{"list":"other","total":72,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"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":"2208.01626","title":"Prompt-to-Prompt Image Editing with Cross Attention Control","created":"2022-08-02","cited_by_count":2431},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"id":"2310.08528","title":"4D Gaussian Splatting for Real-Time Dynamic Scene Rendering","created":"2023-10-12","cited_by_count":1157},{"id":"2404.02905","title":"Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction","created":"2024-04-03","cited_by_count":1023},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1704.00675","title":"The 2017 DAVIS Challenge on Video Object Segmentation","created":"2017-04-03","cited_by_count":957},{"id":"2501.03575","title":"Cosmos World Foundation Model Platform for Physical AI","created":"2025-01-07","cited_by_count":864},{"id":"2308.09713","title":"Dynamic 3D Gaussians: Tracking by Persistent Dynamic View Synthesis","created":"2023-08-18","cited_by_count":737},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2412.20404","title":"Open-Sora: Democratizing Efficient Video Production for All","created":"2024-12-29","cited_by_count":652},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2312.17090","title":"Q-Align: Teaching LMMs for Visual Scoring via Discrete Text-Defined Levels","created":"2023-12-28","cited_by_count":503},{"id":"2310.10642","title":"Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting","created":"2023-10-16","cited_by_count":476},{"id":"2312.00732","title":"Gaussian Grouping: Segment and Edit Anything in 3D Scenes","created":"2023-12-01","cited_by_count":393},{"id":"2211.13221","title":"Latent Video Diffusion Models for High-Fidelity Long Video Generation","created":"2022-11-23","cited_by_count":388},{"id":"2212.05032","title":"Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis","created":"2022-12-09","cited_by_count":388},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"2305.15393","title":"LayoutGPT: Compositional Visual Planning and Generation with Large Language Models","created":"2023-05-24","cited_by_count":347},{"id":"2312.14937","title":"SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes","created":"2023-12-04","cited_by_count":347},{"id":"2311.14521","title":"GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting","created":"2023-11-24","cited_by_count":335},{"id":"2304.03373","title":"Training-Free Layout Control with Cross-Attention Guidance","created":"2023-04-06","cited_by_count":313},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2411.02385","title":"How Far is Video Generation from World Model: A Physical Law Perspective","created":"2024-11-04","cited_by_count":212},{"id":"2405.14832","title":"Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer","created":"2024-05-23","cited_by_count":210},{"id":"2301.11280","title":"Text-To-4D Dynamic Scene Generation","created":"2023-01-26","cited_by_count":205},{"id":"2312.17142","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","created":"2023-12-28","cited_by_count":194},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179},{"id":"2312.13763","title":"Align Your Gaussians: Text-to-4D with Dynamic 3D Gaussians and Composed Diffusion Models","created":"2023-12-21","cited_by_count":169},{"id":"2311.16037","title":"GaussianEditor: Editing 3D Gaussians Delicately with Text Instructions","created":"2023-11-27","cited_by_count":168},{"id":"2306.13455","title":"DreamEditor: Text-Driven 3D Scene Editing with Neural Fields","created":"2023-06-23","cited_by_count":155},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117},{"id":"2303.12048","title":"Vox-E: Text-guided Voxel Editing of 3D Objects","created":"2023-03-21","cited_by_count":115},{"id":"2311.14603","title":"Animate124: Animating One Image to 4D Dynamic Scene","created":"2023-11-24","cited_by_count":115},{"id":"2403.08733","title":"GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing","created":"2024-03-13","cited_by_count":115},{"id":"2409.12957","title":"3DTopia-XL: Scaling High-quality 3D Asset Generation via Primitive Diffusion","created":"2024-09-19","cited_by_count":101},{"id":"2406.18717","title":"Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos","created":"2024-06-26","cited_by_count":97},{"id":"2401.09985","title":"WorldDreamer: Towards General World Models for Video Generation via Predicting Masked Tokens","created":"2024-01-18","cited_by_count":89},{"id":"2406.09455","title":"Pandora: Towards General World Model with Natural Language Actions and Video States","created":"2024-06-12","cited_by_count":86},{"id":"2401.14828","title":"TIP-Editor: An Accurate 3D Editor Following Both Text-Prompts And Image-Prompts","created":"2024-01-26","cited_by_count":77},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77},{"id":"2405.18991","title":"EasyAnimate: High-Performance Video Generation Framework with Hybrid Windows Attention and Reward Backpropagation","created":"2024-05-29","cited_by_count":77},{"id":"2406.07472","title":"4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models","created":"2024-06-11","cited_by_count":64},{"id":"2406.13527","title":"4K4DGen: Panoramic 4D Generation at 4K Resolution","created":"2024-06-19","cited_by_count":54},{"id":"2409.11211","title":"SplatFields: Neural Gaussian Splats for Sparse 3D and 4D Reconstruction","created":"2024-09-17","cited_by_count":52},{"id":"2403.16993","title":"Comp4D: LLM-Guided Compositional 4D Scene Generation","created":"2024-03-25","cited_by_count":50},{"id":"2404.01223","title":"Feature Splatting: Language-Driven Physics-Based Scene Synthesis and Editing","created":"2024-04-01","cited_by_count":45},{"id":"2405.18132","title":"EG4D: Explicit Generation of 4D Object without Score Distillation","created":"2024-05-28","cited_by_count":45},{"id":"2305.20082","title":"Control4D: Efficient 4D Portrait Editing with Text","created":"2023-05-31","cited_by_count":32},{"id":"2312.06655","title":"Sherpa3D: Boosting High-Fidelity Text-to-3D Generation via Coarse 3D Prior","created":"2023-12-11","cited_by_count":32},{"id":"2406.09402","title":"Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusion","created":"2024-06-13","cited_by_count":24},{"id":"2306.12760","title":"Blended-NeRF: Zero-Shot Object Generation and Blending in Existing Neural Radiance Fields","created":"2023-06-22","cited_by_count":23},{"id":"2407.06842","title":"Chat-Edit-3D: Interactive 3D Scene Editing via Text Prompts","created":"2024-07-09","cited_by_count":19},{"id":"2312.09313","title":"LatentEditor: Text Driven Local Editing of 3D Scenes","created":"2023-12-14","cited_by_count":17},{"id":"2410.12836","title":"EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing","created":"2024-10-03","cited_by_count":15},{"id":"2305.10722","title":"Discffusion: Discriminative Diffusion Models as Few-shot Vision and Language Learners","created":"2023-05-18","cited_by_count":14},{"id":"2503.20776","title":"Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields","created":"2025-03-26","cited_by_count":13},{"id":"2412.01792","title":"CTRL-D: Controllable Dynamic 3D Scene Editing with Personalized 2D Diffusion","created":"2024-12-02","cited_by_count":11},{"id":"2412.08948","title":"Mojito: Motion Trajectory and Intensity Control for Video Generation","created":"2024-12-12","cited_by_count":9},{"id":"2401.17895","title":"ReplaceAnything3D:Text-Guided 3D Scene Editing with Compositional Neural Radiance Fields","created":"2024-01-31","cited_by_count":7},{"id":"2405.04834","title":"FlexEControl: Flexible and Efficient Multimodal Control for Text-to-Image Generation","created":"2024-05-08","cited_by_count":5}],"next_cursor":null}