{"total":147,"rows":[{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367,"area":null},{"id":"2312.03806","title":"XCube: Large-Scale 3D Generative Modeling using Sparse Voxel Hierarchies","created":"2023-12-06","cited_by_count":189,"area":null},{"id":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174,"area":null},{"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":"2406.11824","title":"Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation","created":"2024-06-17","cited_by_count":137,"area":null},{"id":"2403.01248","title":"SceneCraft: An LLM Agent for Synthesizing 3D Scene as Blender Code","created":"2024-03-02","cited_by_count":134,"area":"agents"},{"id":"2405.14868","title":"Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis","created":"2024-05-23","cited_by_count":117,"area":null},{"id":"2405.11656","title":"URDFormer: A Pipeline for Constructing Articulated Simulation Environments from Real-World Images","created":"2024-05-19","cited_by_count":111,"area":null},{"id":"2310.12945","title":"3D-GPT: Procedural 3D Modeling with Large Language Models","created":"2023-10-19","cited_by_count":95,"area":null},{"id":"2507.21809","title":"HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixels","created":"2025-07-29","cited_by_count":94,"area":null},{"id":"2503.17316","title":"Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors","created":"2025-03-21","cited_by_count":72,"area":null},{"id":"2311.12631","title":"GPT4Motion: Scripting Physical Motions in Text-to-Video Generation via Blender-Oriented GPT Planning","created":"2023-11-21","cited_by_count":61,"area":"diffusion"},{"id":"2401.06056","title":"MatSynth: A Modern PBR Materials Dataset","created":"2024-01-11","cited_by_count":42,"area":null},{"id":"2308.11408","title":"MatFuse: Controllable Material Generation with Diffusion Models","created":"2023-08-22","cited_by_count":39,"area":"diffusion"},{"id":"2504.13157","title":"AerialMegaDepth: Learning Aerial-Ground Reconstruction and View Synthesis","created":"2025-04-17","cited_by_count":39,"area":null},{"id":"2312.07063","title":"Template Free Reconstruction of Human-object Interaction with Procedural Interaction Generation","created":"2023-12-12","cited_by_count":38,"area":"diffusion"},{"id":"2510.13802","title":"Trace Anything: Representing Any Video in 4D via Trajectory Fields","created":"2025-10-15","cited_by_count":33,"area":null},{"id":"2504.01786","title":"BlenderGym: Benchmarking Foundational Model Systems for Graphics Editing","created":"2025-04-02","cited_by_count":31,"area":null},{"id":"2605.15187","title":"Articraft: An Agentic System for Scalable Articulated 3D Asset Generation","created":"2026-05-14","cited_by_count":30,"area":"agents"},{"id":"2403.09439","title":"3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation","created":"2024-03-14","cited_by_count":29,"area":null},{"id":"2506.00742","title":"ArtiScene: Language-Driven Artistic 3D Scene Generation Through Image Intermediary","created":"2025-05-31","cited_by_count":28,"area":null},{"id":"2401.08739","title":"EgoGen: An Egocentric Synthetic Data Generator","created":"2024-01-16","cited_by_count":27,"area":null},{"id":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2401.11067","title":"Make-A-Shape: a Ten-Million-scale 3D Shape Model","created":"2024-01-20","cited_by_count":25,"area":null},{"id":"2412.07770","title":"From an Image to a Scene: Learning to Imagine the World from a Million 360 Videos","created":"2024-12-10","cited_by_count":23,"area":null},{"id":"2404.17672","title":"BlenderAlchemy: Editing 3D Graphics with Vision-Language Models","created":"2024-04-26","cited_by_count":22,"area":"mllm"},{"id":"2408.04567","title":"Sketch2Scene: Automatic Generation of Interactive 3D Game Scenes from User's Casual