{"total":205,"rows":[{"id":"2309.16653","title":"DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation","created":"2023-09-28","cited_by_count":843,"area":null},{"id":"2311.17042","title":"Adversarial Diffusion Distillation","created":"2023-11-28","cited_by_count":759,"area":"diffusion"},{"id":"2406.13897","title":"CLAY: A Controllable Large-scale Generative Model for Creating High-quality 3D Assets","created":"2024-05-30","cited_by_count":455,"area":"diffusion"},{"id":"2309.11499","title":"DreamLLM: Synergistic Multimodal Comprehension and Creation","created":"2023-09-20","cited_by_count":297,"area":"mllm"},{"id":"2303.11989","title":"Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models","created":"2023-03-21","cited_by_count":245,"area":null},{"id":"2511.00062","title":"World Simulation with Video Foundation Models for Physical AI","created":"2025-10-28","cited_by_count":200,"area":null},{"id":"2312.17142","title":"DreamGaussian4D: Generative 4D Gaussian Splatting","created":"2023-12-28","cited_by_count":194,"area":null},{"id":"2404.13026","title":"PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation","created":"2024-04-19","cited_by_count":191,"area":"wm"},{"id":"2311.17984","title":"4D-fy: Text-to-4D Generation Using Hybrid Score Distillation Sampling","created":"2023-11-29","cited_by_count":185,"area":null},{"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,"area":"diffusion"},{"id":"2304.06025","title":"DreamPose: Fashion Image-to-Video Synthesis via Stable Diffusion","created":"2023-04-12","cited_by_count":167,"area":"diffusion"},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161,"area":"diffusion"},{"id":"2302.01133","title":"SceneScape: Text-Driven Consistent Scene Generation","created":"2023-02-02","cited_by_count":160,"area":null},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156,"area":"diffusion"},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156,"area":null},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154,"area":"diffusion"},{"id":"2303.17015","title":"HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion","created":"2023-03-29","cited_by_count":152,"area":null},{"id":"2406.10324","title":"L4GM: Large 4D Gaussian Reconstruction Model","created":"2024-06-14","cited_by_count":144,"area":null},{"id":"2407.17470","title":"SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency","created":"2024-07-24","cited_by_count":144,"area":"diffusion"},{"id":"2307.11335","title":"Tri-MipRF: Tri-Mip Representation for Efficient Anti-Aliasing Neural Radiance Fields","created":"2023-07-21","cited_by_count":143,"area":null},{"id":"2310.07204","title":"State of the Art on Diffusion Models for Visual Computing","created":"2023-10-11","cited_by_count":127,"area":"diffusion"},{"id":"2311.02848","title":"Consistent4D: Consistent 360{\\deg} Dynamic Object Generation from Monocular Video","created":"2023-11-06","cited_by_count":125,"area":null},{"id":"2312.17225","title":"4DGen: Grounded 4D Content Generation with Spatial-temporal Consistency","created":"2023-12-28","cited_by_count":117,"area":"diffusion"},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117,"area":null},{"id":"2311.14603","title":"Animate124: Animating One Image to 4D Dynamic Scene","created":"2023-11-24","cited_by_count":115,"area":"diffusion"},{"id":"2405.20674","title":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","created":"2024-05-31","cited_by_count":104,"area":"diffusion"},{"id":"2306.09329","title":"DreamHuman: Animatable 3D Avatars from Text","created":"2023-06-15","cited_by_count":102,"area":null},{"id":"2403.14939","title":"STAG4D: Spatial-Temporal Anchored Generative 4D Gaussians","created":"2024-03-22","cited_by_count":102,"area":"diffusion"},{"id":"2403.12365","title":"GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation","created":"2024-03-19","cited_by_count":100,"area":null},{"id":"2405.16645","title":"Diffusion4D: Fast Spatial-temporal Consistent 4D Generation via Video Diffusion Models","created":"2024-05-26","cited_by_count":100,"area":"diffusion"},{"id":"2504.20995","title":"TesserAct: Learning 4D Embodied World Models","created":"2025-04-29","cited_by_count":94,"area":"wm"},{"id":"2306.07349","title":"ATT3D: Amortized Text-to-3D Object Synthesis","created":"2023-06-06","cited_by_count":87,"area":null},{"id":"2409.18114","title":"EdgeRunner: Auto-regressive Auto-encoder for Artistic Mesh Generation","created":"2024-09-26","cited_by_count":87,"area":null},{"id":"2311.16854","title":"A Unified Approach for Text- and Image-guided 4D Scene Generation","created":"2023-11-28","cited_by_count":82,"area":"diffusion"},{"id":"2403.17920","title":"TC4D: Trajectory-Conditioned Text-to-4D Generation","created":"2024-03-26","cited_by_count":77,"area":null},{"id":"2403.02234","title":"3DTopia: Large Text-to-3D Generation Model with Hybrid Diffusion