{"total":87,"rows":[{"id":"2102.07064","title":"NeRF--: Neural Radiance Fields Without Known Camera Parameters","created":"2021-02-14","cited_by_count":155,"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":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122,"area":null},{"id":"2404.02838","title":"I-Design: Personalized LLM Interior Designer","created":"2024-04-03","cited_by_count":87,"area":null},{"id":"2109.06061","title":"Learning Indoor Inverse Rendering with 3D Spatially-Varying Lighting","created":"2021-09-13","cited_by_count":83,"area":null},{"id":"2211.03017","title":"Learning-based Inverse Rendering of Complex Indoor Scenes with Differentiable Monte Carlo Raytracing","created":"2022-11-06","cited_by_count":78,"area":null},{"id":"2203.10157","title":"ViewFormer: NeRF-free Neural Rendering from Few Images Using Transformers","created":"2022-03-18","cited_by_count":70,"area":null},{"id":"2106.03336","title":"Wide-Baseline Relative Camera Pose Estimation with Directional Learning","created":"2021-06-07","cited_by_count":49,"area":null},{"id":"2104.13530","title":"Extreme Rotation Estimation using Dense Correlation Volumes","created":"2021-04-28","cited_by_count":42,"area":null},{"id":"2208.08988","title":"The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs","created":"2022-08-18","cited_by_count":38,"area":null},{"id":"2108.08574","title":"StructDepth: Leveraging the structural regularities for self-supervised indoor depth estimation","created":"2021-08-19","cited_by_count":36,"area":null},{"id":"2204.06183","title":"ViViD++: Vision for Visibility Dataset","created":"2022-04-13","cited_by_count":34,"area":null},{"id":"2110.04955","title":"BuildingNet: Learning to Label 3D Buildings","created":"2021-10-11","cited_by_count":33,"area":null},{"id":"2205.03467","title":"EVIMO2: An Event Camera Dataset for Motion Segmentation, Optical Flow, Structure from Motion, and Visual Inertial Odometry in Indoor Scenes with Monocular or Stereo Algorithms","created":"2022-05-06","cited_by_count":31,"area":null},{"id":"2103.05368","title":"ChangeSim: Towards End-to-End Online Scene Change Detection in Industrial Indoor Environments","created":"2021-03-09","cited_by_count":28,"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":"2112.13659","title":"M2DGR: A Multi-sensor and Multi-scenario SLAM Dataset for Ground Robots","created":"2021-12-19","cited_by_count":25,"area":null},{"id":"2303.10559","title":"Deep Learning for Camera Calibration and Beyond: A Survey","created":"2023-03-19","cited_by_count":20,"area":null},{"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":"2303.11910","title":"360BEV: Panoramic Semantic Mapping for Indoor Bird's-Eye View","created":"2023-03-21","cited_by_count":18,"area":null},{"id":"2401.09126","title":"Objects With Lighting: A Real-World Dataset for Evaluating Reconstruction and Rendering for Object Relighting","created":"2024-01-17","cited_by_count":18,"area":null},{"id":"2211.08658","title":"Consistent Direct Time-of-Flight Video Depth Super-Resolution","created":"2022-11-16","cited_by_count":16,"area":null},{"id":"2306.15662","title":"Measured Albedo in the Wild: Filling the Gap in Intrinsics Evaluation","created":"2023-06-27","cited_by_count":16,"area":null},{"id":"2311.11013","title":"Implicit Event-RGBD Neural SLAM","created":"2023-11-18","cited_by_count":16,"area":null},{"id":"2508.14461","title":"Ouroboros: Single-step Diffusion Models for Cycle-consistent Forward and Inverse Rendering","created":"2025-08-20","cited_by_count":16,"area":"diffusion"},{"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":"2405.09546","title":"BEHAVIOR Vision Suite: Customizable Dataset Generation via Simulation","created":"2024-05-15","cited_by_count":14,"area":null},{"id":"2507.07644","title":"FloorplanQA: A Benchmark for Spatial Reasoning in LLMs using Structured Representations","created":"2025-07-10","cited_by_count":13,"area":"lr"},{"id":"2303.12368","title":"MAIR: Multi-view Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation","created":"2023-03-22","cited_by_count":12,"area":null},{"id":"2305.04374","title":"Spatiotemporally Consistent HDR Indoor Lighting Estimation","created":"2023-05-07","cited_by_count":12,"area":null},{"id":"2403.03221","title":"FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation","created":"2024-03-05","cited_by_count":12,"area":null},{"id":"2201.05761","title":"A