{"total":267,"rows":[{"id":"2206.00665","title":"MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction","created":"2022-06-01","cited_by_count":470,"area":null},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395,"area":null},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382,"area":null},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381,"area":null},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367,"area":null},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365,"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":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299,"area":null},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291,"area":null},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286,"area":null},{"id":"2312.09147","title":"Triplane Meets Gaussian Splatting: Fast and Generalizable Single-View 3D Reconstruction with Transformers","created":"2023-12-14","cited_by_count":258,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2206.12403","title":"ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddings","created":"2022-06-24","cited_by_count":178,"area":null},{"id":"2409.18964","title":"PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation","created":"2024-09-27","cited_by_count":174,"area":null},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173,"area":null},{"id":"2302.03594","title":"NICER-SLAM: Neural Implicit Scene Encoding for RGB SLAM","created":"2023-02-07","cited_by_count":164,"area":null},{"id":"2404.17774","title":"High-quality Surface Reconstruction using Gaussian Surfels","created":"2024-04-27","cited_by_count":161,"area":null},{"id":"2403.12722","title":"HUGS: Holistic Urban 3D Scene Understanding via Gaussian Splatting","created":"2024-03-19","cited_by_count":142,"area":null},{"id":"2403.17822","title":"DN-Splatter: Depth and Normal Priors for Gaussian Splatting and Meshing","created":"2024-03-26","cited_by_count":138,"area":null},{"id":"2403.00712","title":"Rethinking Inductive Biases for Surface Normal Estimation","created":"2024-03-01","cited_by_count":124,"area":null},{"id":"2306.04988","title":"StreetSurf: Extending Multi-view Implicit Surface Reconstruction to Street Views","created":"2023-06-08","cited_by_count":120,"area":null},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120,"area":null},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119,"area":null},{"id":"2306.17253","title":"Towards Zero-Shot Scale-Aware Monocular Depth Estimation","created":"2023-06-29","cited_by_count":101,"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":"2301.07302","title":"PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav","created":"2023-01-18","cited_by_count":93,"area":null},{"id":"2204.13226","title":"Offline Visual Representation Learning for Embodied Navigation","created":"2022-04-27","cited_by_count":75,"area":null},{"id":"2312.12274","title":"Intrinsic Image Diffusion for Indoor Single-view Material Estimation","created":"2023-12-19","cited_by_count":73,"area":null},{"id":"2402.13255","title":"How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Survey","created":"2024-02-20","cited_by_count":72,"area":null},{"id":"2303.07798","title":"OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNav","created":"2023-03-14","cited_by_count":70,"area":null},{"id":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67,"area":null},{"id":"2405.16544","title":"Splat-SLAM: Globally Optimized RGB-only SLAM with 3D Gaussians","created":"2024-05-26","cited_by_count":66,"area":null},{"id":"2309.09668","title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","created":"2023-09-18","cited_by_count":60,"area":null},{"id":"2305.02312","title":"AG3D: Learning to Generate 3D Avatars from 2D Image Collections","created":"2023-05-03","cited_by_count":55,"area":null},{"id":"2311.12792","title":"Intrinsic Image Decomposition via Ordinal Shading","created":"2023-11-21","cited_by_count":53,"area":null},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52,"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":"2303.01416","title":"3D generation on ImageNet","created":"2023-03-02","cited_by_count":47,"area":null},{"id":"2305.06351","title":"Reconstructing Animatable Categories from Videos","created":"2023-05-10","cited_by_count":47,"area":null},{"id":"2412.04472","title":"Stereo Anywhere: Robust