{"total":203,"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":"2311.06214","title":"Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Reconstruction Model","created":"2023-11-10","cited_by_count":378,"area":"diffusion"},{"id":"2311.12871","title":"An Embodied Generalist Agent in 3D World","created":"2023-11-18","cited_by_count":365,"area":"agents"},{"id":"2308.16911","title":"PointLLM: Empowering Large Language Models to Understand Point Clouds","created":"2023-08-31","cited_by_count":333,"area":null},{"id":"2310.08529","title":"GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models","created":"2023-10-12","cited_by_count":255,"area":"diffusion"},{"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":"2311.18651","title":"LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning","created":"2023-11-30","cited_by_count":210,"area":"lr"},{"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":"2312.03700","title":"OneLLM: One Framework to Align All Modalities with Language","created":"2023-12-06","cited_by_count":187,"area":"mllm"},{"id":"2311.16918","title":"RichDreamer: A Generalizable Normal-Depth Diffusion Model for Detail Richness in Text-to-3D","created":"2023-11-28","cited_by_count":168,"area":"diffusion"},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137,"area":"mllm"},{"id":"2405.05945","title":"Lumina-T2X: Transforming Text into Any Modality, Resolution, and Duration via Flow-based Large Diffusion Transformers","created":"2024-05-09","cited_by_count":137,"area":"diffusion"},{"id":"2310.02596","title":"SweetDreamer: Aligning Geometric Priors in 2D Diffusion for Consistent Text-to-3D","created":"2023-10-04","cited_by_count":134,"area":"diffusion"},{"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":"2406.18583","title":"Lumina-Next: Making Lumina-T2X Stronger and Faster with Next-DiT","created":"2024-06-05","cited_by_count":132,"area":"diffusion"},{"id":"2310.19415","title":"Text-to-3D with Classifier Score Distillation","created":"2023-10-30","cited_by_count":128,"area":"diffusion"},{"id":"2312.13913","title":"Paint3D: Paint Anything 3D with Lighting-Less Texture Diffusion Models","created":"2023-12-21","cited_by_count":123,"area":"diffusion"},{"id":"2412.03632","title":"MV-Adapter: Multi-view Consistent Image Generation Made Easy","created":"2024-12-04","cited_by_count":112,"area":null},{"id":"2405.20674","title":"4Diffusion: Multi-view Video Diffusion Model for 4D Generation","created":"2024-05-31","cited_by_count":104,"area":"diffusion"},{"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":"2403.12019","title":"LN3DIFF++: Scalable Latent Neural Fields Diffusion for Speedy 3D Generation","created":"2024-03-18","cited_by_count":92,"area":null},{"id":"2311.18799","title":"X-InstructBLIP: A Framework for aligning X-Modal instruction-aware representations to LLMs and Emergent Cross-modal Reasoning","created":"2023-11-30","cited_by_count":80,"area":"lr"},{"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":"2312.02980","title":"GPT4Point: A Unified Framework for Point-Language Understanding and Generation","created":"2023-12-05","cited_by_count":71,"area":"mllm"},{"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":"2412.18608","title":"PartGen: Part-level 3D Generation and Reconstruction with Multi-View Diffusion Models","created":"2024-12-24","cited_by_count":62,"area":"diffusion"},{"id":"2310.02977","title":"T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation","created":"2023-10-04","cited_by_count":57,"area":"diffusion"},{"id":"2403.12034","title":"VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Models","created":"2024-03-18","cited_by_count":56,"area":"diffusion"},{"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":"2409.02389","title":"Multi-modal Situated Reasoning in 3D Scenes","created":"2024-09-04","cited_by_count":51,"area":"lr"},{"id":"2311.15980","title":"Direct2.5: Diverse Text-to-3D Generation via Multi-view 2.5D Diffusion","created":"2023-11-27","cited_by_count":50,"area":"diffusion"},{"id":"2501.16764","title":"DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation","created":"2025-01-28","cited_by_count":50,"area":"diffusion"},{"id":"2312.09222","title":"Mosaic-SDF for 3D Generative Models","created":"2023-12-14","cited_by_count":48,"area":"diffusion"},{"id":"2312.08754","title":"UniDream: Unifying Diffusion Priors for