{"total":117,"rows":[{"id":"2310.15008","title":"Wonder3D: Single Image to 3D using Cross-Domain Diffusion","created":"2023-10-23","cited_by_count":689,"area":"diffusion"},{"id":"2309.03453","title":"SyncDreamer: Generating Multiview-consistent Images from a Single-view Image","created":"2023-09-07","cited_by_count":645,"area":"diffusion"},{"id":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490,"area":null},{"id":"2312.02981","title":"ReconFusion: 3D Reconstruction with Diffusion Priors","created":"2023-12-05","cited_by_count":318,"area":"diffusion"},{"id":"2304.02602","title":"Generative Novel View Synthesis with 3D-Aware Diffusion Models","created":"2023-04-05","cited_by_count":274,"area":"diffusion"},{"id":"2310.02601","title":"MagicDrive: Street View Generation with Diverse 3D Geometry Control","created":"2023-10-04","cited_by_count":252,"area":"diffusion"},{"id":"2311.16918","title":"RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D","created":"2023-11-28","cited_by_count":168,"area":"diffusion"},{"id":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166,"area":"diffusion"},{"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":"2410.15957","title":"CamI2V: Camera-Controlled Image-to-Video Diffusion Model","created":"2024-10-21","cited_by_count":120,"area":"diffusion"},{"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":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116,"area":null},{"id":"2411.04924","title":"MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views","created":"2024-11-07","cited_by_count":116,"area":null},{"id":"2306.11719","title":"Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision","created":"2023-06-20","cited_by_count":112,"area":"diffusion"},{"id":"2506.18903","title":"VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory","created":"2025-06-23","cited_by_count":109,"area":null},{"id":"2405.11616","title":"Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention","created":"2024-05-19","cited_by_count":100,"area":null},{"id":"2304.06720","title":"Expressive Text-to-Image Generation with Rich Text","created":"2023-04-13","cited_by_count":89,"area":null},{"id":"2407.19918","title":"FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention","created":"2024-07-29","cited_by_count":89,"area":"diffusion"},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","cited_by_count":87,"area":null},{"id":"2310.08092","title":"Consistent123: Improve Consistency for One Image to 3D Object Synthesis","created":"2023-10-12","cited_by_count":84,"area":"diffusion"},{"id":"2310.03020","title":"Consistent-1-to-3: Consistent Image to 3D View Synthesis via Geometry-aware Diffusion Models","created":"2023-10-04","cited_by_count":79,"area":"diffusion"},{"id":"2405.15364","title":"NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer","created":"2024-05-24","cited_by_count":79,"area":"diffusion"},{"id":"2304.10700","title":"Long-Term Photometric Consistent Novel View Synthesis with Diffusion Models","created":"2023-04-21","cited_by_count":76,"area":"diffusion"},{"id":"2405.17251","title":"GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping","created":"2024-05-27","cited_by_count":73,"area":null},{"id":"2312.04551","title":"Free3D: Consistent Novel View Synthesis without 3D Representation","created":"2023-12-07","cited_by_count":72,"area":null},{"id":"2312.06725","title":"EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion","created":"2023-12-11","cited_by_count":72,"area":"diffusion"},{"id":"2406.18524","title":"MultiDiff: Consistent Novel View Synthesis from a Single Image","created":"2024-06-26","cited_by_count":68,"area":"diffusion"},{"id":"2407.07860","title":"Controlling Space and Time with Diffusion Models","created":"2024-07-10","cited_by_count":66,"area":"diffusion"},{"id":"2310.10343","title":"ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion","created":"2023-10-16","cited_by_count":65,"area":null},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63,"area":null},{"id":"2402.05235","title":"SPAD : Spatially Aware Multiview Diffusers","created":"2024-02-07","cited_by_count":62,"area":null},{"id":"2403.01807","title":"ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models","created":"2024-03-04","cited_by_count":57,"area":null},{"id":"2502.10059","title":"RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control","created":"2025-02-14","cited_by_count":57,"area":null},{"id":"2311.15980","title":"Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion","created":"2023-11-27","cited_by_count":50,"area":"diffusion"},{"id":"2403.12010","title":"VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model","created":"2024-03-18","cited_by_count":45,"area":null},{"id":"2508.08248","title":"StableAvatar: Infinite-Length Audio-Driven Avatar Video Generation","created":"2025-08-11","cited_by_count":44,"area":"diffusion"},{"id":"2410.09049","title":"SceneCraft: Layout-Guided 3D Scene Generation","created":"2024-10-11","cited_by_count":41,"area":null},{"id":"2403.16407","title":"A