Zero-Shot Deep Stereo Matching Even Where Either Stereo or Mono Fail","created":"2024-12-05","cited_by_count":47,"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":"2310.16831","title":"PERF: Panoramic Neural Radiance Field from a Single Panorama","created":"2023-10-25","cited_by_count":45,"area":null},{"id":"2404.16666","title":"PhyRecon: Physically Plausible Neural Scene Reconstruction","created":"2024-04-25","cited_by_count":45,"area":null},{"id":"2306.00987","title":"StyleGAN knows Normal, Depth, Albedo, and More","created":"2023-06-01","cited_by_count":44,"area":null},{"id":"2307.12335","title":"Learning Navigational Visual Representations with Semantic Map Supervision","created":"2023-07-23","cited_by_count":43,"area":null},{"id":"2410.02619","title":"GI-GS: Global Illumination Decomposition on Gaussian Splatting for Inverse Rendering","created":"2024-10-03","cited_by_count":42,"area":null},{"id":"2501.02464","title":"Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera","created":"2025-01-05","cited_by_count":40,"area":null},{"id":"2308.07868","title":"ObjectSDF++: Improved Object-Compositional Neural Implicit Surfaces","created":"2023-08-15","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":"2403.19549","title":"GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM","created":"2024-03-28","cited_by_count":36,"area":null},{"id":"2503.07535","title":"LBM: Latent Bridge Matching for Fast Image-to-Image Translation","created":"2025-03-10","cited_by_count":36,"area":null},{"id":"2410.15971","title":"Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly","created":"2024-10-21","cited_by_count":35,"area":null},{"id":"2305.09664","title":"Understanding 3D Object Interaction from a Single Image","created":"2023-05-16","cited_by_count":33,"area":null},{"id":"2403.09625","title":"Make-Your-3D: Fast and Consistent Subject-Driven 3D Content Generation","created":"2024-03-14","cited_by_count":32,"area":null},{"id":"2310.04787","title":"HI-SLAM: Monocular Real-time Dense Mapping with Hybrid Implicit Fields","created":"2023-10-07","cited_by_count":31,"area":null},{"id":"2407.17492","title":"Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry","created":"2024-07-04","cited_by_count":31,"area":null},{"id":"2312.13102","title":"SpecNeRF: Gaussian Directional Encoding for Specular Reflections","created":"2023-12-20","cited_by_count":30,"area":null},{"id":"2312.14198","title":"ZeroShape: Regression-based Zero-shot Shape Reconstruction","created":"2023-12-21","cited_by_count":30,"area":null},{"id":"2403.07535","title":"Adaptive Fusion of Single-View and Multi-View Depth for Autonomous Driving","created":"2024-03-12","cited_by_count":30,"area":null},{"id":"2112.09081","title":"CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data","created":"2021-12-16","cited_by_count":28,"area":null},{"id":"2407.17952","title":"BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation","created":"2024-07-25","cited_by_count":28,"area":null},{"id":"2411.02394","title":"AutoVFX: Physically Realistic Video Editing from Natural Language Instructions","created":"2024-11-04","cited_by_count":27,"area":null},{"id":"2412.18153","title":"DepthLab: From Partial to Complete","created":"2024-12-24","cited_by_count":27,"area":null},{"id":"2404.09833","title":"Video2Game: Real-time, Interactive, Realistic and Browser-Compatible Environment from a Single Video","created":"2024-04-15","cited_by_count":26,"area":null},{"id":"2211.11746","title":"Last-Mile Embodied Visual Navigation","created":"2022-11-21","cited_by_count":25,"area":null},{"id":"2407.02945","title":"VEGS: View Extrapolation of Urban Scenes in 3D Gaussian Splatting using Learned Priors","created":"2024-07-03","cited_by_count":25,"area":null},{"id":"2411.17982","title":"HI-SLAM2: Geometry-Aware Gaussian SLAM for Fast Monocular Scene Reconstruction","created":"2024-11-27","cited_by_count":25,"area":null},{"id":"2305.17102","title":"GeoVLN: Learning Geometry-Enhanced Visual Representation with Slot Attention for Vision-and-Language Navigation","created":"2023-05-26","cited_by_count":24,"area":null},{"id":"2410.17249","title":"SpectroMotion: Dynamic 3D Reconstruction of Specular Scenes","created":"2024-10-22","cited_by_count":24,"area":null},{"id":"2207.11365","title":"EgoEnv: Human-centric environment representations from egocentric