{"total":94,"rows":[{"id":"2112.00726","title":"MonoScene: Monocular 3D Semantic Scene Completion","created":"2021-12-01","cited_by_count":363,"area":null},{"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":"2203.07918","title":"GPV-Pose: Category-level Object Pose Estimation via Geometry-guided Point-wise Voting","created":"2022-03-15","cited_by_count":94,"area":null},{"id":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","cited_by_count":89,"area":null},{"id":"2207.13691","title":"ShAPO: Implicit Representations for Multi-Object Shape, Appearance, and Pose Optimization","created":"2022-07-27","cited_by_count":72,"area":null},{"id":"2203.01929","title":"CenterSnap: Single-Shot Multi-Object 3D Shape Reconstruction and Categorical 6D Pose and Size Estimation","created":"2022-03-03","cited_by_count":70,"area":null},{"id":"2208.07227","title":"DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images","created":"2022-08-15","cited_by_count":69,"area":null},{"id":"2303.15782","title":"CARTO: Category and Joint Agnostic Reconstruction of ARTiculated Objects","created":"2023-03-28","cited_by_count":64,"area":null},{"id":"2404.03421","title":"Gen3DSR: Generalizable 3D Scene Reconstruction via Divide and Conquer from a Single View","created":"2024-04-04","cited_by_count":61,"area":null},{"id":"2203.03609","title":"Human-Aware Object Placement for Visual Environment Reconstruction","created":"2022-03-07","cited_by_count":56,"area":null},{"id":"2212.02501","title":"SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields","created":"2022-12-05","cited_by_count":49,"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":"2404.16666","title":"PhyRecon: Physically Plausible Neural Scene Reconstruction","created":"2024-04-25","cited_by_count":45,"area":null},{"id":"2207.08656","title":"Towards High-Fidelity Single-view Holistic Reconstruction of Indoor Scenes","created":"2022-07-18","cited_by_count":44,"area":null},{"id":"2208.00237","title":"RBP-Pose: Residual Bounding Box Projection for Category-Level Pose Estimation","created":"2022-07-30","cited_by_count":43,"area":null},{"id":"2405.10255","title":"When LLMs step into the 3D World: A Survey and Meta-Analysis of 3D Tasks via Multi-modal Large Language Models","created":"2024-05-16","cited_by_count":43,"area":"mllm"},{"id":"2303.13479","title":"IST-Net: Prior-free Category-level Pose Estimation with Implicit Space Transformation","created":"2023-03-23","cited_by_count":41,"area":null},{"id":"2305.02743","title":"Incremental 3D Semantic Scene Graph Prediction from RGB Sequences","created":"2023-05-04","cited_by_count":39,"area":null},{"id":"2311.00457","title":"Single-view 3D Scene Reconstruction with High-fidelity Shape and Texture","created":"2023-11-01","cited_by_count":37,"area":null},{"id":"2108.10743","title":"DeepPanoContext: Panoramic 3D Scene Understanding with Holistic Scene Context Graph and Relation-based Optimization","created":"2021-08-24","cited_by_count":33,"area":null},{"id":"2302.14052","title":"LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR","created":"2023-02-27","cited_by_count":31,"area":null},{"id":"2503.14830","title":"Decompositional Neural Scene Reconstruction with Generative Diffusion Prior","created":"2025-03-19","cited_by_count":31,"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":"2111.12608","title":"Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing","created":"2021-11-24","cited_by_count":22,"area":null},{"id":"2112.03030","title":"Pose2Room: Understanding 3D Scenes from Human Activities","created":"2021-12-01","cited_by_count":22,"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":"2303.08605","title":"RICO: Regularizing the Unobservable for Indoor Compositional Reconstruction","created":"2023-03-15","cited_by_count":20,"area":null},{"id":"2404.01300","title":"NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Radiance Fields","created":"2024-04-01","cited_by_count":20,"area":null},{"id":"2305.12497","title":"PanoContext-Former: Panoramic Total Scene Understanding with a Transformer","created":"2023-05-21","cited_by_count":19,"area":null},{"id":"2112.10541","title":"Implicit Neural Representation Learning for Hyperspectral