{"total":142,"rows":[{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511,"area":null},{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363,"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":"2207.10660","title":"Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild","created":"2022-07-21","cited_by_count":160,"area":null},{"id":"2202.08227","title":"Ditto: Building Digital Twins of Articulated Objects from Interaction","created":"2022-02-16","cited_by_count":156,"area":null},{"id":"2306.09310","title":"Infinite Photorealistic Worlds using Procedural Generation","created":"2023-06-15","cited_by_count":147,"area":null},{"id":"2406.11824","title":"Infinigen Indoors: Photorealistic Indoor Scenes using Procedural Generation","created":"2024-06-17","cited_by_count":137,"area":null},{"id":"2210.05633","title":"Habitat-Matterport 3D Semantics Dataset","created":"2022-10-11","cited_by_count":110,"area":null},{"id":"2207.11514","title":"Semantic Abstraction: Open-World 3D Scene Understanding from 2D Vision-Language Models","created":"2022-07-23","cited_by_count":95,"area":"mllm"},{"id":"2103.07466","title":"3D Semantic Scene Completion: a Survey","created":"2021-03-12","cited_by_count":74,"area":null},{"id":"2112.01988","title":"ROCA: Robust CAD Model Retrieval and Alignment from a Single Image","created":"2021-12-03","cited_by_count":67,"area":null},{"id":"2112.01530","title":"StyleMesh: Style Transfer for Indoor 3D Scene Reconstructions","created":"2021-12-02","cited_by_count":58,"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":"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":"2101.07889","title":"Joint Learning of 3D Shape Retrieval and Deformation","created":"2021-01-19","cited_by_count":42,"area":null},{"id":"2204.10688","title":"Spatiality-guided Transformer for 3D Dense Captioning on Point Clouds","created":"2022-04-22","cited_by_count":40,"area":null},{"id":"2108.09368","title":"Patch2CAD: Patchwise Embedding Learning for In-the-Wild Shape Retrieval from a Single Image","created":"2021-08-20","cited_by_count":39,"area":null},{"id":"2304.05868","title":"Mesh2Tex: Generating Mesh Textures from Image Queries","created":"2023-04-12","cited_by_count":31,"area":null},{"id":"2505.02388","title":"MetaScenes: Towards Automated Replica Creation for Real-world 3D Scans","created":"2025-05-05","cited_by_count":31,"area":null},{"id":"2104.00024","title":"RetrievalFuse: Neural 3D Scene Reconstruction with a Database","created":"2021-03-31","cited_by_count":28,"area":null},{"id":"2202.07135","title":"Compositional Scene Representation Learning via Reconstruction: A Survey","created":"2022-02-15","cited_by_count":27,"area":null},{"id":"2406.10224","title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","created":"2024-06-14","cited_by_count":26,"area":null},{"id":"2211.14157","title":"Learning 3D Scene Priors with 2D Supervision","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2205.09248","title":"MESH2IR: Neural Acoustic Impulse Response Generator for Complex 3D Scenes","created":"2022-05-18","cited_by_count":23,"area":null},{"id":"2108.10165","title":"ODAM: Object Detection, Association, and Mapping using Posed RGB Video","created":"2021-08-23","cited_by_count":22,"area":null},{"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":"2601.11514","title":"ShapeR: Robust Conditional 3D Shape Generation from Casual Captures","created":"2026-01-16","cited_by_count":22,"area":null},{"id":"2204.13630","title":"Rotationally Equivariant 3D Object Detection","created":"2022-04-28","cited_by_count":21,"area":null},{"id":"2206.04916","title":"PatchComplete: Learning Multi-Resolution Patch Priors for 3D Shape Completion on Unseen Categories","created":"2022-06-10","cited_by_count":21,"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":"2111.03098","title":"Voxel-based 3D Detection and Reconstruction of Multiple Objects from a Single Image","created":"2021-11-04","cited_by_count":20,"area":null},{"id":"2203.16832","title":"Point Scene Understanding via Disentangled Instance Mesh Reconstruction","created":"2022-03-31","cited_by_count":20,"area":null},{"id":"2409.18336","title":"DeBaRA: Denoising-Based 3D Room Arrangement Generation","created":"2024-09-26","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":"2103.07969","title":"Monte