{"list":"other","total":71,"rows":[{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"2503.20314","title":"Wan: Open and Advanced Large-Scale Video Generative Models","created":"2025-03-26","cited_by_count":2708},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2311.17982","title":"VBench: Comprehensive Benchmark Suite for Video Generative Models","created":"2023-11-29","cited_by_count":1822},{"id":"2412.03603","title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","created":"2024-12-03","cited_by_count":1660},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"2312.03641","title":"MotionCtrl: A Unified and Flexible Motion Controller for Video Generation","created":"2023-12-06","cited_by_count":580},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2503.07598","title":"VACE: All-in-One Video Creation and Editing","created":"2025-03-10","cited_by_count":479},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"id":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"2403.13298","title":"Rotary Position Embedding for Vision Transformer","created":"2024-03-20","cited_by_count":236},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2210.13445","title":"Monocular Dynamic View Synthesis: A Reality Check","created":"2022-10-24","cited_by_count":200},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170},{"id":"2406.02509","title":"CamCo: Camera-Controllable 3D-Consistent Image-to-Video Generation","created":"2024-06-04","cited_by_count":166},{"id":"2506.03141","title":"Context as Memory: Scene-Consistent Interactive Long Video Generation with Memory Retrieval","created":"2025-06-03","cited_by_count":163},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"2406.10126","title":"Training-free Camera Control for Video Generation","created":"2024-06-14","cited_by_count":122},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117},{"id":"2410.06205","title":"Round and Round We Go! What makes Rotary Positional Encodings useful?","created":"2024-10-08","cited_by_count":115},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98},{"id":"2402.03908","title":"EscherNet: A Generative Model for Scalable View Synthesis","created":"2024-02-06","cited_by_count":95},{"id":"2501.06336","title":"MEt3R: Measuring Multi-View Consistency in Generated Images","created":"2025-01-10","cited_by_count":95},{"id":"2310.10375","title":"GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers","created":"2023-10-16","cited_by_count":79},{"id":"2405.15364","title":"NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer","created":"2024-05-24","cited_by_count":79},{"id":"2405.17251","title":"GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping","created":"2024-05-27","cited_by_count":73},{"id":"2203.10157","title":"ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers","created":"2022-03-18","cited_by_count":70},{"id":"2411.05003","title":"ReCapture: Generative Video Camera Controls for User-Provided Videos using Masked Video Fine-Tuning","created":"2024-11-07","cited_by_count":70},{"id":"2406.18524","title":"MultiDiff: Consistent Novel View Synthesis from a Single Image","created":"2024-06-26","cited_by_count":68},{"id":"2411.19324","title":"Trajectory Attention for Fine-grained Video Motion Control","created":"2024-11-28","cited_by_count":63},{"id":"2506.03140","title":"CamCloneMaster: Enabling Reference-based Camera Control for Video Generation","created":"2025-06-03","cited_by_count":46},{"id":"2503.09151","title":"Reangle-A-Video: 4D Video Generation as Video-to-Video Translation","created":"2025-03-12","cited_by_count":35},{"id":"2411.16443","title":"SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis","created":"2024-11-25","cited_by_count":34},{"id":"2403.09176","title":"Switch Diffusion Transformer: Synergizing Denoising Tasks with Sparse Mixture-of-Experts","created":"2024-03-14","cited_by_count":31},{"id":"2505.05495","title":"Learning 3D Persistent Embodied World Models","created":"2025-05-05","cited_by_count":29},{"id":"2310.07138","title":"Denoising Task Routing for Diffusion Models","created":"2023-10-11","cited_by_count":28},{"id":"2312.15980","title":"HarmonyView: Harmonizing Consistency and Diversity in One-Image-to-3D","created":"2023-12-26","cited_by_count":28},{"id":"2501.06006","title":"CamCtrl3D: Single-Image Scene Exploration with Precise 3D Camera Control","created":"2025-01-10","cited_by_count":21},{"id":"2510.20385","title":"Positional Encoding Field","created":"2025-10-23","cited_by_count":20},{"id":"2503.22622","title":"Zero4D: Training-Free 4D Video Generation From Single Video Using Off-the-Shelf Video Diffusion","created":"2025-03-28","cited_by_count":16},{"id":"2503.12024","title":"SteerX: Creating Any Camera-Free 3D and 4D Scenes with Geometric Steering","created":"2025-03-15","cited_by_count":15},{"id":"2503.15855","title":"VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling","created":"2025-03-20","cited_by_count":14},{"id":"2507.12646","title":"Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos","created":"2025-07-16","cited_by_count":14},{"id":"2310.09647","title":"Point-DynRF: Point-based Dynamic Radiance Fields from a Monocular Video","created":"2023-10-14","cited_by_count":12},{"id":"2506.08004","title":"Dynamic View Synthesis as an Inverse Problem","created":"2025-06-09","cited_by_count":12},{"id":"2510.26796","title":"See4D: Pose-Free 4D Generation via Auto-Regressive Video Inpainting","created":"2025-10-30","cited_by_count":12},{"id":"2209.07105","title":"Bridging Implicit and Explicit Geometric Transformation for Single-Image View Synthesis","created":"2022-09-15","cited_by_count":11},{"id":"2405.17825","title":"Diffusion Model Patching via Mixture-of-Prompts","created":"2024-05-28","cited_by_count":11},{"id":"2510.03909","title":"Generating Human Motion Videos using a Cascaded Text-to-Video Framework","created":"2025-10-04","cited_by_count":4}],"next_cursor":null}