Sketches","created":"2024-08-08","cited_by_count":21,"area":null},{"id":"2412.14166","title":"MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data","created":"2024-12-18","cited_by_count":21,"area":null},{"id":"2502.15601","title":"WorldCraft: Photo-Realistic 3D World Creation and Customization via LLM Agents","created":"2025-02-21","cited_by_count":21,"area":"agents"},{"id":"2503.13424","title":"Infinite Mobility: Scalable High-Fidelity Synthesis of Articulated Objects via Procedural Generation","created":"2025-03-17","cited_by_count":19,"area":null},{"id":"2510.06218","title":"EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark","created":"2025-10-07","cited_by_count":19,"area":null},{"id":"2511.16825","title":"WorldGen: From Text to Traversable and Interactive 3D Worlds","created":"2025-11-20","cited_by_count":19,"area":null},{"id":"2602.11757","title":"Code2Worlds: Empowering Coding LLMs for 4D World Generation","created":"2026-02-12","cited_by_count":19,"area":null},{"id":"2409.13456","title":"Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?","created":"2024-09-20","cited_by_count":18,"area":null},{"id":"2501.08983","title":"Compositional Generative Model of Unbounded 4D Cities","created":"2025-01-15","cited_by_count":17,"area":null},{"id":"2605.09423","title":"SimWorld Studio: Automatic Environment Generation with Evolving Coding Agent for Embodied Agent Learning","created":"2026-05-10","cited_by_count":17,"area":"agents"},{"id":"2408.10453","title":"Kubrick: Multimodal Agent Collaborations for Synthetic Video Generation","created":"2024-08-19","cited_by_count":16,"area":"agents"},{"id":"2508.14461","title":"Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering","created":"2025-08-20","cited_by_count":16,"area":"diffusion"},{"id":"2510.21682","title":"WorldGrow: Generating Infinite 3D World","created":"2025-10-24","cited_by_count":16,"area":null},{"id":"2606.01057","title":"3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code","created":"2026-05-31","cited_by_count":15,"area":"agents"},{"id":"2509.14981","title":"SPATIALGEN: Layout-guided 3D Indoor Scene Generation","created":"2025-09-18","cited_by_count":14,"area":null},{"id":"2601.16982","title":"AnyView: Synthesizing Any Novel View in Dynamic Scenes","created":"2026-01-23","cited_by_count":12,"area":null},{"id":"2409.05688","title":"LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow","created":"2024-09-09","cited_by_count":11,"area":null},{"id":"2409.20283","title":"Match Stereo Videos via Bidirectional Alignment","created":"2024-09-30","cited_by_count":11,"area":null},{"id":"2605.19587","title":"SceneCode: Executable World Programs for Editable Indoor Scenes with Articulated Objects","created":"2026-05-19","cited_by_count":11,"area":null},{"id":"2411.08017","title":"Wavelet Latent Diffusion (Wala): Billion-Parameter 3D Generative Model with Compact Wavelet Encodings","created":"2024-11-12","cited_by_count":10,"area":"diffusion"},{"id":"2501.18623","title":"VLMaterial: Procedural Material Generation with Large Vision-Language Models","created":"2025-01-27","cited_by_count":9,"area":"mllm"},{"id":"2506.22291","title":"RoomCraft: Controllable and Complete 3D Indoor Scene Generation","created":"2025-06-27","cited_by_count":9,"area":null},{"id":"2603.07106","title":"AutoUE: Automated Generation of 3D Games in Unreal Engine via Multi-Agent Systems","created":"2026-03-07","cited_by_count":9,"area":"agents"},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","cited_by_count":8,"area":null},{"id":"2607.01766","title":"SimWorlds: A Multi-Agent System for Dynamic 3D Scene Creation","created":"2026-07-02","cited_by_count":8,"area":"agents"},{"id":"2608.05248","title":"WorldClaw: Agentic 3D Open-World Generation at Scale","created":"2026-08-05","cited_by_count":8,"area":"agents"},{"id":"2403.18351","title":"Generating