{"list":"other","total":52,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"1904.05866","title":"Expressive Body Capture: 3D Hands, Face, and Body from a Single Image","created":"2019-04-11","cited_by_count":1612},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2401.03048","title":"Latte: Latent Diffusion Transformer for Video Generation","created":"2024-01-05","cited_by_count":546},{"id":"2410.05954","title":"Pyramidal Flow Matching for Efficient Video Generative Modeling","created":"2024-10-08","cited_by_count":366},{"id":"2305.12577","title":"Guided Motion Diffusion for Controllable Human Motion Synthesis","created":"2023-05-21","cited_by_count":223},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202},{"id":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182},{"id":"2310.15169","title":"FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling","created":"2023-10-23","cited_by_count":180},{"id":"2312.03884","title":"WonderJourney: Going from Anywhere to Everywhere","created":"2023-12-06","cited_by_count":158},{"id":"2411.04928","title":"DimensionX: Create Any 3D and 4D Scenes from a Single Image with Controllable Video Diffusion","created":"2024-11-07","cited_by_count":140},{"id":"2305.18264","title":"Gen-L-Video: Multi-Text to Long Video Generation via Temporal Co-Denoising","created":"2023-05-29","cited_by_count":139},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136},{"id":"2411.00769","title":"GameGen-X: Interactive Open-world Game Video Generation","created":"2024-11-01","cited_by_count":128},{"id":"2106.02019","title":"Neural Actor: Neural Free-view Synthesis of Human Actors with Pose Control","created":"2021-06-03","cited_by_count":106},{"id":"2303.12218","title":"Compositional 3D Scene Generation using Locally Conditioned Diffusion","created":"2023-03-21","cited_by_count":101},{"id":"2410.02757","title":"Loong: Generating Minute-level Long Videos with Autoregressive Language Models","created":"2024-10-03","cited_by_count":99},{"id":"2406.17758","title":"MotionBooth: Motion-Aware Customized Text-to-Video Generation","created":"2024-06-25","cited_by_count":93},{"id":"1803.01837","title":"ST-GAN: Spatial Transformer Generative Adversarial Networks for Image Compositing","created":"2018-03-05","cited_by_count":90},{"id":"2504.14899","title":"Uni3C: Unifying Precisely 3D-Enhanced Camera and Human Motion Controls for Video Generation","created":"2025-04-21","cited_by_count":77},{"id":"2303.13450","title":"Set-the-Scene: Global-Local Training for Generating Controllable NeRF Scenes","created":"2023-03-23","cited_by_count":75},{"id":"2403.02234","title":"3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors","created":"2024-03-04","cited_by_count":74},{"id":"2503.10625","title":"LHM: Large Animatable Human Reconstruction Model from a Single Image in Seconds","created":"2025-03-13","cited_by_count":61},{"id":"2408.13252","title":"LayerPano3D: Layered 3D Panorama for Hyper-Immersive Scene Generation","created":"2024-08-23","cited_by_count":53},{"id":"1904.05475","title":"Learning to Generate Synthetic Data via Compositing","created":"2019-04-10","cited_by_count":52},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50},{"id":"2310.16831","title":"PERF: Panoramic Neural Radiance Field from a Single Panorama","created":"2023-10-25","cited_by_count":45},{"id":"2410.16892","title":"VistaDream: Sampling multiview consistent images for single-view scene reconstruction","created":"2024-10-22","cited_by_count":38},{"id":"2408.11085","title":"GS-CPR: Efficient Camera Pose Refinement via 3D Gaussian Splatting","created":"2024-08-20","cited_by_count":31},{"id":"2412.03552","title":"Imagine360: Immersive 360 Video Generation from Perspective Anchor","created":"2024-12-04","cited_by_count":29},{"id":"2208.11905","title":"Neural Novel Actor: Learning a Generalized Animatable Neural Representation for Human Actors","created":"2022-08-25","cited_by_count":28},{"id":"2504.01956","title":"VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step","created":"2025-04-02","cited_by_count":27},{"id":"2405.18424","title":"3DitScene: Editing Any Scene via Language-guided Disentangled Gaussian Splatting","created":"2024-05-28","cited_by_count":25},{"id":"2303.05724","title":"3D Cinemagraphy from a Single Image","created":"2023-03-10","cited_by_count":24},{"id":"2410.15391","title":"Layout-your-3D: Controllable and Precise 3D Generation with 2D Blueprint","created":"2024-10-20","cited_by_count":21},{"id":"2207.11464","title":"Learning Object Placement via Dual-path Graph Completion","created":"2022-07-23","cited_by_count":20},{"id":"1809.02492","title":"On the Importance of Visual Context for Data Augmentation in Scene Understanding","created":"2018-09-06","cited_by_count":19},{"id":"2312.04543","title":"HyperDreamer: Hyper-Realistic 3D Content Generation and Editing from a Single Image","created":"2023-12-07","cited_by_count":17},{"id":"2304.03372","title":"TopNet: Transformer-based Object Placement Network for Image Compositing","created":"2023-04-06","cited_by_count":16},{"id":"2504.04294","title":"3R-GS: Best Practice in Optimizing Camera Poses Along with 3DGS","created":"2025-04-05","cited_by_count":11},{"id":"2410.06014","title":"SplaTraj: Camera Trajectory Generation with Semantic Gaussian Splatting","created":"2024-10-08","cited_by_count":10},{"id":"2504.08181","title":"TokenMotion: Decoupled Motion Control via Token Disentanglement for Human-centric Video Generation","created":"2025-04-11","cited_by_count":9},{"id":"2501.11508","title":"See In Detail: Enhancing Sparse-view 3D Gaussian Splatting with Local Depth and Semantic Regularization","created":"2025-01-20","cited_by_count":8},{"id":"2502.13234","title":"MotionMatcher: Motion Customization of Text-to-Video Diffusion Models via Motion Feature Matching","created":"2025-02-18","cited_by_count":3},{"id":"2504.12029","title":"Object Placement for Anything","created":"2025-04-16","cited_by_count":3}],"next_cursor":null}