Survey on Long Video Generation: Challenges, Methods, and Prospects","created":"2024-03-25","cited_by_count":40,"area":null},{"id":"2410.16892","title":"VistaDream: Sampling multiview consistent images for single-view scene reconstruction","created":"2024-10-22","cited_by_count":38,"area":"diffusion"},{"id":"2410.24203","title":"DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion","created":"2024-10-31","cited_by_count":38,"area":"diffusion"},{"id":"2402.17768","title":"Diffusion Meets DAgger: Supercharging Eye-in-hand Imitation Learning","created":"2024-02-27","cited_by_count":35,"area":"offlinerl"},{"id":"2403.06351","title":"Put Myself in Your Shoes: Lifting the Egocentric Perspective from Exocentric Videos","created":"2024-03-11","cited_by_count":32,"area":null},{"id":"2403.09439","title":"3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation","created":"2024-03-14","cited_by_count":29,"area":null},{"id":"2408.14211","title":"MagicMan: Generative Novel View Synthesis of Humans with 3D-Aware Diffusion and Iterative Refinement","created":"2024-08-26","cited_by_count":24,"area":"diffusion"},{"id":"2410.10774","title":"Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention","created":"2024-10-14","cited_by_count":24,"area":"diffusion"},{"id":"2505.05474","title":"3D Scene Generation: A Survey","created":"2025-05-08","cited_by_count":24,"area":"diffusion"},{"id":"2408.14765","title":"CrossViewDiff: A Cross-View Diffusion Model for Satellite-to-Street View Synthesis","created":"2024-08-27","cited_by_count":23,"area":"diffusion"},{"id":"2409.05463","title":"DriveScape: Towards High-Resolution Controllable Multi-View Driving Video Generation","created":"2024-09-09","cited_by_count":22,"area":"wm"},{"id":"2402.14792","title":"Consolidating Attention Features for Multi-view Image Editing","created":"2024-02-22","cited_by_count":19,"area":null},{"id":"2411.07765","title":"Novel View Synthesis with Pixel-Space Diffusion Models","created":"2024-11-12","cited_by_count":16,"area":"diffusion"},{"id":"2411.16680","title":"Quark: Real-time, High-resolution, and General Neural View Synthesis","created":"2024-11-25","cited_by_count":16,"area":null},{"id":"2402.03445","title":"Denoising Diffusion via Image-Based Rendering","created":"2024-02-05","cited_by_count":15,"area":"diffusion"},{"id":"2403.17782","title":"GenesisTex: Adapting Image Denoising Diffusion to Texture Space","created":"2024-03-26","cited_by_count":15,"area":"diffusion"},{"id":"2511.20186","title":"Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis","created":"2025-11-25","cited_by_count":15,"area":null},{"id":"2402.18842","title":"ViewFusion: Towards Multi-View Consistency via Interpolated Denoising","created":"2024-02-29","cited_by_count":14,"area":"diffusion"},{"id":"2312.03869","title":"Inpaint3D: 3D Scene Content Generation using 2D Inpainting Diffusion","created":"2023-12-06","cited_by_count":13,"area":"diffusion"},{"id":"2403.10395","title":"Isotropic3D: Image-to-3D Generation Based on a Single CLIP Embedding","created":"2024-03-15","cited_by_count":13,"area":"diffusion"},{"id":"2412.08410","title":"Physical Informed Driving World Model","created":"2024-12-11","cited_by_count":13,"area":"wm"},{"id":"2403.08902","title":"Envision3D: One Image to 3D with Anchor Views Interpolation","created":"2024-03-13","cited_by_count":12,"area":"diffusion"},{"id":"2404.07949","title":"Taming Stable Diffusion for Text to 360{\\deg} Panorama Image Generation","created":"2024-04-11","cited_by_count":12,"area":"diffusion"},{"id":"2406.06133","title":"ExtraNeRF: Visibility-Aware View Extrapolation of Neural Radiance Fields with Diffusion Models","created":"2024-06-10","cited_by_count":12,"area":"diffusion"},{"id":"2412.18565","title":"3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement","created":"2024-12-24","cited_by_count":12,"area":"diffusion"},{"id":"2408.01812","title":"Leveraging BEV Paradigm for Ground-to-Aerial Image Synthesis","created":"2024-08-03","cited_by_count":11,"area":"diffusion"},{"id":"2410.04738","title":"Diffusion Models in 3D Vision: A Survey","created":"2024-10-07","cited_by_count":11,"area":"diffusion"},{"id":"2312.04875","title":"MVDD: Multi-View Depth Diffusion Models","created":"2023-12-08","cited_by_count":10,"area":"diffusion"},{"id":"2402.17986","title":"PolyOculus: Simultaneous Multi-view Image-based Novel View Synthesis","created":"2024-02-28","cited_by_count":10,"area":null},{"id":"2406.13099","title":"Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models","created":"2024-06-18","cited_by_count":10,"area":"diffusion"},{"id":"2504.01689","title":"InvFusion: Bridging Supervised and Zero-shot Diffusion for Inverse Problems","created":"2025-04-02","cited_by_count":10,"area":"diffusion"},{"id":"2512.03045","title":"CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models","created":"2025-12-02","cited_by_count":10,"area":"diffusion"},{"id":"2310.05833","title":"A