{"total":184,"rows":[{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774,"area":null},{"id":"2306.16928","title":"One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization","created":"2023-06-29","cited_by_count":560,"area":"diffusion"},{"id":"2410.13848","title":"Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generation","created":"2024-10-17","cited_by_count":457,"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":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237,"area":null},{"id":"2306.17115","title":"Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation","created":"2023-06-29","cited_by_count":228,"area":null},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203,"area":null},{"id":"2309.00615","title":"Point-Bind & Point-LLM: Aligning Point Cloud with Multi-modality for 3D Understanding, Generation, and Instruction Following","created":"2023-09-01","cited_by_count":194,"area":null},{"id":"2312.08168","title":"Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers","created":"2023-12-13","cited_by_count":175,"area":null},{"id":"2306.15880","title":"Towards Open Vocabulary Learning: A Survey","created":"2023-06-28","cited_by_count":166,"area":null},{"id":"2402.17766","title":"ShapeLLM: Universal 3D Object Understanding for Embodied Interaction","created":"2024-02-27","cited_by_count":137,"area":"mllm"},{"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":"2308.08769","title":"Chat-3D: Data-efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes","created":"2023-08-17","cited_by_count":129,"area":null},{"id":"2402.04717","title":"InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior","created":"2024-02-07","cited_by_count":117,"area":null},{"id":"2405.10370","title":"Grounded 3D-LLM with Referent Tokens","created":"2024-05-16","cited_by_count":115,"area":null},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2505.17412","title":"Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention","created":"2025-05-23","cited_by_count":110,"area":null},{"id":"2405.20853","title":"MeshXL: Neural Coordinate Field for Generative 3D Foundation Models","created":"2024-05-31","cited_by_count":103,"area":null},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","cited_by_count":87,"area":null},{"id":"2505.07747","title":"Step1X-3D: Towards High-Fidelity and Controllable Generation of Textured 3D Assets","created":"2025-05-12","cited_by_count":87,"area":"diffusion"},{"id":"2412.14042","title":"CAD-Recode: Reverse Engineering CAD Code from Point Clouds","created":"2024-12-18","cited_by_count":66,"area":null},{"id":"2311.15599","title":"UniRepLKNet: A Universal Perception Large-Kernel ConvNet for Audio, Video, Point Cloud, Time-Series and Image Recognition","created":"2023-11-27","cited_by_count":64,"area":null},{"id":"2405.20224","title":"EvaGaussians: Event Stream Assisted Gaussian Splatting from Blurry Images","created":"2024-05-29","cited_by_count":56,"area":null},{"id":"2509.20414","title":"SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent","created":"2025-09-24","cited_by_count":56,"area":"agents"},{"id":"2503.00513","title":"Inst3D-LMM: Instance-Aware 3D Scene Understanding with Multi-modal Instruction Tuning","created":"2025-03-01","cited_by_count":51,"area":"mllm"},{"id":"2406.17741","title":"Point-SAM: Promptable 3D Segmentation Model for Point Clouds","created":"2024-06-25","cited_by_count":50,"area":null},{"id":"2409.03757","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","created":"2024-09-05","cited_by_count":49,"area":null},{"id":"2503.18673","title":"Any6D: Model-free 6D Pose Estimation of Novel Objects","created":"2025-03-24","cited_by_count":49,"area":null},{"id":"2407.11895","title":"OmniBind: Large-scale Omni Multimodal Representation via Binding Spaces","created":"2024-07-16","cited_by_count":39,"area":null},{"id":"2408.10195","title":"SpaRP: Fast 3D Object Reconstruction and Pose Estimation from Sparse Views","created":"2024-08-19","cited_by_count":35,"area":"diffusion"},{"id":"2307.03135","title":"Distilling Large Vision-Language Model with Out-of-Distribution Generalizability","created":"2023-07-06","cited_by_count":33,"area":"mllm"},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2402.18490","title":"TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding","created":"2024-02-28","cited_by_count":27,"area":null},{"id":"2404.01491","title":"SUGAR: Pre-training 3D Visual Representations for Robotics","created":"2024-04-01","cited_by_count":26,"area":null},{"id":"2504.17695","title":"PICO: Reconstructing 3D People In Contact with Objects","created":"2025-04-24","cited_by_count":22,"area":null},{"id":"2310.08884","title":"Extending Multi-modal