Carlo Scene Search for 3D Scene Understanding","created":"2021-03-14","cited_by_count":19,"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":"2203.05238","title":"Back to Reality: Weakly-supervised 3D Object Detection with Shape-guided Label Enhancement","created":"2022-03-10","cited_by_count":17,"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":"2103.16095","title":"Reconstructing Interactive 3D Scenes by Panoptic Mapping and CAD Model Alignments","created":"2021-03-30","cited_by_count":15,"area":null},{"id":"2110.08861","title":"3D-RETR: End-to-End Single and Multi-View 3D Reconstruction with Transformers","created":"2021-10-17","cited_by_count":15,"area":null},{"id":"2212.01985","title":"ObjectMatch: Robust Registration using Canonical Object Correspondences","created":"2022-12-05","cited_by_count":15,"area":null},{"id":"2306.09011","title":"CAD-Estate: Large-scale CAD Model Annotation in RGB Videos","created":"2023-06-15","cited_by_count":14,"area":null},{"id":"2310.01401","title":"Pixel-Aligned Recurrent Queries for Multi-View 3D Object Detection","created":"2023-10-02","cited_by_count":14,"area":null},{"id":"2206.11808","title":"Unseen Object 6D Pose Estimation: A Benchmark and Baselines","created":"2022-06-23","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":"2502.15011","title":"CrossOver: 3D Scene Cross-Modal Alignment","created":"2025-02-20","cited_by_count":12,"area":null},{"id":"2603.02133","title":"SimRecon: SimReady Compositional Scene Reconstruction from Real Videos","created":"2026-03-02","cited_by_count":12,"area":null},{"id":"2312.15130","title":"PACE: A Large-Scale Dataset with Pose Annotations in Cluttered Environments","created":"2023-12-23","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":"2507.08416","title":"InstaScene: Towards Complete 3D Instance Decomposition and Reconstruction from Cluttered Scenes","created":"2025-07-11","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":"2108.00355","title":"ELLIPSDF: Joint Object Pose and Shape Optimization with a Bi-level Ellipsoid and Signed Distance Function Description","created":"2021-08-01","cited_by_count":10,"area":null},{"id":"2203.09440","title":"TO-Scene: A Large-scale Dataset for Understanding 3D Tabletop Scenes","created":"2022-03-17","cited_by_count":10,"area":null},{"id":"2401.03470","title":"FurniScene: A Large-scale 3D Room Dataset with Intricate Furnishing Scenes","created":"2024-01-07","cited_by_count":10,"area":null},{"id":"2212.11796","title":"Automatically Annotating Indoor Images with CAD Models via RGB-D Scans","created":"2022-12-22","cited_by_count":9,"area":null},{"id":"2304.10179","title":"SCoDA: Domain Adaptive Shape Completion for Real Scans","created":"2023-04-20","cited_by_count":9,"area":null},{"id":"2308.09591","title":"O$^2$-Recon: Completing 3D Reconstruction of Occluded Objects in the Scene with a Pre-trained 2D Diffusion Model","created":"2023-08-18","cited_by_count":8,"area":"diffusion"},{"id":"2309.09118","title":"Uncertainty-aware 3D Object-Level Mapping with Deep Shape Priors","created":"2023-09-17","cited_by_count":8,"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":"2111.14582","title":"Multi-instance Point Cloud Registration by Efficient Correspondence Clustering","created":"2021-11-29","cited_by_count":7,"area":null},{"id":"2403.15161","title":"FastCAD: Real-Time CAD Retrieval and Alignment from Scans and Videos","created":"2024-03-22","cited_by_count":7,"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":"2411.19292","title":"UrbanCAD: Towards Highly Controllable and Photorealistic 3D Vehicles for Urban Scene Simulation","created":"2024-11-28","cited_by_count":7,"area":null},{"id":"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":"2103.04494","title":"Fully Convolutional Geometric Features for Category-level Object Alignment","created":"2021-03-08","cited_by_count":6,"area":null},{"id":"2203.09375","title":"Neural Part Priors: Learning to Optimize Part-Based Object Completion in RGB-D Scans","created":"2022-03-17","cited_by_count":6,"area":null},{"id":"2209.00219","title":"PointCLM: A Contrastive Learning-based Framework for Multi-instance Point Cloud Registration","created":"2022-09-01","cited_by_count":6,"area":null},{"id":"2306.09077","title":"Estimating