Diverse Agricultural Data for Vision-Based Farming Applications","created":"2024-03-27","cited_by_count":7,"area":null},{"id":"2411.18807","title":"Reconstructing Animals and the Wild","created":"2024-11-27","cited_by_count":7,"area":null},{"id":"2412.15200","title":"DI-PCG: Diffusion-based Efficient Inverse Procedural Content Generation for High-quality 3D Asset Creation","created":"2024-12-19","cited_by_count":7,"area":null},{"id":"2504.16930","title":"What Makes Good Synthetic Training Data for Zero-Shot Stereo Matching?","created":"2025-04-23","cited_by_count":7,"area":null},{"id":"2403.19517","title":"XScale-NVS: Cross-Scale Novel View Synthesis with Hash Featurized Manifold","created":"2024-03-28","cited_by_count":6,"area":null},{"id":"2412.07660","title":"Proc-GS: Procedural Building Generation for City Assembly with 3D Gaussians","created":"2024-12-10","cited_by_count":6,"area":null},{"id":"2508.08384","title":"Spatiotemporally Consistent Indoor Lighting Estimation with Diffusion Priors","created":"2025-08-11","cited_by_count":6,"area":"diffusion"},{"id":"2508.18597","title":"SemLayoutDiff: Semantic Layout Generation with Diffusion Model for Indoor Scene Synthesis","created":"2025-08-26","cited_by_count":6,"area":"diffusion"},{"id":"2509.23728","title":"M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generation","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2603.12238","title":"SceneAssistant: A Visual Feedback Agent for Open-Vocabulary 3D Scene Generation","created":"2026-03-12","cited_by_count":6,"area":"agents"},{"id":"2406.12671","title":"GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models","created":"2024-06-18","cited_by_count":5,"area":null},{"id":"2506.14315","title":"ImmerseGen: Agent-Guided Immersive World Generation with Alpha-Textured Proxies","created":"2025-06-17","cited_by_count":5,"area":null},{"id":"2509.05263","title":"LatticeWorld: A Multimodal Large Language Model-Empowered Framework for Interactive Complex World Generation","created":"2025-09-05","cited_by_count":5,"area":"wm"},{"id":"2601.16272","title":"GR3EN: Generative Relighting for 3D Environments","created":"2026-01-22","cited_by_count":5,"area":"diffusion"},{"id":"2310.04416","title":"Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic","created":"2023-10-06","cited_by_count":4,"area":null},{"id":"2507.00981","title":"Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations","created":"2025-07-01","cited_by_count":4,"area":null},{"id":"2510.26800","title":"OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2512.22351","title":"VULCAN: Tool-Augmented Multi Agents for Iterative 3D Object Arrangement","created":"2025-12-26","cited_by_count":4,"area":"mllm"},{"id":"2601.07143","title":"EZBlender: Efficient 3D Editing with Plan-and-ReAct Agent","created":"2026-01-12","cited_by_count":4,"area":"agents"},{"id":"2603.13856","title":"Can AI Understand the Language of Origami?","created":"2026-03-14","cited_by_count":4,"area":null},{"id":"2605.05207","title":"Syn4D: A Multiview Synthetic 4D Dataset","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2608.26238","title":"Procedura: Agentic 3D Modeling with Procedural Control","created":"2026-08-26","cited_by_count":4,"area":"agents"},{"id":"2310.08471","title":"WinSyn: A High Resolution Testbed for Synthetic Data","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2404.18750","title":"Survey on Datasets for Perception in Unstructured Outdoor Environments","created":"2024-04-29","cited_by_count":3,"area":null},{"id":"2503.23062","title":"Shape and Texture Recognition in Large Vision-Language Models","created":"2025-03-29","cited_by_count":3,"area":"mllm"},{"id":"2510.05532","title":"Teamwork: Collaborative Diffusion with Low-rank