Contrastive Representations","created":"2023-10-13","cited_by_count":21,"area":null},{"id":"2504.05303","title":"InteractVLM: 3D Interaction Reasoning from 2D Foundational Models","created":"2025-04-07","cited_by_count":21,"area":null},{"id":"2403.09140","title":"Sculpt3D: Multi-View Consistent Text-to-3D Generation with Sparse 3D Prior","created":"2024-03-14","cited_by_count":20,"area":"diffusion"},{"id":"2507.02747","title":"DexVLG: Dexterous Vision-Language-Grasp Model at Scale","created":"2025-07-03","cited_by_count":20,"area":"vla"},{"id":"2405.04883","title":"FreeBind: Free Lunch in Unified Multimodal Space via Knowledge Fusion","created":"2024-05-08","cited_by_count":19,"area":null},{"id":"2311.01734","title":"Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training","created":"2023-11-03","cited_by_count":18,"area":null},{"id":"2408.16768","title":"SAM2Point: Segment Any 3D as Videos in Zero-shot and Promptable Manners","created":"2024-08-29","cited_by_count":18,"area":null},{"id":"2501.07819","title":"3UR-LLM: An End-to-End Multimodal Large Language Model for 3D Scene Understanding","created":"2025-01-14","cited_by_count":16,"area":"mllm"},{"id":"2312.09738","title":"3DAxiesPrompts: Unleashing the 3D Spatial Task Capabilities of GPT-4V","created":"2023-12-15","cited_by_count":15,"area":null},{"id":"2401.11395","title":"UniM-OV3D: Uni-Modality Open-Vocabulary 3D Scene Understanding with Fine-Grained Feature Representation","created":"2024-01-21","cited_by_count":15,"area":null},{"id":"2408.11567","title":"Positional Prompt Tuning for Efficient 3D Representation Learning","created":"2024-08-21","cited_by_count":15,"area":null},{"id":"2410.12836","title":"EditRoom: LLM-parameterized Graph Diffusion for Composable 3D Room Layout Editing","created":"2024-10-03","cited_by_count":15,"area":null},{"id":"2311.12144","title":"Applications of Large Scale Foundation Models for Autonomous Driving","created":"2023-11-20","cited_by_count":14,"area":"driving"},{"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":"2412.17226","title":"OLiDM: Object-aware LiDAR Diffusion Models for Autonomous Driving","created":"2024-12-23","cited_by_count":13,"area":"wm"},{"id":"2310.10027","title":"RoomDesigner: Encoding Anchor-latents for Style-consistent and Shape-compatible Indoor Scene Generation","created":"2023-10-16","cited_by_count":12,"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":"2503.21745","title":"3DGen-Bench: Comprehensive Benchmark Suite for 3D Generative Models","created":"2025-03-27","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":"2311.18402","title":"MV-CLIP: Multi-View CLIP for Zero-shot 3D Shape Recognition","created":"2023-11-30","cited_by_count":11,"area":null},{"id":"2411.19492","title":"Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2403.13524","title":"Compress3D: a Compressed Latent Space for 3D Generation from a Single Image","created":"2024-03-20","cited_by_count":10,"area":"diffusion"},{"id":"2412.15618","title":"3D Shape Tokenization via Latent Flow Matching","created":"2024-12-20","cited_by_count":10,"area":"diffusion"},{"id":"2503.10307","title":"6D Object Pose Tracking in Internet Videos for Robotic Manipulation","created":"2025-03-13","cited_by_count":10,"area":null},{"id":"2309.17175","title":"TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields","created":"2023-09-29","cited_by_count":9,"area":null},{"id":"2404.06119","title":"DreamView: Injecting View-specific Text Guidance into Text-to-3D Generation","created":"2024-04-09","cited_by_count":9,"area":null},{"id":"2404.12139","title":"Omniview-Tuning: Boosting Viewpoint Invariance of Vision-Language Pre-training Models","created":"2024-04-18","cited_by_count":9,"area":"mllm"},{"id":"2404.16538","title":"OpenDlign: Open-World Point Cloud Understanding with Depth-Aligned Images","created":"2024-04-25","cited_by_count":9,"area":"mllm"},{"id":"2408.17027","title":"ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images","created":"2024-08-30","cited_by_count":9,"area":null},{"id":"2409.16178","title":"SDFit: 3D Object Pose and Shape by Fitting a Morphable SDF to a Single Image","created":"2024-09-24","cited_by_count":9,"area":null},{"id":"2410.08049","title":"Scaling Up Your Kernels: Large Kernel Design in ConvNets towards Universal Representations","created":"2024-10-10","cited_by_count":8,"area":null},{"id":"2506.02781","title":"FreeScene: Mixed Graph Diffusion for 3D Scene Synthesis from Free Prompts","created":"2025-06-03","cited_by_count":8,"area":null},{"id":"2506.05318","title":"Does Your 3D Encoder Really Work? When Pretrain-SFT from 2D VLMs Meets 3D