Bias-Variance-Covariance Decomposition of Kernel Scores for Generative Models","created":"2023-10-09","cited_by_count":8,"area":null},{"id":"2311.14494","title":"MVControl: Adding Conditional Control to Multi-view Diffusion for Controllable Text-to-3D Generation","created":"2023-11-24","cited_by_count":8,"area":"diffusion"},{"id":"2505.01172","title":"FreePCA: Integrating Consistency Information across Long-short Frames in Training-free Long Video Generation via Principal Component Analysis","created":"2025-05-02","cited_by_count":8,"area":null},{"id":"2511.01767","title":"Wonder3D++: Cross-domain Diffusion for High-fidelity 3D Generation from a Single Image","created":"2025-11-03","cited_by_count":8,"area":"diffusion"},{"id":"2602.03242","title":"InstaDrive: Instance-Aware Driving World Models for Realistic and Consistent Video Generation","created":"2026-02-03","cited_by_count":8,"area":"wm"},{"id":"2311.16203","title":"ChatTraffic: Text-to-Traffic Generation via Diffusion Model","created":"2023-11-27","cited_by_count":7,"area":"diffusion"},{"id":"2312.13324","title":"ShowRoom3D: Text to High-Quality 3D Room Generation Using 3D Priors","created":"2023-12-20","cited_by_count":7,"area":"diffusion"},{"id":"2411.13549","title":"KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2507.05678","title":"LiON-LoRA: Rethinking LoRA Fusion to Unify Controllable Spatial and Temporal Generation for Video Diffusion","created":"2025-07-08","cited_by_count":7,"area":"diffusion"},{"id":"2411.10947","title":"Direct and Explicit 3D Generation from a Single Image","created":"2024-11-17","cited_by_count":6,"area":null},{"id":"2502.13335","title":"Geometry-Aware Diffusion Models for Multiview Scene Inpainting","created":"2025-02-18","cited_by_count":6,"area":"diffusion"},{"id":"2503.12720","title":"Towards Open-World Generation of Stereo Images and Unsupervised Matching","created":"2025-03-17","cited_by_count":6,"area":null},{"id":"2509.06579","title":"CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis","created":"2025-09-08","cited_by_count":6,"area":"diffusion"},{"id":"2403.10242","title":"GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting","created":"2024-03-15","cited_by_count":5,"area":"diffusion"},{"id":"2508.03690","title":"Veila: Panoramic LiDAR Generation from a Monocular RGB Image","created":"2025-08-05","cited_by_count":5,"area":"wm"},{"id":"2312.08892","title":"VaLID: Variable-Length Input Diffusion for Novel View Synthesis","created":"2023-12-14","cited_by_count":4,"area":null},{"id":"2407.09672","title":"Mixed-View Panorama Synthesis using Geospatially Guided Diffusion","created":"2024-07-12","cited_by_count":4,"area":"diffusion"},{"id":"2501.02913","title":"Pointmap-Conditioned Diffusion for Consistent Novel View Synthesis","created":"2025-01-06","cited_by_count":4,"area":null},{"id":"2503.17804","title":"DVG-Diffusion: Dual-View Guided Diffusion Model for CT Reconstruction from X-Rays","created":"2025-03-22","cited_by_count":4,"area":"diffusion"},{"id":"2504.04532","title":"BrainMRDiff: A Diffusion Model for Anatomically Consistent Brain MRI Synthesis","created":"2025-04-06","cited_by_count":4,"area":"diffusion"},{"id":"2309.11525","title":"Light Field Diffusion for Single-View Novel View Synthesis","created":"2023-09-20","cited_by_count":3,"area":"diffusion"},{"id":"2406.04337","title":"Coherent Zero-Shot Visual Instruction Generation","created":"2024-06-06","cited_by_count":3,"area":"diffusion"},{"id":"2408.01678","title":"iControl3D: An Interactive System for Controllable 3D Scene Generation","created":"2024-08-03","cited_by_count":3,"area":null},{"id":"2503.19673","title":"MultimodalStudio: A Heterogeneous Sensor Dataset and Framework for Neural Rendering across Multiple Imaging Modalities","created":"2025-03-25","cited_by_count":3,"area":null},{"id":"2508.13091","title":"DMS:Diffusion-Based Multi-Baseline Stereo Generation for Improving Self-Supervised Depth Estimation","created":"2025-08-18","cited_by_count":3,"area":"diffusion"},{"id":"2509.00843","title":"Look Beyond: Two-Stage Scene View Generation via Panorama and Video Diffusion","created":"2025-08-31","cited_by_count":3,"area":"diffusion"},{"id":"2312.08071","title":"Novel View Synthesis with View-Dependent Effects from a Single Image","created":"2023-12-13","cited_by_count":2,"area":null},{"id":"2312.13832","title":"SyncDreamer for 3D Reconstruction of Endangered Animal Species with NeRF and NeuS","created":"2023-12-21","cited_by_count":2,"area":null},{"id":"2508.04050","title":"DOMR: Establishing Cross-View Segmentation via Dense Object Matching","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2512.07197","title":"SUCCESS-GS: Survey of Compactness and Compression for Efficient Static and Dynamic Gaussian Splatting","created":"2025-12-08","cited_by_count":2,"area":null},{"id":"2312.11774","title":"Text-Image Conditioned Diffusion for Consistent Text-to-3D Generation","created":"2023-12-19","cited_by_count":1,"area":"diffusion"}],"next_cursor":"100"}