Image Super-Resolution","created":"2021-12-20","cited_by_count":17,"area":null},{"id":"2204.09138","title":"RangeUDF: Semantic Surface Reconstruction from 3D Point Clouds","created":"2022-04-19","cited_by_count":16,"area":null},{"id":"2305.11768","title":"Generating Visual Spatial Description via Holistic 3D Scene Understanding","created":"2023-05-19","cited_by_count":16,"area":null},{"id":"2312.05277","title":"3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection","created":"2023-12-08","cited_by_count":15,"area":null},{"id":"2308.09098","title":"ImGeoNet: Image-induced Geometry-aware Voxel Representation for Multi-view 3D Object Detection","created":"2023-08-17","cited_by_count":14,"area":null},{"id":"2504.03177","title":"Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image","created":"2025-04-04","cited_by_count":13,"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":"2310.19629","title":"RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency","created":"2023-10-30","cited_by_count":12,"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":"2111.14798","title":"Semi-supervised Implicit Scene Completion from Sparse LiDAR","created":"2021-11-29","cited_by_count":10,"area":null},{"id":"2512.17459","title":"3D-RE-GEN: 3D Reconstruction of Indoor Scenes with a Generative Framework","created":"2025-12-19","cited_by_count":10,"area":null},{"id":"2602.18882","title":"SceneTok: A Compressed, Diffusable Token Space for 3D Scenes","created":"2026-02-21","cited_by_count":10,"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":"2412.10294","title":"Coherent 3D Scene Diffusion From a Single RGB Image","created":"2024-12-13","cited_by_count":8,"area":null},{"id":"2205.02714","title":"Neural Rendering in a Room: Amodal 3D Understanding and Free-Viewpoint Rendering for the Closed Scene Composed of Pre-Captured Objects","created":"2022-05-05","cited_by_count":7,"area":null},{"id":"2307.09112","title":"NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF","created":"2023-07-18","cited_by_count":7,"area":null},{"id":"2403.14539","title":"Robust 3D Shape Reconstruction in Zero-Shot from a Single Image in the Wild","created":"2024-03-21","cited_by_count":7,"area":null},{"id":"2403.16412","title":"Unsupervised Template-assisted Point Cloud Shape Correspondence Network","created":"2024-03-25","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":"2504.13159","title":"Digital Twin Generation from Visual Data: A Survey","created":"2025-04-17","cited_by_count":7,"area":null},{"id":"2111.12728","title":"Online Adaptation for Implicit Object Tracking and Shape Reconstruction in the Wild","created":"2021-11-24","cited_by_count":6,"area":null},{"id":"2307.12194","title":"LIST: Learning Implicitly from Spatial Transformers for Single-View 3D Reconstruction","created":"2023-07-23","cited_by_count":6,"area":null},{"id":"2309.01925","title":"DR-Pose: A Two-stage Deformation-and-Registration Pipeline for Category-level 6D Object Pose Estimation","created":"2023-09-05","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":"2505.17966","title":"Is Single-View Mesh Reconstruction Ready for Robotics?","created":"2025-05-23","cited_by_count":6,"area":null},{"id":"2308.02239","title":"DTF-Net: Category-Level Pose Estimation and Shape Reconstruction via Deformable Template Field","created":"2023-08-04","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":"2503.15211","title":"GO-N3RDet: Geometry Optimized NeRF-enhanced 3D Object Detector","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2310.11184","title":"Sparse Multi-Object Render-and-Compare","created":"2023-10-17","cited_by_count":3,"area":null},{"id":"2403.10452","title":"Robust Shape Fitting for 3D Scene Abstraction","created":"2024-03-15","cited_by_count":3,"area":null},{"id":"2404.09993","title":"No More Ambiguity in 360{\\deg} Room Layout via Bi-Layout Estimation","created":"2024-04-15","cited_by_count":3,"area":null},{"id":"2410.11019","title":"ET-Former: Efficient Triplane Deformable Attention for 3D Semantic Scene Completion From Monocular Camera","created":"2024-10-14","cited_by_count":3,"area":null},{"id":"2411.12635","title":"M3D: Dual-Stream Selective State Spaces