients","created":"2025-05-06","cited_by_count":15,"area":"diffusion"},{"id":"2503.01845","title":"Denoising Functional Maps: Diffusion Models for Shape Correspondence","created":"2025-03-03","cited_by_count":14,"area":"diffusion"},{"id":"2506.07998","title":"Generative Modeling of Weights: Generalization or Memorization?","created":"2025-06-09","cited_by_count":14,"area":null},{"id":"2311.15435","title":"Functional Diffusion","created":"2023-11-26","cited_by_count":13,"area":"diffusion"},{"id":"2406.04239","title":"Solving Inverse Problems in Protein Space Using Diffusion-Based Priors","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2406.04253","title":"A Survey on 3D Human Avatar Modeling -- From Reconstruction to Generation","created":"2024-06-06","cited_by_count":13,"area":null},{"id":"2409.00230","title":"Spatially-Aware Diffusion Models with Cross-Attention for Global Field Reconstruction with Sparse Observations","created":"2024-08-30","cited_by_count":13,"area":"diffusion"},{"id":"2410.05259","title":"GS-VTON: Controllable 3D Virtual Try-on with Gaussian Splatting","created":"2024-10-07","cited_by_count":13,"area":null},{"id":"2412.06753","title":"InstantRestore: Single-Step Personalized Face Restoration with Shared-Image Attention","created":"2024-12-09","cited_by_count":13,"area":null},{"id":"2408.00001","title":"Replication in Visual Diffusion Models: A Survey and Outlook","created":"2024-07-07","cited_by_count":11,"area":"diffusion"},{"id":"2411.17249","title":"Buffer Anytime: Zero-Shot Video Depth and Normal from Image Priors","created":"2024-11-26","cited_by_count":11,"area":null},{"id":"2402.17986","title":"PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis","created":"2024-02-28","cited_by_count":10,"area":null},{"id":"2404.15692","title":"Deep Learning for Accelerated and Robust MRI Reconstruction: a Review","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2410.14770","title":"A Survey on Computational Solutions for Reconstructing Complete Objects by Reassembling Their Fractured Parts","created":"2024-10-18","cited_by_count":9,"area":null},{"id":"2311.18328","title":"Advances in 3D Neural Stylization: A Survey","created":"2023-11-30","cited_by_count":8,"area":null},{"id":"2504.13226","title":"Image Editing with Diffusion Models: A Survey","created":"2025-04-17","cited_by_count":8,"area":"diffusion"},{"id":"2406.07648","title":"Multi-View Large Reconstruction Model via Geometry-Aware Positional Encoding and Attention","created":"2024-06-11","cited_by_count":6,"area":null},{"id":"2411.18702","title":"Random Walks with Tweedie: A Unified View of Score-Based Diffusion Models","created":"2024-11-27","cited_by_count":6,"area":"diffusion"},{"id":"2503.10365","title":"Piece it Together: Part-Based Concepting with IP-Priors","created":"2025-03-13","cited_by_count":6,"area":null},{"id":"2312.14977","title":"Diffusion Models for Generative Artificial Intelligence: An Introduction for Applied Mathematicians","created":"2023-12-21","cited_by_count":5,"area":"diffusion"},{"id":"2404.12378","title":"6Img-to-3D: Few-Image Large-Scale Outdoor Driving Scene Reconstruction","created":"2024-04-18","cited_by_count":5,"area":null},{"id":"2407.10592","title":"InsertDiffusion: Identity Preserving Visualization of Objects through a Training-Free Diffusion Architecture","created":"2024-07-15","cited_by_count":5,"area":"diffusion"},{"id":"2508.03034","title":"MoCA: Identity-Preserving Text-to-Video Generation via Mixture of Cross Attention","created":"2025-08-05","cited_by_count":5,"area":"diffusion"},{"id":"2510.07317","title":"Quantum-enhanced Computer Vision: Going Beyond Classical Algorithms","created":"2025-10-08","cited_by_count":5,"area":null},{"id":"2312.14579","title":"Synthesizing Environment-Specific People in Photographs","created":"2023-12-22","cited_by_count":4,"area":null},{"id":"2403.14987","title":"Generative Active Learning for Image Synthesis Personalization","created":"2024-03-22","cited_by_count":4,"area":null},{"id":"2406.18581","title":"Dream-in-Style: Text-to-3D Generation Using Stylized Score Distillation","created":"2024-06-05","cited_by_count":4,"area":null},{"id":"2407.04191","title":"GazeFusion: Saliency-Guided Image Generation","created":"2024-03-16","cited_by_count":4,"area":"diffusion"},{"id":"2511.00103","title":"FreeSliders: Training-Free, Modality-Agnostic Concept Sliders for Fine-Grained Diffusion Control in Images, Audio, and Video","created":"2025-10-30","cited_by_count":4,"area":"diffusion"},{"id":"2604.01274","title":"Non-Rigid 3D Shape Correspondences: From Foundations to Open Challenges and Opportunities","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2312.17234","title":"Personalized Restoration via Dual-Pivot Tuning","created":"2023-12-28","cited_by_count":3,"area":"diffusion"},{"id":"2407.11104","title":"Exploring the Potentials and Challenges of Deep Generative Models in Product Design Conception","created":"2024-07-15","cited_by_count":3,"area":null},{"id":"2410.06236","title":"SD-$\\pi$XL: Generating Low-Resolution Quantized Imagery via Score Distillation","created":"2024-10-08","cited_by_count":3,"area":null},{"id":"2502.02187","title":"ShapeShifter: 3D Variations Using Multiscale and Sparse Point-Voxel Diffusion","created":"2025-02-04","cited_by_count":3,"area":null},{"id":"2510.04504","title":"Asynchronous Denoising Diffusion Models for Aligning Text-to-Image Generation","created":"2025-10-06","cited_by_count":3,"area":"diffusion"},{"id":"2511.22069","title":"Convergence Dynamics of Over-Parameterized Score Matching for a Single Gaussian","created":"2025-11-27","cited_by_count":3,"area":"diffusion"},{"id":"2603.03287","title":"Deep Sketch-Based 3D Modeling: A Survey","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2312.00778","title":"MorpheuS: Neural Dynamic 360{\\deg} Surface Reconstruction from Monocular RGB-D Video","created":"2023-12-01","cited_by_count":2,"area":null},{"id":"2401.14379","title":"UrbanGenAI: Reconstructing Urban Landscapes using Panoptic Segmentation and Diffusion Models","created":"2024-01-25","cited_by_count":2,"area":"diffusion"},{"id":"2402.15909","title":"Enhanced Droplet Analysis Using Generative Adversarial Networks","created":"2024-02-24","cited_by_count":2,"area":null},{"id":"2407.15153","title":"Anchored Diffusion for Video Face Reenactment","created":"2024-07-21","cited_by_count":2,"area":null},{"id":"2409.17045","title":"GeoBiked: A Dataset with Geometric Features and Automated Labeling Techniques to Enable Deep Generative Models in Engineering Design","created":"2024-09-25","cited_by_count":2,"area":null},{"id":"2412.04086","title":"BodyMetric: Evaluating the Realism of Human Bodies in Text-to-Image Generation","created":"2024-12-05","cited_by_count":2,"area":null}],"next_cursor":"100"}