Survey on RGB-D Datasets","created":"2022-01-15","cited_by_count":11,"area":null},{"id":"2506.18904","title":"TC-Light: Temporally Coherent Generative Rendering for Realistic World Transfer","created":"2025-06-23","cited_by_count":11,"area":null},{"id":"2503.11958","title":"CHOrD: Generation of Collision-Free, House-Scale, and Organized Digital Twins for 3D Indoor Scenes with Controllable Floor Plans and Optimal Layouts","created":"2025-03-15","cited_by_count":10,"area":null},{"id":"2604.02329","title":"Generative World Renderer","created":"2026-04-02","cited_by_count":10,"area":null},{"id":"2103.13696","title":"SSLayout360: Semi-Supervised Indoor Layout Estimation from 360-Degree Panorama","created":"2021-03-25","cited_by_count":9,"area":null},{"id":"2505.24521","title":"UniGeo: Taming Video Diffusion for Unified Consistent Geometry Estimation","created":"2025-05-30","cited_by_count":9,"area":"diffusion"},{"id":"2111.09006","title":"Probabilistic Spatial Distribution Prior Based Attentional Keypoints Matching Network","created":"2021-11-17","cited_by_count":8,"area":null},{"id":"2409.07715","title":"FIReStereo: Forest InfraRed Stereo Dataset for UAS Depth Perception in Visually Degraded Environments","created":"2024-09-12","cited_by_count":8,"area":null},{"id":"2411.12250","title":"ADV2E: Bridging the Gap Between Analogue Circuit and Discrete Frames in the Video-to-Events Simulator","created":"2024-11-19","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":"2104.12564","title":"Synthetic 3D Data Generation Pipeline for Geometric Deep Learning in Architecture","created":"2021-04-26","cited_by_count":7,"area":null},{"id":"2112.12577","title":"NVS-MonoDepth: Improving Monocular Depth Prediction with Novel View Synthesis","created":"2021-12-22","cited_by_count":7,"area":null},{"id":"2209.04634","title":"Real-time event simulation with frame-based cameras","created":"2022-09-10","cited_by_count":7,"area":null},{"id":"2302.03640","title":"SSR-2D: Semantic 3D Scene Reconstruction from 2D Images","created":"2023-02-07","cited_by_count":7,"area":null},{"id":"2105.01203","title":"Event Camera Simulator Design for Modeling Attention-based Inference Architectures","created":"2021-05-03","cited_by_count":6,"area":null},{"id":"2109.00405","title":"EVReflex: Dense Time-to-Impact Prediction for Event-based Obstacle Avoidance","created":"2021-09-01","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":"2503.22943","title":"Event Camera Meets Mobile Embodied Perception: Abstraction, Algorithm, Acceleration, Application","created":"2025-03-29","cited_by_count":6,"area":null},{"id":"2508.08384","title":"Spatiotemporally Consistent Indoor Lighting Estimation with Diffusion Priors","created":"2025-08-11","cited_by_count":6,"area":"diffusion"},{"id":"2511.21129","title":"CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion","created":"2025-11-26","cited_by_count":6,"area":"diffusion"},{"id":"2203.03833","title":"Quasi-Balanced Self-Training on Noise-Aware Synthesis of Object Point Clouds for Closing Domain Gap","created":"2022-03-08","cited_by_count":5,"area":null},{"id":"2605.18451","title":"Code-as-Room: Generating 3D Rooms from Top-Down View Images via Agentic Code Synthesis","created":"2026-05-18","cited_by_count":5,"area":"agents"},{"id":"2403.01183","title":"Leveraging Self-Supervised Learning for Scene Classification in Child Sexual Abuse Imagery","created":"2024-03-02","cited_by_count":4,"area":null},{"id":"2510.26800","title":"OmniX: From Unified Panoramic Generation and Perception to Graphics-Ready 3D Scenes","created":"2025-10-30","cited_by_count":4,"area":null},{"id":"2107.13087","title":"DCL: Differential Contrastive Learning for Geometry-Aware Depth Synthesis","created":"2021-07-27","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":"2304.08186","title":"Human Pose Estimation in Monocular Omnidirectional Top-View Images","created":"2023-04-17","cited_by_count":3,"area":null},{"id":"2312.00532","title":"DeepDR: Deep Structure-Aware RGB-D Inpainting for Diminished Reality","created":"2023-12-01","cited_by_count":3,"area":null},{"id":"2402.14354","title":"GAM-Depth: Self-Supervised Indoor Depth Estimation Leveraging a Gradient-Aware Mask