{"total":366,"rows":[{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540,"area":null},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849,"area":null},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774,"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":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2206.06994","title":"ProcTHOR: Large-Scale Embodied AI Using Procedural Generation","created":"2022-06-14","cited_by_count":380,"area":null},{"id":"2501.12202","title":"Hunyuan3D 2.0: Scaling Diffusion Models for High Resolution Textured 3D Assets Generation","created":"2025-01-21","cited_by_count":356,"area":"diffusion"},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349,"area":null},{"id":"2301.07525","title":"OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation","created":"2023-01-18","cited_by_count":326,"area":null},{"id":"2310.06773","title":"Uni3D: Exploring Unified 3D Representation at Scale","created":"2023-10-10","cited_by_count":237,"area":null},{"id":"2303.06042","title":"MVImgNet: A Large-scale Dataset of Multi-view Images","created":"2023-03-10","cited_by_count":220,"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":"2212.01206","title":"DiffRF: Rendering-Guided 3D Radiance Field Diffusion","created":"2022-12-02","cited_by_count":204,"area":"diffusion"},{"id":"2306.07279","title":"Scalable 3D Captioning with Pretrained Models","created":"2023-06-12","cited_by_count":203,"area":null},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189,"area":null},{"id":"2305.10764","title":"OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding","created":"2023-05-18","cited_by_count":184,"area":null},{"id":"2302.10109","title":"NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion","created":"2023-02-20","cited_by_count":180,"area":null},{"id":"2304.06714","title":"Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction","created":"2023-04-13","cited_by_count":180,"area":"diffusion"},{"id":"2512.14692","title":"Native and Compact Structured Latents for 3D Generation","created":"2025-12-16","cited_by_count":175,"area":null},{"id":"2311.12024","title":"PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction","created":"2023-11-20","cited_by_count":165,"area":null},{"id":"2404.12385","title":"MeshLRM: Large Reconstruction Model for High-Quality Meshes","created":"2024-04-18","cited_by_count":139,"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":"2310.07204","title":"State of the Art on Diffusion Models for Visual Computing","created":"2023-10-11","cited_by_count":127,"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":"2401.12592","title":"RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos","created":"2024-01-23","cited_by_count":115,"area":null},{"id":"2306.11565","title":"HomeRobot: Open-Vocabulary Mobile Manipulation","created":"2023-06-20","cited_by_count":106,"area":null},{"id":"2503.22236","title":"Hi3DGen: High-fidelity 3D Geometry Generation from Images via Normal Bridging","created":"2025-03-28","cited_by_count":99,"area":null},{"id":"2412.17808","title":"Dora: Sampling and Benchmarking for 3D Shape Variational Auto-Encoders","created":"2024-12-23","cited_by_count":98,"area":"diffusion"},{"id":"2403.13064","title":"SceneScript: Reconstructing Scenes With An Autoregressive Structured Language Model","created":"2024-03-19","cited_by_count":96,"area":null},{"id":"2205.13914","title":"3DILG: Irregular Latent Grids for 3D Generative Modeling","created":"2022-05-27","cited_by_count":93,"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":"2506.05573","title":"PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers","created":"2025-06-05","cited_by_count":84,"area":"diffusion"},{"id":"2503.21732","title":"SparseFlex: High-Resolution and Arbitrary-Topology 3D Shape Modeling","created":"2025-03-27","cited_by_count":79,"area":null},{"id":"2204.02389","title":"ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer","created":"2022-04-05","cited_by_count":75,"area":null},{"id":"2505.16707","title":"KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models","created":"2025-05-22","cited_by_count":71,"area":null},{"id":"2503.15265","title":"DeepMesh: Auto-Regressive Artist-mesh