{"total":117,"rows":[{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2412.01506","title":"Structured 3D Latents for Scalable and Versatile 3D Generation","created":"2024-12-02","cited_by_count":770,"area":null},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739,"area":null},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333,"area":null},{"id":"2311.01455","title":"RoboGen: Towards Unleashing Infinite Data for Automated Robot Learning via Generative Simulation","created":"2023-11-02","cited_by_count":218,"area":null},{"id":"2311.09217","title":"DMV3D: Denoising Multi-View Diffusion using 3D Large Reconstruction Model","created":"2023-11-15","cited_by_count":214,"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":"2401.09340","title":"SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding","created":"2024-01-17","cited_by_count":133,"area":null},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112,"area":null},{"id":"2403.12019","title":"LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation","created":"2024-03-18","cited_by_count":92,"area":null},{"id":"2407.02445","title":"Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials","created":"2024-07-02","cited_by_count":66,"area":null},{"id":"2402.05235","title":"SPAD : Spatially Aware Multiview Diffusers","created":"2024-02-07","cited_by_count":62,"area":null},{"id":"2403.14613","title":"DreamReward: Text-to-3D Generation with Human Preference","created":"2024-03-21","cited_by_count":56,"area":null},{"id":"2412.14963","title":"IDOL: Instant Photorealistic 3D Human Creation from a Single Image","created":"2024-12-19","cited_by_count":55,"area":null},{"id":"2407.02430","title":"Meta 3D TextureGen: Fast and Consistent Texture Generation for 3D Objects","created":"2024-07-02","cited_by_count":52,"area":null},{"id":"2403.12957","title":"GVGEN: Text-to-3D Generation with Volumetric Representation","created":"2024-03-19","cited_by_count":51,"area":null},{"id":"2403.09675","title":"Open-Universe Indoor Scene Generation using LLM Program Synthesis and Uncurated Object Databases","created":"2024-02-05","cited_by_count":45,"area":null},{"id":"2406.09401","title":"MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations","created":"2024-06-13","cited_by_count":40,"area":null},{"id":"2403.15385","title":"LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis","created":"2024-03-22","cited_by_count":39,"area":null},{"id":"2312.04424","title":"Cascade-Zero123: One Image to Highly Consistent 3D with Self-Prompted Nearby Views","created":"2023-12-07","cited_by_count":33,"area":null},{"id":"2404.07984","title":"View Selection for 3D Captioning via Diffusion Ranking","created":"2024-04-11","cited_by_count":32,"area":null},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2404.19752","title":"Visual Fact Checker: Enabling High-Fidelity Detailed Caption Generation","created":"2024-04-30","cited_by_count":28,"area":null},{"id":"2411.19654","title":"TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting","created":"2024-11-29","cited_by_count":28,"area":null},{"id":"2505.06227","title":"Anymate: A Dataset and Baselines for Learning 3D Object Rigging","created":"2025-05-09","cited_by_count":27,"area":null},{"id":"2310.10644","title":"TOSS:High-quality Text-guided Novel View Synthesis from a Single Image","created":"2023-10-16","cited_by_count":26,"area":null},{"id":"2510.20155","title":"PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding","created":"2025-10-23","cited_by_count":26,"area":null},{"id":"2402.03327","title":"Uni3D-LLM: Unifying Point Cloud Perception, Generation and Editing with Large Language Models","created":"2024-01-09","cited_by_count":25,"area":null},{"id":"2502.01720","title":"Generating Multi-Image Synthetic Data for Text-to-Image Customization","created":"2025-02-03","cited_by_count":25,"area":null},{"id":"2412.11258","title":"GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs","created":"2024-12-15","cited_by_count":23,"area":null},{"id":"2503.22420","title":"Unveiling the Mist over 3D Vision-Language Understanding: Object-centric Evaluation with Chain-of-Analysis","created":"2025-03-28","cited_by_count":23,"area":null},{"id":"2403.11878","title":"InTeX: Interactive Text-to-texture Synthesis via Unified Depth-aware Inpainting","created":"2024-03-18","cited_by_count":22,"area":null},{"id":"2401.07727","title":"HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation","created":"2024-01-15","cited_by_count":21,"area":null},{"id":"2404.16510","title":"Interactive3D: Create What You Want by Interactive 3D Generation","created":"2024-04-25","cited_by_count":21,"area":null},{"id":"2603.03283","title":"Utonia: Toward One Encoder for All Point Clouds","created":"2026-03-03","cited_by_count":21,"area":null},{"id":"2509.10813","title":"InternScenes: A Large-scale Simulatable