{"total":67,"rows":[{"id":"2412.03558","title":"MIDI: Multi-Instance Diffusion for Single Image to 3D Scene Generation","created":"2024-12-04","cited_by_count":117,"area":"diffusion"},{"id":"2502.12894","title":"CAST: Component-Aligned 3D Scene Reconstruction from an RGB Image","created":"2025-02-18","cited_by_count":106,"area":null},{"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":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54,"area":null},{"id":"2311.18610","title":"DiffCAD: Weakly-Supervised Probabilistic CAD Model Retrieval and Alignment from an RGB Image","created":"2023-11-30","cited_by_count":48,"area":null},{"id":"2311.17618","title":"ShapeGPT: 3D Shape Generation with A Unified Multi-modal Language Model","created":"2023-11-29","cited_by_count":39,"area":"mllm"},{"id":"2409.16294","title":"GenCAD: Image-Conditioned Computer-Aided Design Generation with Transformer-Based Contrastive Representation and Diffusion Priors","created":"2024-09-08","cited_by_count":38,"area":"diffusion"},{"id":"2404.00469","title":"SceneGraphLoc: Cross-Modal Coarse Visual Localization on 3D Scene Graphs","created":"2024-03-30","cited_by_count":29,"area":null},{"id":"2408.03225","title":"Line-based 6-DoF Object Pose Estimation and Tracking With an Event Camera","created":"2024-08-06","cited_by_count":29,"area":null},{"id":"2502.20732","title":"CADDreamer: CAD Object Generation from Single-view Images","created":"2025-02-28","cited_by_count":25,"area":"diffusion"},{"id":"2211.14157","title":"Learning 3D Scene Priors with 2D Supervision","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2507.22825","title":"DepR: Depth Guided Single-view Scene Reconstruction with Instance-level Diffusion","created":"2025-07-30","cited_by_count":23,"area":"diffusion"},{"id":"2407.08711","title":"OmniNOCS: A unified NOCS dataset and model for 3D lifting of 2D objects","created":"2024-07-11","cited_by_count":22,"area":null},{"id":"2507.02861","title":"LiteReality: Graphics-Ready 3D Scene Reconstruction from RGB-D Scans","created":"2025-07-03","cited_by_count":21,"area":null},{"id":"2304.05947","title":"Visual Localization using Imperfect 3D Models from the Internet","created":"2023-04-12","cited_by_count":20,"area":null},{"id":"2210.01044","title":"SPARC: Sparse Render-and-Compare for CAD model alignment in a single RGB image","created":"2022-10-03","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":"2203.13296","title":"RayTran: 3D pose estimation and shape reconstruction of multiple objects from videos with ray-traced transformers","created":"2022-03-24","cited_by_count":17,"area":null},{"id":"2212.01985","title":"ObjectMatch: Robust Registration using Canonical Object Correspondences","created":"2022-12-05","cited_by_count":15,"area":null},{"id":"2206.11215","title":"Certifiable 3D Object Pose Estimation: Foundations, Learning Models, and Self-Training","created":"2022-06-22","cited_by_count":12,"area":null},{"id":"2308.06383","title":"U-RED: Unsupervised 3D Shape Retrieval and Deformation for Partial Point Clouds","created":"2023-08-11","cited_by_count":12,"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":"2604.04406","title":"3D-Fixer: Coarse-to-Fine In-place Completion for 3D Scenes from a Single Image","created":"2026-04-06","cited_by_count":11,"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":"2311.11106","title":"ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation","created":"2023-11-18","cited_by_count":8,"area":null},{"id":"2401.00405","title":"Generalizing Single-View 3D Shape Retrieval to Occlusions and Unseen Objects","created":"2023-12-31","cited_by_count":8,"area":null},{"id":"2412.10294","title":"Coherent 3D Scene Diffusion From a Single RGB Image","created":"2024-12-13","cited_by_count":8,"area":null},{"id":"2404.04557","title":"Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes","created":"2024-04-06","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":"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":"2504.13159","title":"Digital Twin Generation from Visual Data: A Survey","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2210.16815","title":"CAD 3D Model classification by Graph Neural Networks: A new approach based on STEP format","created":"2022-10-30","cited_by_count":6,"area":null},{"id":"2403.10099","title":"KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation","created":"2024-03-15","cited_by_count":6,"area":null},{"id":"2312.12418","title":"LASA: Instance Reconstruction from Real Scans using A Large-scale Aligned Shape Annotation Dataset","created":"2023-12-19","cited_by_count":5,"area":null},{"id":"2503.19914","title":"Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models","created":"2025-03-25","cited_by_count":5,"area":"diffusion"},{"id":"2301.02232","title":"CA$^2$T-Net: Category-Agnostic 3D Articulation Transfer from Single Image","created":"2023-01-05","cited_by_count":3,"area":null},{"id":"2304.05731","title":"SketchANIMAR: Sketch-based 3D Animal Fine-Grained Retrieval","created":"2023-04-12","cited_by_count":3,"area":null},{"id":"2310.11184","title":"Sparse Multi-Object Render-and-Compare","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2403.19022","title":"WALT3D: Generating Realistic Training Data from Time-Lapse Imagery for Reconstructing Dynamic Objects under Occlusion","created":"2024-03-27","cited_by_count":3,"area":null},{"id":"2506.21520","title":"MADrive: Memory-Augmented Driving Scene Modeling","created":"2025-06-26","cited_by_count":3,"area":null},{"id":"2512.01204","title":"TabletopGen: Tabletop Scene Generation and Interactive Simulation for Robotic Manipulation","created":"2025-12-01","cited_by_count":3,"area":null},{"id":"2603.25494","title":"AdaSFormer: Adaptive Serialized Transformers for Monocular Semantic Scene Completion from Indoor Environments","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2203.12873","title":"Weakly-Supervised End-to-End CAD Retrieval to Scan Objects","created":"2022-03-24","cited_by_count":2,"area":null},{"id":"2504.13580","title":"Leveraging Automatic CAD Annotations for Supervised Learning in 3D Scene Understanding","created":"2025-04-18","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":"2603.25985","title":"JRM: Joint Reconstruction Model for Multiple Objects without Alignment","created":"2026-03-27","cited_by_count":2,"area":null},{"id":"2608.30821","title":"Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling","created":"2026-08-31","cited_by_count":2,"area":null},{"id":"2609.05416","title":"WorldSculpt: Generating Compositional Worlds from Grounded Videos","created":"2026-09-04","cited_by_count":2,"area":null},{"id":"2409.19641","title":"fCOP: Focal Length Estimation from Category-level Object Priors","created":"2024-09-29","cited_by_count":1,"area":null},{"id":"2507.03292","title":"Zero-shot Inexact CAD Model Alignment from a Single Image","created":"2025-07-04","cited_by_count":1,"area":null},{"id":"2511.22187","title":"HybridWorldSim: A Scalable and Controllable High-fidelity Simulator for Autonomous Driving","created":"2025-11-27","cited_by_count":1,"area":"driving"},{"id":"2603.16868","title":"MessyKitchens: Contact-rich object-level 3D scene reconstruction","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2605.13018","title":"OCH3R: Object-Centric Holistic 3D Reconstruction","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.19019","title":"FlowObject: Flow Steering for Bridging Generative Priors and Reconstruction Fidelity","created":"2026-06-17","cited_by_count":1,"area":"diffusion"},{"id":"2608.07012","title":"Scenix: Sparse-View 3D Scene Reconstruction via Executable Scene Programs","created":"2026-08-07","cited_by_count":1,"area":null},{"id":"2603.16133","title":"DualPrim: Compact 3D Reconstruction with Positive and Negative Primitives","created":"2026-03-17","cited_by_count":0,"area":null},{"id":"2604.20093","title":"FurnSet: Exploiting Repeats for 3D Scene Reconstruction","created":"2026-04-22","cited_by_count":0,"area":null},{"id":"2604.27578","title":"World2Minecraft: Occupancy-Driven Simulated Scenes Construction","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.16807","title":"DecoRec: Decomposed 3D Scene Reconstruction from Single-View Images via Object-Level Diffusion","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2606.01702","title":"KDH-CAD: Knowledge-data hybrid CAD learning under data scarcity","created":"2026-06-01","cited_by_count":0,"area":null},{"id":"2606.04291","title":"A Cookbook of 3D Vision: Data, Learning Paradigms, and Application","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.01205","title":"Linkify: Learning from Interface-Augmented Assembly Graphs","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.03990","title":"InSpace: Structure-Aware 3D Indoor Scene Generation from a Single 360{\\deg} Image","created":"2026-07-04","cited_by_count":0,"area":null},{"id":"2607.05393","title":"Interpretable Human-Label-Free Deep Learning for Real-Bogus Classification with Uncertainty Quantification","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.15058","title":"SUFLECA: Scaling Up Feature Learning for CAD-to-image Alignment","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2609.18473","title":"CADSplat: Sparse-View 3D Gaussian Splatting Aided by CAD Models for Robust, Photorealistic Digital-Twin Reconstruction","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2610.05249","title":"ArticuTable: Generating Instance-Level Interactive Rigid-Articulated 3D Tabletop Scenes from a Single Image","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}