Creation with Reinforcement Learning","created":"2025-03-19","cited_by_count":65,"area":"alignment"},{"id":"2401.17807","title":"Advances in 3D Generation: A Survey","created":"2024-01-31","cited_by_count":63,"area":null},{"id":"2504.07943","title":"HoloPart: Generative 3D Part Amodal Segmentation","created":"2025-04-10","cited_by_count":60,"area":null},{"id":"2205.10712","title":"Housekeep: Tidying Virtual Households using Commonsense Reasoning","created":"2022-05-22","cited_by_count":57,"area":"lr"},{"id":"2503.13439","title":"Amodal3R: Amodal 3D Reconstruction from Occluded 2D Images","created":"2025-03-17","cited_by_count":54,"area":null},{"id":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54,"area":null},{"id":"2306.09109","title":"NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations","created":"2023-06-15","cited_by_count":53,"area":null},{"id":"2310.16044","title":"Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark","created":"2023-10-24","cited_by_count":51,"area":null},{"id":"2307.05445","title":"AutoDecoding Latent 3D Diffusion Models","created":"2023-07-07","cited_by_count":50,"area":"diffusion"},{"id":"2404.04242","title":"Physical Property Understanding from Language-Embedded Feature Fields","created":"2024-04-05","cited_by_count":48,"area":null},{"id":"2210.06849","title":"Retrospectives on the Embodied AI Workshop","created":"2022-10-13","cited_by_count":46,"area":null},{"id":"2507.16290","title":"Dens3R: A Foundation Model for 3D Geometry Prediction","created":"2025-07-22","cited_by_count":46,"area":null},{"id":"2310.07018","title":"NEWTON: Are Large Language Models Capable of Physical Reasoning?","created":"2023-10-10","cited_by_count":45,"area":"lr"},{"id":"2508.10868","title":"TexVerse: A Universe of 3D Objects with High-Resolution Textures","created":"2025-08-14","cited_by_count":45,"area":null},{"id":"2410.13530","title":"L3DG: Latent 3D Gaussian Diffusion","created":"2024-10-17","cited_by_count":42,"area":null},{"id":"2507.12465","title":"PhysX-3D: Physical-Grounded 3D Asset Generation","created":"2025-07-16","cited_by_count":42,"area":null},{"id":"2306.00956","title":"The ObjectFolder Benchmark: Multisensory Learning with Neural and Real Objects","created":"2023-06-01","cited_by_count":41,"area":null},{"id":"2412.09573","title":"FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D Reconstruction","created":"2024-12-12","cited_by_count":41,"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":"2506.01853","title":"ShapeLLM-Omni: A Native Multimodal LLM for 3D Generation and Understanding","created":"2025-06-02","cited_by_count":38,"area":"mllm"},{"id":"2406.09371","title":"LRM-Zero: Training Large Reconstruction Models with Synthesized Data","created":"2024-06-13","cited_by_count":35,"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":"2403.10075","title":"A survey of synthetic data augmentation methods in computer vision","created":"2024-03-15","cited_by_count":34,"area":null},{"id":"2408.03178","title":"An Object is Worth 64x64 Pixels: Generating 3D Object via Image Diffusion","created":"2024-08-06","cited_by_count":34,"area":null},{"id":"2205.07058","title":"RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis","created":"2022-05-14","cited_by_count":33,"area":null},{"id":"2510.23306","title":"ReconViaGen: Towards Accurate Multi-view 3D Object Reconstruction via Generation","created":"2025-10-27","cited_by_count":33,"area":null},{"id":"2403.15382","title":"DragAPart: Learning a Part-Level Motion Prior for Articulated Objects","created":"2024-03-22","cited_by_count":32,"area":null},{"id":"2411.14384","title":"Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction","created":"2024-11-21","cited_by_count":32,"area":"diffusion"},{"id":"2207.08082","title":"CATRE: Iterative Point Clouds Alignment for Category-level Object Pose Refinement","created":"2022-07-17","cited_by_count":29,"area":null},{"id":"2311.16081","title":"ViT-Lens: Towards Omni-modal Representations","created":"2023-11-27","cited_by_count":29,"area":null},{"id":"2504.08541","title":"Digital Twin Catalog: A Large-Scale Photorealistic 3D Object Digital Twin Dataset","created":"2025-04-11","cited_by_count":29,"area":null},{"id":"2408.04631","title":"Puppet-Master: Scaling Interactive Video Generation as a Motion Prior for Part-Level Dynamics","created":"2024-08-08","cited_by_count":28,"area":null},{"id":"2409.15273","title":"MaterialFusion: Enhancing Inverse Rendering with Material Diffusion Priors","created":"2024-09-23","cited_by_count":28,"area":"diffusion"},{"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":"2402.18490","title":"TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding","created":"2024-02-28","cited_by_count":27,"area":null},{"id":"2404.17569","title":"MaPa: Text-driven Photorealistic Material Painting for 3D Shapes","created":"2024-04-26","cited_by_count":27,"area":"diffusion"},{"id":"2305.13291","title":"Materialistic: Selecting Similar Materials in Images","created":"2023-05-22","cited_by_count":26,"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":"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":"2401.11067","title":"Make-A-Shape: a Ten-Million-scale 3D Shape Model","created":"2024-01-20","cited_by_count":25,"area":null},{"id":"2502.12231","title":"PUGS: Zero-shot Physical Understanding with Gaussian Splatting","created":"2025-02-17","cited_by_count":24,"area":null},{"id":"2408.13953","title":"InterTrack: Tracking Human Object Interaction without Object Templates","created":"2024-08-25","cited_by_count":23,"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":"2409.18896","title":"S2O: Static to Openable Enhancement for Articulated 3D Objects","created":"2024-09-27","cited_by_count":22,"area":null},{"id":"2412.12083","title":"IDArb: Intrinsic Decomposition for Arbitrary Number of Input Views and Illuminations","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2310.18511","title":"3DCoMPaT$^{++}$: An improved Large-scale 3D Vision Dataset for Compositional Recognition","created":"2023-10-27","cited_by_count":21,"area":null},{"id":"2408.10906","title":"ShapeSplat: A Large-scale Dataset of Gaussian Splats and Their Self-Supervised Pretraining","created":"2024-08-20","cited_by_count":21,"area":null},{"id":"2505.20460","title":"DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data","created":"2025-05-26","cited_by_count":21,"area":null},{"id":"2509.25079","title":"UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D Generation","created":"2025-09-29","cited_by_count":20,"area":"diffusion"},{"id":"2208.11537","title":"PeRFception: Perception using Radiance Fields","created":"2022-08-24","cited_by_count":19,"area":null},{"id":"2307.10235","title":"Towards Viewpoint-Invariant Visual Recognition via Adversarial Training","created":"2023-07-16","cited_by_count":19,"area":null},{"id":"2311.00750","title":"Are These the Same Apple? Comparing Images Based on Object Intrinsics","created":"2023-11-01","cited_by_count":19,"area":null},{"id":"2410.01719","title":"OmniSR: Shadow Removal under Direct and Indirect Lighting","created":"2024-10-02","cited_by_count":19,"area":null},{"id":"2502.02562","title":"Learning the RoPEs: Better 2D and 3D Position Encodings with STRING","created":"2025-02-04","cited_by_count":19,"area":null},{"id":"2201.07366","title":"TriCoLo: Trimodal Contrastive Loss for Text to Shape Retrieval","created":"2022-01-19","cited_by_count":18,"area":null},{"id":"2303.16382","title":"ARMBench: An Object-centric Benchmark Dataset for Robotic Manipulation","created":"2023-03-29","cited_by_count":18,"area":null},{"id":"2308.16880","title":"Text2Scene: Text-driven Indoor Scene Stylization with Part-aware Details","created":"2023-08-31","cited_by_count":18,"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":"2412.08641","title":"3D Mesh Editing using Masked LRMs","created":"2024-12-11","cited_by_count":18,"area":null},{"id":"2405.17859","title":"Adapting Pre-Trained Vision Models for Novel Instance Detection and Segmentation","created":"2024-05-28","cited_by_count":17,"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":"2410.01295","title":"LaGeM: A Large Geometry Model for 3D Representation Learning and Diffusion","created":"2024-10-02","cited_by_count":16,"area":null},{"id":"2410.08168","title":"ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion","created":"2024-10-10","cited_by_count":16,"area":null}],"next_cursor":"100"}