Priors","created":"2024-03-04","cited_by_count":74,"area":"diffusion"},{"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,"area":null},{"id":"2406.07472","title":"4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models","created":"2024-06-11","cited_by_count":64,"area":"diffusion"},{"id":"2405.02280","title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","created":"2024-05-03","cited_by_count":63,"area":null},{"id":"2305.06131","title":"Generative AI meets 3D: A Survey on Text-to-3D in AIGC Era","created":"2023-05-10","cited_by_count":61,"area":null},{"id":"2404.03736","title":"SC4D: Sparse-Controlled Video-to-4D Generation and Motion Transfer","created":"2024-04-04","cited_by_count":61,"area":null},{"id":"2410.06756","title":"DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation","created":"2024-10-09","cited_by_count":58,"area":null},{"id":"2407.11398","title":"Animate3D: Animating Any 3D Model with Multi-view Video Diffusion","created":"2024-07-16","cited_by_count":56,"area":"diffusion"},{"id":"2403.16993","title":"Comp4D: LLM-Guided Compositional 4D Scene Generation","created":"2024-03-25","cited_by_count":50,"area":"diffusion"},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50,"area":null},{"id":"2311.13608","title":"Breathing Life Into Sketches Using Text-to-Video Priors","created":"2023-11-21","cited_by_count":48,"area":null},{"id":"2503.16396","title":"SV4D 2.0: Enhancing Spatio-Temporal Consistency in Multi-View Video Diffusion for High-Quality 4D Generation","created":"2025-03-20","cited_by_count":48,"area":"diffusion"},{"id":"2502.09615","title":"RigAnything: Template-Free Autoregressive Rigging for Diverse 3D Assets","created":"2025-02-13","cited_by_count":47,"area":null},{"id":"2304.04262","title":"A Comprehensive Survey on Knowledge Distillation of Diffusion Models","created":"2023-04-09","cited_by_count":45,"area":"diffusion"},{"id":"2405.18132","title":"EG4D: Explicit Generation of 4D Object without Score Distillation","created":"2024-05-28","cited_by_count":45,"area":"diffusion"},{"id":"2505.18151","title":"WonderPlay: Dynamic 3D Scene Generation from a Single Image and Actions","created":"2025-05-23","cited_by_count":45,"area":null},{"id":"2401.08742","title":"Efficient4D: Fast Dynamic 3D Object Generation from a Single-view Video","created":"2024-01-16","cited_by_count":44,"area":null},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2406.01476","title":"DreamPhysics: Learning Physics-Based 3D Dynamics with Video Diffusion Priors","created":"2024-06-03","cited_by_count":41,"area":"diffusion"},{"id":"2509.19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation","created":"2025-09-23","cited_by_count":41,"area":"diffusion"},{"id":"2406.08659","title":"Vivid-ZOO: Multi-View Video Generation with Diffusion Model","created":"2024-06-12","cited_by_count":40,"area":"diffusion"},{"id":"2309.12276","title":"LLMR: Real-time Prompting of Interactive Worlds using Large Language Models","created":"2023-09-21","cited_by_count":39,"area":null},{"id":"2304.10535","title":"Farm3D: Learning Articulated 3D Animals by Distilling 2D Diffusion","created":"2023-04-20","cited_by_count":38,"area":"diffusion"},{"id":"2405.16822","title":"Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels","created":"2024-05-27","cited_by_count":38,"area":null},{"id":"2406.09417","title":"Rethinking Score Distillation as a Bridge Between Image Distributions","created":"2024-06-13","cited_by_count":38,"area":"diffusion"},{"id":"2410.18084","title":"DynamicCity: Large-Scale 4D Occupancy Generation from Dynamic Scenes","created":"2024-10-23","cited_by_count":38,"area":"wm"},{"id":"2401.00909","title":"Taming Mode Collapse in Score Distillation for Text-to-3D Generation","created":"2023-12-31","cited_by_count":36,"area":null},{"id":"2501.00601","title":"DreamDrive: Generative 4D Scene Modeling from Street View Images","created":"2024-12-31","cited_by_count":35,"area":"wm"},{"id":"2503.20785","title":"Free4D: Tuning-free 4D Scene Generation with Spatial-Temporal Consistency","created":"2025-03-26","cited_by_count":35,"area":null},{"id":"2305.10503","title":"OR-NeRF: Object Removing from 3D Scenes Guided by Multiview Segmentation with Neural Radiance Fields","created":"2023-05-17","cited_by_count":34,"area":null},{"id":"2508.13154","title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy","created":"2025-08-18","cited_by_count":34,"area":"diffusion"},{"id":"2507.23785","title":"Gaussian Variation Field Diffusion for High-fidelity Video-to-4D Synthesis","created":"2025-07-31","cited_by_count":33,"area":"diffusion"},{"id":"2305.20082","title":"Control4D: Efficient 4D Portrait Editing with Text","created":"2023-05-31","cited_by_count":32,"area":null},{"id":"2506.09982","title":"AnimateAnyMesh: A Feed-Forward 4D Foundation Model for Text-Driven Universal Mesh Animation","created":"2025-06-11","cited_by_count":32,"area":null},{"id":"2308.06725","title":"CLE