video","created":"2022-07-22","cited_by_count":22,"area":null},{"id":"2212.02497","title":"PEANUT: Predicting and Navigating to Unseen Targets","created":"2022-12-05","cited_by_count":22,"area":null},{"id":"2306.09349","title":"UrbanIR: Large-Scale Urban Scene Inverse Rendering from a Single Video","created":"2023-06-15","cited_by_count":22,"area":null},{"id":"2412.11694","title":"From Specific-MLLMs to Omni-MLLMs: A Survey on MLLMs Aligned with Multi-modalities","created":"2024-12-16","cited_by_count":22,"area":null},{"id":"2211.16799","title":"NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction","created":"2022-11-30","cited_by_count":21,"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":"2401.12977","title":"IRIS: Inverse Rendering of Indoor Scenes from Low Dynamic Range Images","created":"2024-01-23","cited_by_count":20,"area":null},{"id":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20,"area":null},{"id":"2501.08643","title":"MonSter++: Unified Stereo Matching, Multi-view Stereo, and Real-time Stereo with Monodepth Priors","created":"2025-01-15","cited_by_count":19,"area":null},{"id":"2301.11326","title":"Unsupervised Volumetric Animation","created":"2023-01-26","cited_by_count":18,"area":null},{"id":"2312.04803","title":"SuperNormal: Neural Surface Reconstruction via Multi-View Normal Integration","created":"2023-12-08","cited_by_count":18,"area":null},{"id":"2408.15235","title":"Learning-based Multi-View Stereo: A Survey","created":"2024-08-27","cited_by_count":18,"area":null},{"id":"2501.05446","title":"Relative Pose Estimation through Affine Corrections of Monocular Depth Priors","created":"2025-01-09","cited_by_count":18,"area":null},{"id":"2209.15153","title":"MonoNeuralFusion: Online Monocular Neural 3D Reconstruction with Geometric Priors","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2308.10417","title":"The Change You Want to See (Now in 3D)","created":"2023-08-21","cited_by_count":17,"area":null},{"id":"2308.15536","title":"DebSDF: Delving into the Details and Bias of Neural Indoor Scene Reconstruction","created":"2023-08-29","cited_by_count":17,"area":null},{"id":"2509.18090","title":"GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction","created":"2025-09-22","cited_by_count":17,"area":null},{"id":"2304.06247","title":"ShapeClipper: Scalable 3D Shape Learning from Single-View Images via Geometric and CLIP-based Consistency","created":"2023-04-13","cited_by_count":16,"area":null},{"id":"2407.16988","title":"DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction","created":"2024-07-24","cited_by_count":16,"area":null},{"id":"2408.10178","title":"NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction","created":"2024-08-19","cited_by_count":16,"area":null},{"id":"2504.18509","title":"Eval3D: Interpretable and Fine-grained Evaluation for 3D Generation","created":"2025-04-25","cited_by_count":16,"area":null},{"id":"2503.18363","title":"MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction","created":"2025-03-24","cited_by_count":15,"area":null},{"id":"2309.10255","title":"RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery","created":"2023-09-19","cited_by_count":14,"area":null},{"id":"2311.12174","title":"LABELMAKER: Automatic Semantic Label Generation from RGB-D Trajectories","created":"2023-11-20","cited_by_count":14,"area":null},{"id":"2403.17915","title":"Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos","created":"2024-03-26","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":"2406.13607","title":"Ultra-High-Definition Image Restoration: New Benchmarks and A Dual Interaction Prior-Driven Solution","created":"2024-06-19","cited_by_count":14,"area":null},{"id":"2507.01955","title":"How Well Does GPT-4o Understand Vision? Evaluating Multimodal Foundation Models on Standard Computer Vision Tasks","created":"2025-07-02","cited_by_count":14,"area":null},{"id":"2412.03451","title":"PlanarSplatting: Accurate Planar Surface Reconstruction in 3 Minutes","created":"2024-12-04","cited_by_count":13,"area":null},{"id":"2307.10206","title":"NEAT: Distilling 3D Wireframes from Neural Attraction Fields","created":"2023-07-14","cited_by_count":12,"area":null},{"id":"2403.19314","title":"Total-Decom: Decomposed 3D Scene Reconstruction with Minimal Interaction","created":"2024-03-28","cited_by_count":12,"area":null}],"next_cursor":"100"}