and Semantic Constraints","created":"2024-02-22","cited_by_count":3,"area":null},{"id":"2408.06707","title":"MAIR++: Improving Multi-view Attention Inverse Rendering with Implicit Lighting Representation","created":"2024-08-13","cited_by_count":3,"area":null},{"id":"2510.08530","title":"X2Video: Adapting Diffusion Models for Multimodal Controllable Neural Video Rendering","created":"2025-10-09","cited_by_count":3,"area":"diffusion"},{"id":"2208.00919","title":"Benchmarking Visual-Inertial Deep Multimodal Fusion for Relative Pose Regression and Odometry-aided Absolute Pose Regression","created":"2022-08-01","cited_by_count":2,"area":null},{"id":"2408.15038","title":"Interactive Occlusion Boundary Estimation through Exploitation of Synthetic Data","created":"2024-08-27","cited_by_count":2,"area":null},{"id":"2102.04136","title":"Points2Vec: Unsupervised Object-level Feature Learning from Point Clouds","created":"2021-02-08","cited_by_count":1,"area":null},{"id":"2105.12038","title":"Unpaired Depth Super-Resolution in the Wild","created":"2021-05-25","cited_by_count":1,"area":null},{"id":"2107.06149","title":"MINERVAS: Massive INterior EnviRonments VirtuAl Synthesis","created":"2021-07-13","cited_by_count":1,"area":null},{"id":"2406.18898","title":"360 in the Wild: Dataset for Depth Prediction and View Synthesis","created":"2024-06-27","cited_by_count":1,"area":null},{"id":"2408.13712","title":"Riemann-based Multi-scale Attention Reasoning Network for Text-3D Retrieval","created":"2024-08-25","cited_by_count":1,"area":null},{"id":"2411.13251","title":"BelHouse3D: A Benchmark Dataset for Assessing Occlusion Robustness in 3D Point Cloud Semantic Segmentation","created":"2024-11-20","cited_by_count":1,"area":null},{"id":"2509.25905","title":"User-Centric Communication Service Provision for Edge-Assisted Mobile Augmented Reality","created":"2025-09-30","cited_by_count":1,"area":null},{"id":"2510.14965","title":"ChangingGrounding: 3D Visual Grounding in Changing Scenes","created":"2025-10-16","cited_by_count":1,"area":null},{"id":"2512.17573","title":"RoomEditor++: A Parameter-Sharing Diffusion Architecture for High-Fidelity Furniture Synthesis","created":"2025-12-19","cited_by_count":1,"area":null},{"id":"2603.24912","title":"ICTPolarReal: A Polarized Reflection and Material Dataset of Real World Objects","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2607.20866","title":"Agentic Designer: Progressive Multi-Agent Collaboration for Structure-Aware Interior Layout Generation","created":"2026-07-23","cited_by_count":1,"area":"agents"},{"id":"2110.10805","title":"DVIO: Depth aided visual inertial odometry for RGBD sensors","created":"2021-10-20","cited_by_count":0,"area":null},{"id":"2312.08364","title":"View-Dependent Octree-based Mesh Extraction in Unbounded Scenes for Procedural Synthetic Data","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2402.11836","title":"DIO: Dataset of 3D Mesh Models of Indoor Objects for Robotics and Computer Vision Applications","created":"2024-02-19","cited_by_count":0,"area":null},{"id":"2406.03388","title":"SelfReDepth: Self-Supervised Real-Time Depth Restoration for Consumer-Grade Sensors","created":"2024-06-05","cited_by_count":0,"area":null},{"id":"2412.03259","title":"GERD: Geometric event response data generation","created":"2024-12-04","cited_by_count":0,"area":null},{"id":"2512.12165","title":"Audio-Visual Camera Pose Estimation with Passive Scene Sounds and In-the-Wild Video","created":"2025-12-13","cited_by_count":0,"area":null},{"id":"2604.07010","title":"Synthetic Dataset Generation for Partially Observed Indoor Objects","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2607.02718","title":"Diagnosing Aerial-View Object Detectors with Foundational Image Generative Models","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2607.03614","title":"IDEAL-Bench: Indoor Dataset and Evaluation suite for Analyzing 3D Layout reasoning","created":"2026-07-03","cited_by_count":0,"area":"lr"},{"id":"2607.21592","title":"Unified Video Dense Prediction from Disjoint Data","created":"2026-07-23","cited_by_count":0,"area":null},{"id":"2609.04196","title":"Puffin-World: Scaling a Unified Multimodal Model with Native 3D World States","created":"2026-09-03","cited_by_count":0,"area":null}],"next_cursor":null}