Indoor Scene Dataset with Realistic Layouts","created":"2025-09-13","cited_by_count":20,"area":null},{"id":"2406.18462","title":"GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality","created":"2024-06-26","cited_by_count":18,"area":null},{"id":"2409.03718","title":"Geometry Image Diffusion: Fast and Data-Efficient Text-to-3D with Image-Based Surface Representation","created":"2024-09-05","cited_by_count":17,"area":null},{"id":"2501.07574","title":"UnCommon Objects in 3D","created":"2025-01-13","cited_by_count":17,"area":null},{"id":"2310.17914","title":"3D-Aware Visual Question Answering about Parts, Poses and Occlusions","created":"2023-10-27","cited_by_count":16,"area":null},{"id":"2412.16919","title":"TAR3D: Creating High-Quality 3D Assets via Next-Part Prediction","created":"2024-12-22","cited_by_count":16,"area":null},{"id":"2407.09822","title":"VividDreamer: Invariant Score Distillation For Hyper-Realistic Text-to-3D Generation","created":"2024-07-13","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":"2405.09431","title":"A Survey On Text-to-3D Contents Generation In The Wild","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2412.04470","title":"Turbo3D: Ultra-fast Text-to-3D Generation","created":"2024-12-05","cited_by_count":14,"area":null},{"id":"2403.13289","title":"Text-to-3D Shape Generation","created":"2024-03-20","cited_by_count":13,"area":null},{"id":"2404.19760","title":"Lightplane: Highly-Scalable Components for Neural 3D Fields","created":"2024-04-30","cited_by_count":13,"area":null},{"id":"2406.11579","title":"Duoduo CLIP: Efficient 3D Understanding with Multi-View Images","created":"2024-06-17","cited_by_count":12,"area":null},{"id":"2412.09997","title":"GT23D-Bench: A Comprehensive General Text-to-3D Generation Benchmark","created":"2024-12-13","cited_by_count":12,"area":null},{"id":"2511.13211","title":"3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale","created":"2025-11-17","cited_by_count":12,"area":null},{"id":"2502.00342","title":"Embodied Intelligence for 3D Understanding: A Survey on 3D Scene Question Answering","created":"2025-02-01","cited_by_count":11,"area":null},{"id":"2408.10935","title":"Large Point-to-Gaussian Model for Image-to-3D Generation","created":"2024-08-20","cited_by_count":10,"area":null},{"id":"2408.15966","title":"More Text, Less Point: Towards 3D Data-Efficient Point-Language Understanding","created":"2024-08-28","cited_by_count":10,"area":null},{"id":"2410.20723","title":"CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians","created":"2024-10-28","cited_by_count":10,"area":null},{"id":"2503.22194","title":"ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation","created":"2025-03-28","cited_by_count":10,"area":null},{"id":"2312.03026","title":"Uni3DL: Unified Model for 3D and Language Understanding","created":"2023-12-05","cited_by_count":9,"area":null},{"id":"2403.15009","title":"TexRO: Generating Delicate Textures of 3D Models by Recursive Optimization","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2506.18527","title":"Auto-Regressively Generating Multi-View Consistent Images","created":"2025-06-23","cited_by_count":9,"area":null},{"id":"2410.10745","title":"FlexGen: Flexible Multi-View Generation from Text and Image Inputs","created":"2024-10-14","cited_by_count":8,"area":null},{"id":"2405.17104","title":"LLM-Optic: Unveiling the Capabilities of Large Language Models for Universal Visual Grounding","created":"2024-05-27","cited_by_count":7,"area":null},{"id":"2410.05217","title":"Organizing Unstructured Image Collections using Natural Language","created":"2024-10-07","cited_by_count":7,"area":null},{"id":"2411.17945","title":"MARVEL-40M+: Multi-Level Visual Elaboration for High-Fidelity Text-to-3D Content Creation","created":"2024-11-26","cited_by_count":7,"area":null},{"id":"2412.19142","title":"CLIP-GS: Unifying Vision-Language Representation with 3D Gaussian Splatting","created":"2024-12-26","cited_by_count":7,"area":null},{"id":"2604.05212","title":"Boxer: Robust Lifting of Open-World 2D Bounding Boxes to 3D","created":"2026-04-06","cited_by_count":7,"area":null},{"id":"2407.14007","title":"Multi-modal Relation Distillation for Unified 3D Representation Learning","created":"2024-07-19","cited_by_count":6,"area":null},{"id":"2409.11315","title":"MinD-3D++: Advancing fMRI-Based 3D Reconstruction with High-Quality Textured Mesh Generation and a Comprehensive Dataset","created":"2024-09-17","cited_by_count":6,"area":null},{"id":"2503.05283","title":"Escaping Plato's Cave: Towards the Alignment of 3D and Text Latent Spaces","created":"2025-03-07","cited_by_count":6,"area":null},{"id":"2601.01676","title":"LabelAny3D: Label Any Object 3D in the Wild","created":"2026-01-04","cited_by_count":6,"area":null},{"id":"2406.09126","title":"3D-AVS: LiDAR-based 3D Auto-Vocabulary