Diffusion: Controllable Light Enhancement Diffusion Model","created":"2023-08-13","cited_by_count":30,"area":"diffusion"},{"id":"2401.06614","title":"Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking","created":"2024-01-12","cited_by_count":29,"area":"diffusion"},{"id":"2312.03795","title":"AnimatableDreamer: Text-Guided Non-rigid 3D Model Generation and Reconstruction with Canonical Score Distillation","created":"2023-12-06","cited_by_count":28,"area":null},{"id":"2402.01166","title":"A Comprehensive Survey on 3D Content Generation","created":"2024-02-02","cited_by_count":28,"area":null},{"id":"2403.15064","title":"Recent Trends in 3D Reconstruction of General Non-Rigid Scenes","created":"2024-03-22","cited_by_count":28,"area":null},{"id":"2411.16819","title":"Pathways on the Image Manifold: Image Editing via Video Generation","created":"2024-11-25","cited_by_count":27,"area":"diffusion"},{"id":"2412.04462","title":"4Real-Video: Learning Generalizable Photo-Realistic 4D Video Diffusion","created":"2024-12-05","cited_by_count":27,"area":"diffusion"},{"id":"2504.17788","title":"Dynamic Camera Poses and Where to Find Them","created":"2025-04-24","cited_by_count":27,"area":null},{"id":"2404.09833","title":"Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video","created":"2024-04-15","cited_by_count":26,"area":null},{"id":"2410.07164","title":"AvatarGO: Zero-shot 4D Human-Object Interaction Generation and Animation","created":"2024-10-09","cited_by_count":25,"area":"diffusion"},{"id":"2404.02148","title":"Diffusion$^2$: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models","created":"2024-04-02","cited_by_count":24,"area":"diffusion"},{"id":"2410.10774","title":"Cavia: Camera-controllable Multi-view Video Diffusion with View-Integrated Attention","created":"2024-10-14","cited_by_count":24,"area":"diffusion"},{"id":"2505.05474","title":"3D Scene Generation: A Survey","created":"2025-05-08","cited_by_count":24,"area":"diffusion"},{"id":"2409.07179","title":"Phy124: Fast Physics-Driven 4D Content Generation from a Single Image","created":"2024-09-11","cited_by_count":23,"area":"diffusion"},{"id":"2411.16800","title":"Phys4DGen: Physics-Compliant 4D Generation with Multi-Material Composition Perception","created":"2024-11-25","cited_by_count":23,"area":null},{"id":"2306.04619","title":"ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections","created":"2023-06-07","cited_by_count":22,"area":"diffusion"},{"id":"2510.25765","title":"FreeArt3D: Training-Free Articulated Object Generation using 3D Diffusion","created":"2025-10-29","cited_by_count":22,"area":"diffusion"},{"id":"2510.06208","title":"ShapeGen4D: Towards High Quality 4D Shape Generation from Videos","created":"2025-10-07","cited_by_count":21,"area":null},{"id":"2407.03300","title":"DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents","created":"2024-07-03","cited_by_count":20,"area":"diffusion"},{"id":"2410.07155","title":"Trans4D: Realistic Geometry-Aware Transition for Compositional Text-to-4D Synthesis","created":"2024-10-09","cited_by_count":19,"area":"diffusion"},{"id":"2405.14017","title":"MagicPose4D: Crafting Articulated Models with Appearance and Motion Control","created":"2024-05-22","cited_by_count":18,"area":null},{"id":"2303.17546","title":"PAIR-Diffusion: A Comprehensive Multimodal Object-Level Image Editor","created":"2023-03-30","cited_by_count":17,"area":"diffusion"},{"id":"2506.23361","title":"OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions","created":"2025-06-29","cited_by_count":17,"area":null},{"id":"2507.13344","title":"Diffuman4D: 4D Consistent Human View Synthesis from Sparse-View Videos with Spatio-Temporal Diffusion Models","created":"2025-07-17","cited_by_count":17,"area":"diffusion"},{"id":"2302.10916","title":"How Generative AI models such as ChatGPT can be (Mis)Used in SPC Practice, Education, and Research? An Exploratory Study","created":"2023-02-17","cited_by_count":16,"area":null},{"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,"area":"diffusion"},{"id":"2405.19957","title":"PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting","created":"2024-05-30","cited_by_count":15,"area":"diffusion"},{"id":"2407.12684","title":"4Dynamic: Text-to-4D Generation with Hybrid Priors","created":"2024-07-17","cited_by_count":15,"area":"diffusion"},{"id":"2412.20720","title":"4D Gaussian Splatting: Modeling Dynamic Scenes with Native 4D Primitives","created":"2024-12-30","cited_by_count":15,"area":null},{"id":"2503.04641","title":"Simulating the Real World: A Unified Survey of Multimodal Generative Models","created":"2025-03-06","cited_by_count":15,"area":null},{"id":"2403.11427","title":"BAGS: Building Animatable Gaussian Splatting from a Monocular Video with Diffusion Priors","created":"2024-03-18","cited_by_count":14,"area":"diffusion"}],"next_cursor":"100"}