VLMs","created":"2025-06-05","cited_by_count":8,"area":"mllm"},{"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":"2411.19292","title":"UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation","created":"2024-11-28","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":"2504.13159","title":"Digital Twin Generation from Visual Data: A Survey","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2403.09813","title":"Towards Comprehensive Multimodal Perception: Introducing the Touch-Language-Vision Dataset","created":"2024-03-14","cited_by_count":6,"area":null},{"id":"2407.07580","title":"InstructLayout: Instruction-Driven 2D and 3D Layout Synthesis with Semantic Graph Prior","created":"2024-07-10","cited_by_count":6,"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":"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":"2601.02457","title":"PatchAlign3D: Local Feature Alignment for Dense 3D Shape Understanding","created":"2026-01-05","cited_by_count":6,"area":null},{"id":"2607.22393","title":"SceneActBench: Can Agents Act on the 3D Scenes They See?","created":"2026-07-24","cited_by_count":6,"area":"mllm"},{"id":"2502.17860","title":"UniGS: Unified Language-Image-3D Pretraining with Gaussian Splatting","created":"2025-02-25","cited_by_count":5,"area":null},{"id":"2505.16663","title":"CoNav: Collaborative Cross-Modal Reasoning for Embodied Navigation","created":"2025-05-22","cited_by_count":5,"area":"lr"},{"id":"2506.09935","title":"LEO-VL: Efficient Scene Representation for Scalable 3D Vision-Language Learning","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"id":"2507.21489","title":"Describe, Adapt and Combine: Empowering CLIP Encoders for Open-set 3D Object Retrieval","created":"2025-07-29","cited_by_count":5,"area":null},{"id":"2503.12150","title":"Point-Cache: Test-time Dynamic and Hierarchical Cache for Robust and Generalizable Point Cloud Analysis","created":"2025-03-15","cited_by_count":4,"area":null},{"id":"2504.18738","title":"A Review of 3D Object Detection with Vision-Language Models","created":"2025-04-25","cited_by_count":4,"area":"mllm"},{"id":"2506.21152","title":"Geometry and Perception Guided Gaussians for Multiview-consistent 3D Generation from a Single Image","created":"2025-06-26","cited_by_count":4,"area":"diffusion"},{"id":"2510.22491","title":"LAMP: Data-Efficient Linear Affine Weight-Space Models for Parameter-Controlled 3D Shape Generation and Extrapolation","created":"2025-10-26","cited_by_count":4,"area":null},{"id":"2511.16567","title":"POMA-3D: The Point Map Way to 3D Scene Understanding","created":"2025-11-20","cited_by_count":4,"area":null},{"id":"2601.16046","title":"DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning","created":"2026-01-22","cited_by_count":4,"area":"lr"},{"id":"2604.04050","title":"TORA: Topological Representation Alignment for 3D Shape Assembly","created":"2026-04-05","cited_by_count":4,"area":"diffusion"},{"id":"2312.01129","title":"ControlDreamer: Blending Geometry and Style in Text-to-3D","created":"2023-12-02","cited_by_count":3,"area":null},{"id":"2404.09931","title":"Zero-shot detection of buildings in mobile LiDAR using Language Vision Model","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2404.10146","title":"Cross-Modal Self-Training: Aligning Images and Pointclouds to Learn Classification without Labels","created":"2024-04-15","cited_by_count":3,"area":"mllm"},{"id":"2404.19168","title":"PEVA-Net: Prompt-Enhanced View Aggregation Network for Zero/Few-Shot Multi-View 3D Shape Recognition","created":"2024-04-30","cited_by_count":3,"area":"mllm"},{"id":"2410.16995","title":"E-3DGS: Gaussian Splatting with Exposure and Motion Events","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2503.12383","title":"VRsketch2Gaussian: 3D VR Sketch Guided 3D Object Generation with Gaussian Splatting","created":"2025-03-16","cited_by_count":3,"area":null},{"id":"2602.07495","title":"Learning Brain Representation with Hierarchical Visual Embeddings","created":"2026-02-07","cited_by_count":3,"area":null},{"id":"2603.18912","title":"GHOST: Fast Category-agnostic Hand-Object Interaction Reconstruction from RGB Videos using Gaussian Splatting","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2405.18523","title":"MM-Mixing: Multi-Modal Mixing Alignment for 3D Understanding","created":"2024-05-28","cited_by_count":2,"area":null},{"id":"2409.04760","title":"Training-Free Point Cloud Recognition Based on Geometric and Semantic Information Fusion","created":"2024-09-07","cited_by_count":2,"area":null},{"id":"2412.14837","title":"ObjVariantEnsemble: Advancing Point Cloud LLM Evaluation in Challenging Scenes with Subtly Distinguished Objects","created":"2024-12-19","cited_by_count":2,"area":null}],"next_cursor":"100"}