and Depth-Driven Framework for High-Fidelity Single-View 3D Reconstruction","created":"2024-11-19","cited_by_count":3,"area":null},{"id":"2503.15742","title":"Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes","created":"2025-03-19","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":"2306.08671","title":"Learning to Predict Scene-Level Implicit 3D from Posed RGBD Data","created":"2023-06-14","cited_by_count":2,"area":null},{"id":"2307.14570","title":"Physically Plausible 3D Human-Scene Reconstruction from Monocular RGB Image using an Adversarial Learning Approach","created":"2023-07-27","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":"2503.12783","title":"Mixed-granularity Implicit Representation for Continuous Hyperspectral Compressive Reconstruction","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2508.04659","title":"PixCuboid: Room Layout Estimation from Multi-view Featuremetric Alignment","created":"2025-08-06","cited_by_count":2,"area":null},{"id":"2603.05908","title":"Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image","created":"2026-03-06","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":"2111.12924","title":"Joint stereo 3D object detection and implicit surface reconstruction","created":"2021-11-25","cited_by_count":1,"area":null},{"id":"2206.00447","title":"CD$^2$: Fine-grained 3D Mesh Reconstruction With Twice Chamfer Distance","created":"2022-06-01","cited_by_count":1,"area":null},{"id":"2312.05602","title":"EipFormer: Emphasizing Instance Positions in 3D Instance Segmentation","created":"2023-12-09","cited_by_count":1,"area":null},{"id":"2408.11465","title":"MeTTA: Single-View to 3D Textured Mesh Reconstruction with Test-Time Adaptation","created":"2024-08-21","cited_by_count":1,"area":null},{"id":"2503.18988","title":"SG-Tailor: Inter-Object Commonsense Relationship Reasoning for Scene Graph Manipulation","created":"2025-03-23","cited_by_count":1,"area":null},{"id":"2508.07714","title":"DoorDet: Semi-Automated Multi-Class Door Detection Dataset via Object Detection and Large Language Models","created":"2025-08-11","cited_by_count":1,"area":null},{"id":"2510.04125","title":"Joint Learning of Pose Regression and Denoising Diffusion with Score Scaling Sampling for Category-level 6D Pose Estimation","created":"2025-10-05","cited_by_count":1,"area":"diffusion"},{"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":"2605.25326","title":"Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation","created":"2026-05-25","cited_by_count":1,"area":null},{"id":"2203.07120","title":"Neural Message Passing for Objective-Based Uncertainty Quantification and Optimal Experimental Design","created":"2022-03-14","cited_by_count":0,"area":null},{"id":"2211.07108","title":"Recursive Cross-View: Use Only 2D Detectors to Achieve 3D Object Detection without 3D Annotations","created":"2022-11-14","cited_by_count":0,"area":null},{"id":"2302.06494","title":"Explicit3D: Graph Network with Spatial Inference for Single Image 3D Object Detection","created":"2023-02-13","cited_by_count":0,"area":null},{"id":"2501.14896","title":"Glissando-Net: Deep sinGLe vIew category level poSe eStimation ANd 3D recOnstruction","created":"2025-01-24","cited_by_count":0,"area":null},{"id":"2512.00493","title":"CC-FMO: Camera-Conditioned Zero-Shot Single Image to 3D Scene Generation with Foundation Model Orchestration","created":"2025-11-29","cited_by_count":0,"area":null},{"id":"2602.06158","title":"MGP-KAD: Multimodal Geometric Priors and Kolmogorov-Arnold Decoder for Single-View 3D Reconstruction in Complex Scenes","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2605.14601","title":"Towards Accurate Single Panoramic 3D Detection: A Semantic Gaussian Centric Approach","created":"2026-05-14","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":"2605.28477","title":"SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2607.13468","title":"HIVE-3D: Hierarchical Voxel Enhancement for High-Quality 3D Scene Generation","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2608.03323","title":"PolyLayout: Multi-room Manhattan Layout Estimation","created":"2026-08-04","cited_by_count":0,"area":null}],"next_cursor":null}