Coordination and Adaptation","created":"2025-10-07","cited_by_count":3,"area":"diffusion"},{"id":"2603.24836","title":"WAFT-Stereo: Warping-Alone Field Transforms for Stereo Matching","created":"2026-03-25","cited_by_count":3,"area":null},{"id":"2603.29089","title":"WorldFlow3D: Flowing Through 3D Distributions for Unbounded World Generation","created":"2026-03-31","cited_by_count":3,"area":null},{"id":"2605.12449","title":"LychSim: A Controllable and Interactive Simulation Framework for Vision Research","created":"2026-05-12","cited_by_count":3,"area":null},{"id":"2403.03309","title":"Learning Zero-Shot Material States Segmentation, by Implanting Natural Image Patterns in Synthetic Data","created":"2024-03-05","cited_by_count":2,"area":null},{"id":"2403.04940","title":"A spatiotemporal style transfer algorithm for dynamic visual stimulus generation","created":"2024-03-07","cited_by_count":2,"area":null},{"id":"2503.06784","title":"Infinite Leagues Under the Sea: Photorealistic 3D Underwater Terrain Generation by Latent Fractal Diffusion Models","created":"2025-03-09","cited_by_count":2,"area":"diffusion"},{"id":"2503.08111","title":"MaRI: Material Retrieval Integration across Domains","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2505.03623","title":"Bounding Box-Guided Diffusion for Synthesizing Industrial Images and Segmentation Map","created":"2025-05-06","cited_by_count":2,"area":"diffusion"},{"id":"2507.08400","title":"PanMatch: Unleashing the Potential of Large Vision Models for Unified Matching Models","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2511.00041","title":"Endowing GPT-4 with a Humanoid Body: Building the Bridge Between Off-the-Shelf VLMs and the Physical World","created":"2025-10-28","cited_by_count":2,"area":null},{"id":"2601.02793","title":"StableDPT: Temporal Stable Monocular Video Depth Estimation","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2604.04925","title":"SimpleProc: Fully Procedural Synthetic Data from Simple Rules for Multi-View Stereo","created":"2026-04-06","cited_by_count":2,"area":null},{"id":"2607.26646","title":"Genie Sim PanoWorld: An Infinite Indoor 3D World Generation Pipeline via Panoramic Scene Modeling and Simulation","created":"2026-07-29","cited_by_count":2,"area":null},{"id":"2608.15659","title":"WorldRover: A Scalable Synthetic Video Data Engine for World Exploration with Rich Annotations","created":"2026-08-16","cited_by_count":2,"area":null},{"id":"2608.20534","title":"Grounded-Exo2Ego: Structured Semantic Grounding for Robust Exocentric-to-Egocentric Video Generation","created":"2026-08-20","cited_by_count":2,"area":null},{"id":"2311.10129","title":"Intelligent Generation of Graphical Game Assets: A Conceptual Framework and Systematic Review of the State of the Art","created":"2023-11-16","cited_by_count":1,"area":null},{"id":"2404.00593","title":"LAESI: Leaf Area Estimation with Synthetic Imagery","created":"2024-03-31","cited_by_count":1,"area":null},{"id":"2408.17339","title":"Enhancing Underwater Imaging with 4-D Light Fields: Dataset and Method","created":"2024-08-30","cited_by_count":1,"area":null},{"id":"2506.21357","title":"CoPa-SG: Dense Scene Graphs with Parametric and Proto-Relations","created":"2025-06-26","cited_by_count":1,"area":null},{"id":"2509.22864","title":"ControlEvents: Controllable Synthesis of Event Camera Datawith Foundational Prior from Image Diffusion Models","created":"2025-09-26","cited_by_count":1,"area":"diffusion"},{"id":"2509.24441","title":"NeoWorld: Neural Simulation of Explorable Virtual Worlds via Progressive 3D Unfolding","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.19814","title":"Toward A Better Understanding of Monocular Depth Evaluation","created":"2025-10-22","cited_by_count":1,"area":null}],"next_cursor":"100"}