{"list":"other","total":54,"rows":[{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2210.02747","title":"Flow Matching for Generative Modeling","created":"2022-10-06","cited_by_count":5702},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"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":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2308.06571","title":"ModelScope Text-to-Video Technical Report","created":"2023-08-12","cited_by_count":658},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2404.02101","title":"CameraCtrl: Enabling Camera Control for Text-to-Video Generation","created":"2024-04-02","cited_by_count":460},{"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":"2312.16812","title":"Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis","created":"2023-12-28","cited_by_count":344},{"id":"2407.02371","title":"OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation","created":"2024-07-02","cited_by_count":341},{"id":"2305.08891","title":"Common Diffusion Noise Schedules and Sample Steps are Flawed","created":"2023-05-15","cited_by_count":310},{"id":"2412.00131","title":"Open-Sora Plan: Open-Source Large Video Generation Model","created":"2024-11-28","cited_by_count":296},{"id":"2503.11647","title":"ReCamMaster: Camera-Controlled Generative Rendering from A Single Video","created":"2025-03-14","cited_by_count":287},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218},{"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":"1910.12713","title":"Few-shot Video-to-Video Synthesis","created":"2019-10-28","cited_by_count":197},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194},{"id":"2501.03847","title":"Diffusion as Shader: 3D-aware Video Diffusion for Versatile Video Generation Control","created":"2025-01-07","cited_by_count":185},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"2301.02238","title":"HyperReel: High-Fidelity 6-DoF Video with Ray-Conditioned Sampling","created":"2023-01-05","cited_by_count":174},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117},{"id":"2405.17414","title":"Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control","created":"2024-05-27","cited_by_count":117},{"id":"2312.04524","title":"RAVE: Randomized Noise Shuffling for Fast and Consistent Video Editing with Diffusion Models","created":"2023-12-07","cited_by_count":114},{"id":"2403.12365","title":"GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation","created":"2024-03-19","cited_by_count":100},{"id":"2406.18717","title":"Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos","created":"2024-06-26","cited_by_count":97},{"id":"2402.11095","title":"GIM: Learning Generalizable Image Matcher From Internet Videos","created":"2024-02-16","cited_by_count":75},{"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":"2007.08509","title":"World-Consistent Video-to-Video Synthesis","created":"2020-07-16","cited_by_count":69},{"id":"2411.19324","title":"Trajectory Attention for Fine-grained Video Motion Control","created":"2024-11-28","cited_by_count":63},{"id":"2407.08674","title":"Still-Moving: Customized Video Generation without Customized Video Data","created":"2024-07-11","cited_by_count":50},{"id":"2501.02690","title":"GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking","created":"2025-01-05","cited_by_count":39},{"id":"2412.05275","title":"MotionFlow: Attention-Driven Motion Transfer in Video Diffusion Models","created":"2024-12-06","cited_by_count":17},{"id":"2412.05355","title":"MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance","created":"2024-12-06","cited_by_count":14},{"id":"2505.23758","title":"LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers","created":"2025-05-29","cited_by_count":12},{"id":"2403.19738","title":"MIST: Mitigating Intersectional Bias with Disentangled Cross-Attention Editing in Text-to-Image Diffusion Models","created":"2024-03-28","cited_by_count":10},{"id":"2406.14599","title":"Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models","created":"2024-06-20","cited_by_count":7},{"id":"2403.19645","title":"Learn Once, Edit Anywhere: Visual Direction Transfer for Diffusion Models","created":"2024-03-28","cited_by_count":6},{"id":"2406.00457","title":"The Curious Case of End Token: A Zero-Shot Disentangled Image Editing using CLIP","created":"2024-06-01","cited_by_count":4}],"next_cursor":null}