{"list":"other","total":51,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2305.16213","title":"ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation","created":"2023-05-25","cited_by_count":1219},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"2407.01392","title":"Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion","created":"2024-07-01","cited_by_count":681},{"id":"2211.07600","title":"Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures","created":"2022-11-14","cited_by_count":506},{"id":"2306.02018","title":"VideoComposer: Compositional Video Synthesis with Motion Controllability","created":"2023-06-03","cited_by_count":464},{"id":"2302.04867","title":"UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models","created":"2023-02-09","cited_by_count":450},{"id":"2312.02696","title":"Analyzing and Improving the Training Dynamics of Diffusion Models","created":"2023-12-05","cited_by_count":402},{"id":"2311.06214","title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","created":"2023-11-10","cited_by_count":378},{"id":"2403.12008","title":"SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusion","created":"2024-03-18","cited_by_count":364},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356},{"id":"2302.01721","title":"TEXTure: Text-Guided Texturing of 3D Shapes","created":"2023-02-03","cited_by_count":304},{"id":"2105.01859","title":"Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors","created":"2021-05-05","cited_by_count":246},{"id":"2303.11396","title":"Text2Tex: Text-driven Texture Synthesis via Diffusion Models","created":"2023-03-20","cited_by_count":235},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2504.12369","title":"WorldMem: Long-term Consistent World Simulation with Memory","created":"2025-04-16","cited_by_count":168},{"id":"2310.19415","title":"Text-to-3D with Classifier Score Distillation","created":"2023-10-30","cited_by_count":128},{"id":"2503.05638","title":"TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models","created":"2025-03-07","cited_by_count":125},{"id":"2312.13913","title":"Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models","created":"2023-12-21","cited_by_count":123},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112},{"id":"2412.07774","title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics","created":"2024-12-10","cited_by_count":102},{"id":"2310.13772","title":"TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models","created":"2023-10-20","cited_by_count":87},{"id":"2204.02411","title":"Texturify: Generating Textures on 3D Shape Surfaces","created":"2022-04-05","cited_by_count":65},{"id":"2412.01821","title":"World-consistent Video Diffusion with Explicit 3D Modeling","created":"2024-12-02","cited_by_count":65},{"id":"2308.10490","title":"Texture Generation on 3D Meshes with Point-UV Diffusion","created":"2023-08-21","cited_by_count":63},{"id":"2401.09416","title":"TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion","created":"2024-01-17","cited_by_count":52},{"id":"2407.02430","title":"Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects","created":"2024-07-02","cited_by_count":52},{"id":"2411.14740","title":"TEXGen: a Generative Diffusion Model for Mesh Textures","created":"2024-11-22","cited_by_count":46},{"id":"2403.12010","title":"VideoMV: Consistent Multi-View Generation Based on Large Video Generative Model","created":"2024-03-18","cited_by_count":45},{"id":"2412.19761","title":"Generative Video Propagation","created":"2024-12-27","cited_by_count":36},{"id":"2304.05868","title":"Mesh2Tex: Generating Mesh Textures from Image Queries","created":"2023-04-12","cited_by_count":31},{"id":"2503.08037","title":"ObjectMover: Generative Object Movement with Video Prior","created":"2025-03-11","cited_by_count":30},{"id":"2504.08541","title":"Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset","created":"2025-04-11","cited_by_count":29},{"id":"2303.14587","title":"PAniC-3D: Stylized Single-view 3D Reconstruction from Portraits of Anime Characters","created":"2023-03-25","cited_by_count":17},{"id":"2305.03040","title":"TUVF: Learning Generalizable Texture UV Radiance Fields","created":"2023-05-04","cited_by_count":9},{"id":"2505.15800","title":"Interspatial Attention for Efficient 4D Human Video Generation","created":"2025-05-21","cited_by_count":7}],"next_cursor":null}