Segmentation","created":"2024-06-13","cited_by_count":5,"area":null},{"id":"2408.05938","title":"Deep Geometric Moments Promote Shape Consistency in Text-to-3D Generation","created":"2024-08-12","cited_by_count":5,"area":null},{"id":"2410.06475","title":"3D Representation Methods: A Survey","created":"2024-10-09","cited_by_count":5,"area":null},{"id":"2502.17860","title":"UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2405.18258","title":"Text-only Synthesis for Image Captioning","created":"2024-05-28","cited_by_count":4,"area":null},{"id":"2408.14253","title":"Text3DAug -- Prompted Instance Augmentation for LiDAR Perception","created":"2024-08-26","cited_by_count":4,"area":null},{"id":"2503.17044","title":"ExCap3D: Expressive 3D Scene Understanding via Object Captioning with Varying Detail","created":"2025-03-21","cited_by_count":4,"area":null},{"id":"2309.07917","title":"Looking at words and points with attention: a benchmark for text-to-shape coherence","created":"2023-09-14","cited_by_count":3,"area":null},{"id":"2407.04180","title":"Slice-100K: A Multimodal Dataset for Extrusion-based 3D Printing","created":"2024-07-04","cited_by_count":3,"area":null},{"id":"2504.14975","title":"Cyc3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization","created":"2025-04-21","cited_by_count":3,"area":null},{"id":"2507.14555","title":"Descrip3D: Enhancing Large Language Model-based 3D Scene Understanding with Object-Level Text Descriptions","created":"2025-07-19","cited_by_count":3,"area":null},{"id":"2411.18135","title":"ModeDreamer: Mode Guiding Score Distillation for Text-to-3D Generation using Reference Image Prompts","created":"2024-11-27","cited_by_count":2,"area":null},{"id":"2501.00651","title":"Taming Feed-forward Reconstruction Models as Latent Encoders for 3D Generative Models","created":"2024-12-31","cited_by_count":2,"area":null},{"id":"2505.22394","title":"PacTure: Efficient PBR Texture Generation on Packed Views with Visual Autoregressive Models","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2506.20946","title":"Consistent Zero-shot 3D Texture Synthesis Using Geometry-aware Diffusion and Temporal Video Models","created":"2025-06-26","cited_by_count":2,"area":null},{"id":"2509.22112","title":"Large Material Gaussian Model for Relightable 3D Generation","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2601.07333","title":"OSCAR: Open-Set CAD Retrieval from a Language Prompt and a Single Image","created":"2026-01-12","cited_by_count":2,"area":null},{"id":"2602.18830","title":"Spatial-Temporal State Propagation Autoregressive Model for 4D Object Generation","created":"2026-02-21","cited_by_count":2,"area":null},{"id":"2603.05607","title":"DreamCAD: Scaling Multi-modal CAD Generation using Differentiable Parametric Surfaces","created":"2026-03-05","cited_by_count":2,"area":null},{"id":"2604.17472","title":"UniMesh: Unifying 3D Mesh Understanding and Generation","created":"2026-04-19","cited_by_count":2,"area":null},{"id":"2607.01803","title":"PixGS: Pixel-Space Diffusion for Direct 3D Gaussian Splat Generation","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2310.09503","title":"JM3D & JM3D-LLM: Elevating 3D Understanding with Joint Multi-modal Cues","created":"2023-10-14","cited_by_count":1,"area":null},{"id":"2407.14419","title":"HOTS3D: Hyper-Spherical Optimal Transport for Semantic Alignment of Text-to-3D Generation","created":"2024-07-19","cited_by_count":1,"area":null},{"id":"2408.04909","title":"Surveying the Landscape of Image Captioning Evaluation: A Comprehensive Taxonomy, Trends and Metrics Analysis","created":"2024-08-09","cited_by_count":1,"area":null},{"id":"2410.10037","title":"GALA: Geometry-Aware Local Adaptive Grids for Detailed 3D Generation","created":"2024-10-13","cited_by_count":1,"area":null},{"id":"2503.00605","title":"GenVDM: Generating Vector Displacement Maps From a Single Image","created":"2025-03-01","cited_by_count":1,"area":null},{"id":"2503.14002","title":"MeshFleet: Filtered and Annotated 3D Vehicle Dataset for Domain Specific Generative Modeling","created":"2025-03-18","cited_by_count":1,"area":null},{"id":"2508.20470","title":"Droplet3D: Commonsense Priors from Videos Facilitate 3D Generation","created":"2025-08-28","cited_by_count":1,"area":null},{"id":"2512.17302","title":"MatLat: Material Latent Space for PBR Texture Generation","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2512.23628","title":"Memorization in 3D Shape Generation: An Empirical Study","created":"2025-12-29","cited_by_count":1,"area":null},{"id":"2603.14152","title":"SK-Adapter: Skeleton-Based Structural Control for Native 3D Generation","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2608.15710","title":"Beyond Single Object: Learning 3D Relations with Large Language Models","created":"2026-08-16","cited_by_count":1,"area":null}],"next_cursor":"100"}