Relightable Text-to-3D Generation","created":"2023-12-14","cited_by_count":47,"area":"diffusion"},{"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":"2411.16318","title":"One Diffusion to Generate Them All","created":"2024-11-25","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":"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":"2312.11459","title":"VolumeDiffusion: Flexible Text-to-3D Generation with Efficient Volumetric Encoder","created":"2023-12-18","cited_by_count":39,"area":"diffusion"},{"id":"2403.15385","title":"LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis","created":"2024-03-22","cited_by_count":39,"area":null},{"id":"2411.16856","title":"SAR3D: Autoregressive 3D Object Generation and Understanding via Multi-scale 3D VQVAE","created":"2024-11-25","cited_by_count":39,"area":"mllm"},{"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":"2406.07549","title":"A3VLM: Actionable Articulation-Aware Vision Language Model","created":"2024-06-11","cited_by_count":33,"area":"mllm"},{"id":"2404.07984","title":"View Selection for 3D Captioning via Diffusion Ranking","created":"2024-04-11","cited_by_count":32,"area":null},{"id":"2504.09975","title":"OctGPT: Octree-based Multiscale Autoregressive Models for 3D Shape Generation","created":"2025-04-14","cited_by_count":30,"area":"diffusion"},{"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":"2308.02299","title":"RegionBLIP: A Unified Multi-modal Pre-training Framework for Holistic and Regional Comprehension","created":"2023-08-03","cited_by_count":27,"area":"mllm"},{"id":"2407.02040","title":"ScaleDreamer: Scalable Text-to-3D Synthesis with Asynchronous Score Distillation","created":"2024-07-02","cited_by_count":27,"area":"diffusion"},{"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":"2403.09981","title":"Controllable Text-to-3D Generation via Surface-Aligned Gaussian Splatting","created":"2024-03-15","cited_by_count":26,"area":"diffusion"},{"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":"2407.08725","title":"MetaUrban: An Embodied AI Simulation Platform for Urban Micromobility","created":"2024-07-11","cited_by_count":21,"area":"wm"},{"id":"2603.03283","title":"Utonia: Toward One Encoder for All Point Clouds","created":"2026-03-03","cited_by_count":21,"area":null},{"id":"2312.09069","title":"PI3D: Efficient Text-to-3D Generation with Pseudo-Image Diffusion","created":"2023-12-14","cited_by_count":20,"area":"diffusion"},{"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":"2506.23329","title":"IR3D-Bench: Evaluating Vision-Language Model Scene Understanding as Agentic Inverse Rendering","created":"2025-06-29","cited_by_count":19,"area":"mllm"},{"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":"2406.04322","title":"DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data","created":"2024-06-06","cited_by_count":15,"area":"diffusion"},{"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":"2408.13055","title":"Atlas Gaussians Diffusion for 3D Generation","created":"2024-08-23","cited_by_count":15,"area":"diffusion"},{"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":"2606.01057","title":"3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code","created":"2026-05-31","cited_by_count":15,"area":"agents"},{"id":"2402.02972","title":"Retrieval-Augmented Score Distillation for Text-to-3D Generation","created":"2024-02-05","cited_by_count":14,"area":"rag"},{"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":"2410.20178","title":"LLMs Can Evolve Continually on Modality for X-Modal Reasoning","created":"2024-10-26","cited_by_count":12,"area":"lr"},{"id":"2411.08033","title":"GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object Generation","created":"2024-11-12","cited_by_count":12,"area":"diffusion"},{"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":"2410.04738","title":"Diffusion Models in 3D Vision: A Survey","created":"2024-10-07","cited_by_count":11,"area":"diffusion"},{"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":"2507.07781","title":"SURPRISE3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes","created":"2025-07-10","cited_by_count":11,"area":"lr"},{"id":"2311.17851","title":"Leveraging VLM-Based Pipelines to Annotate 3D Objects","created":"2023-11-29","cited_by_count":10,"area":"mllm"},{"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}],"next_cursor":"100"}