Generic 3D Room Structures from 2D Annotations","created":"2023-06-15","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":"2509.23728","title":"M3DLayout: A Multi-Source Dataset of 3D Indoor Layouts and Structured Descriptions for 3D Generation","created":"2025-09-28","cited_by_count":6,"area":null},{"id":"2603.29847","title":"CADReasoner: Iterative Program Editing for CAD Reverse Engineering","created":"2026-02-18","cited_by_count":6,"area":null},{"id":"2103.06911","title":"CORSAIR: Convolutional Object Retrieval and Symmetry-AIded Registration","created":"2021-03-11","cited_by_count":5,"area":null},{"id":"2209.10008","title":"Fine-Grained VR Sketching: Dataset and Insights","created":"2022-09-20","cited_by_count":5,"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":"2410.05514","title":"Toward General Object-level Mapping from Sparse Views with 3D Diffusion Priors","created":"2024-10-07","cited_by_count":5,"area":"diffusion"},{"id":"2602.22667","title":"Monocular Open Vocabulary Occupancy Prediction for Indoor Scenes","created":"2026-02-26","cited_by_count":5,"area":null},{"id":"2206.12356","title":"HM3D-ABO: A Photo-realistic Dataset for Object-centric Multi-view 3D Reconstruction","created":"2022-06-24","cited_by_count":4,"area":null},{"id":"2403.12301","title":"R3DS: Reality-linked 3D Scenes for Panoramic Scene Understanding","created":"2024-03-18","cited_by_count":4,"area":null},{"id":"2503.15897","title":"Learning 3D Scene Analogies with Neural Contextual Scene Maps","created":"2025-03-20","cited_by_count":4,"area":null},{"id":"2111.03039","title":"Towards Panoptic 3D Parsing for Single Image in the Wild","created":"2021-11-04","cited_by_count":3,"area":null},{"id":"2206.02366","title":"Scan2Part: Fine-grained and Hierarchical Part-level Understanding of Real-World 3D Scans","created":"2022-06-06","cited_by_count":3,"area":null},{"id":"2207.01339","title":"Accurate Instance-Level CAD Model Retrieval in a Large-Scale Database","created":"2022-07-04","cited_by_count":3,"area":null},{"id":"2309.06107","title":"HOC-Search: Efficient CAD Model and Pose Retrieval from RGB-D Scans","created":"2023-09-12","cited_by_count":3,"area":null},{"id":"2309.08966","title":"FF-LOGO: Cross-Modality Point Cloud Registration with Feature Filtering and Local to Global Optimization","created":"2023-09-16","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":"2412.05154","title":"Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection","created":"2024-12-06","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":"2603.18496","title":"NymeriaPlus: Enriching Nymeria Dataset with Additional Annotations and Data","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2604.10789","title":"ReplicateAnyScene: Zero-Shot Video-to-3D Composition via Textual-Visual-Spatial Alignment","created":"2026-04-12","cited_by_count":3,"area":null},{"id":"2203.01449","title":"Object Pose Estimation using Mid-level Visual Representations","created":"2022-03-02","cited_by_count":2,"area":null},{"id":"2203.09772","title":"Completing Partial Point Clouds with Outliers by Collaborative Completion and Segmentation","created":"2022-03-18","cited_by_count":2,"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":"2211.00382","title":"Seg&Struct: The Interplay Between Part Segmentation and Structure Inference for 3D Shape Parsing","created":"2022-11-01","cited_by_count":2,"area":null},{"id":"2303.13477","title":"TransPoser: Transformer as an Optimizer for Joint Object Shape and Pose Estimation","created":"2023-03-23","cited_by_count":2,"area":null},{"id":"2306.05978","title":"3D objects and scenes classification, recognition, segmentation, and reconstruction using 3D point cloud data: A review","created":"2023-06-09","cited_by_count":2,"area":null},{"id":"2309.11133","title":"Shape Anchor Guided Holistic Indoor Scene Understanding","created":"2023-09-20","cited_by_count":2,"area":null},{"id":"2401.02357","title":"Fit-NGP: Fitting Object Models to Neural Graphics Primitives","created":"2024-01-04","cited_by_count":2,"area":null},{"id":"2402.04195","title":"Instance by Instance: An Iterative Framework for Multi-instance 3D Registration","created":"2024-02-06","cited_by_count":2,"area":null}],"next_cursor":"100"}