{"total":1360,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422,"area":null},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044,"area":null},{"id":"2404.12390","title":"BLINK: Multimodal Large Language Models Can See but Not Perceive","created":"2024-04-18","cited_by_count":550,"area":"mllm"},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548,"area":null},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442,"area":null},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404,"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":"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":"2503.03751","title":"GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Control","created":"2025-03-05","cited_by_count":341,"area":null},{"id":"2406.01584","title":"SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models","created":"2024-06-03","cited_by_count":311,"area":"lr"},{"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":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286,"area":"diffusion"},{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286,"area":null},{"id":"2406.09403","title":"Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models","created":"2024-06-13","cited_by_count":268,"area":"lr"},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261,"area":null},{"id":"2407.13764","title":"Shape of Motion: 4D Reconstruction from a Single Video","created":"2024-07-18","cited_by_count":250,"area":null},{"id":"2406.06978","title":"Hydra-MDP: End-to-end Multimodal Planning with Multi-target Hydra-Distillation","created":"2024-06-11","cited_by_count":249,"area":"distill"},{"id":"2511.16624","title":"SAM 3D: 3Dfy Anything in Images","created":"2025-11-20","cited_by_count":247,"area":null},{"id":"2408.12569","title":"Sapiens: Foundation for Human Vision Models","created":"2024-08-22","cited_by_count":229,"area":null},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228,"area":null},{"id":"2507.04447","title":"DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge","created":"2025-07-06","cited_by_count":213,"area":"vla"},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207,"area":null},{"id":"2412.12392","title":"MASt3R-SLAM: Real-Time Dense SLAM with 3D Reconstruction Priors","created":"2024-12-16","cited_by_count":205,"area":null},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204,"area":null},{"id":"2407.14505","title":"T2V-CompBench: A Comprehensive Benchmark for Compositional Text-to-video Generation","created":"2024-07-19","cited_by_count":185,"area":null},{"id":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180,"area":null},{"id":"2405.17421","title":"MoSca: Dynamic Gaussian Fusion from Casual Videos via 4D Motion Scaffolds","created":"2024-05-27","cited_by_count":179,"area":null},{"id":"2501.09898","title":"FoundationStereo: Zero-Shot Stereo Matching","created":"2025-01-17","cited_by_count":173,"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":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166,"area":"diffusion"},{"id":"2411.18613","title":"CAT4D: Create Anything in 4D with Multi-View Video Diffusion Models","created":"2024-11-27","cited_by_count":161,"area":"diffusion"},{"id":"2504.00983","title":"WorldScore: A Unified Evaluation Benchmark for World Generation","created":"2025-04-01","cited_by_count":156,"area":null},{"id":"2406.13642","title":"SpatialBot: Precise Spatial Understanding with Vision Language Models","created":"2024-06-19","cited_by_count":152,"area":"mllm"},{"id":"2408.02657","title":"Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretraining","created":"2024-08-05","cited_by_count":150,"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":"2603.14482","title":"V-JEPA 2.1: Unlocking Dense Features in Video Self-Supervised Learning","created":"2026-03-15","cited_by_count":117,"area":null},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116,"area":null},{"id":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114,"area":null},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2404.07199","title":"RealmDreamer: Text-Driven 3D Scene Generation with Inpainting and Depth Diffusion","created":"2024-04-10","cited_by_count":109,"area":"diffusion"},{"id":"2403.17346","title":"TRAM: Global Trajectory and Motion of 3D Humans from in-the-wild Videos","created":"2024-03-26","cited_by_count":106,"area":null},{"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":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2502.04144","title":"HD-EPIC: A Highly-Detailed Egocentric Video Dataset","created":"2025-02-06","cited_by_count":104,"area":null},{"id":"2406.01493","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","created":"2024-06-03","cited_by_count":100,"area":"diffusion"},{"id":"2406.18717","title":"Dynamic Gaussian Marbles for Novel View Synthesis of Casual Monocular Videos","created":"2024-06-26","cited_by_count":97,"area":null},{"id":"2503.18945","title":"Aether: Geometric-Aware Unified World Modeling","created":"2025-03-24","cited_by_count":97,"area":"wm"},{"id":"2410.01756","title":"ImageFolder: Autoregressive Image Generation with Folded Tokens","created":"2024-10-02","cited_by_count":94,"area":"diffusion"},{"id":"2506.06659","title":"DriveSuprim: Towards Precise Trajectory Selection for End-to-End Planning","created":"2025-06-07","cited_by_count":94,"area":null},{"id":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91,"area":null},{"id":"2412.07679","title":"RADIOv2.5: Improved Baselines for Agglomerative Vision Foundation Models","created":"2024-12-10","cited_by_count":89,"area":null},{"id":"2412.09621","title":"Stereo4D: Learning How Things Move in 3D from Internet Stereo Videos","created":"2024-12-12","cited_by_count":89,"area":null},{"id":"2502.20900","title":"DexGraspVLA: A Vision-Language-Action Framework Towards General Dexterous Grasping","created":"2025-02-28","cited_by_count":89,"area":"vla"},{"id":"2504.13152","title":"St4RTrack: Simultaneous 4D Reconstruction and Tracking in the World","created":"2025-04-17","cited_by_count":89,"area":null},{"id":"2507.12462","title":"SpatialTrackerV2: 3D Point Tracking Made Easy","created":"2025-07-16","cited_by_count":87,"area":null},{"id":"2510.07077","title":"Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications","created":"2025-10-08","cited_by_count":84,"area":"mllm"},{"id":"2409.11355","title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think","created":"2024-09-17","cited_by_count":83,"area":"diffusion"},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82,"area":null},{"id":"2405.15364","title":"NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer","created":"2024-05-24","cited_by_count":79,"area":"diffusion"},{"id":"2412.03079","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","created":"2024-12-04","cited_by_count":79,"area":null},{"id":"2407.17418","title":"3D Gaussian Splatting: Survey, Technologies, Challenges, and Opportunities","created":"2024-07-24","cited_by_count":78,"area":null},{"id":"2412.11198","title":"GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control","created":"2024-12-15","cited_by_count":78,"area":"wm"},{"id":"2505.09358","title":"Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis","created":"2025-05-14","cited_by_count":78,"area":"diffusion"},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77,"area":null},{"id":"2509.09676","title":"SpatialVID: A Large-Scale Video Dataset with Spatial Annotations","created":"2025-09-11","cited_by_count":77,"area":null},{"id":"2403.06090","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","created":"2024-03-10","cited_by_count":74,"area":"diffusion"},{"id":"2412.14015","title":"Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation","created":"2024-12-18","cited_by_count":74,"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":"2407.05921","title":"TAPVid-3D: A Benchmark for Tracking Any Point in 3D","created":"2024-07-08","cited_by_count":72,"area":null},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71,"area":null},{"id":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2510.21571","title":"Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videos","created":"2025-10-24","cited_by_count":70,"area":"vla"},{"id":"2504.07961","title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","created":"2025-04-10","cited_by_count":67,"area":"diffusion"},{"id":"2506.06664","title":"Generalized Trajectory Scoring for End-to-end Multimodal Planning","created":"2025-06-07","cited_by_count":67,"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":"2501.02973","title":"HaWoR: World-Space Hand Motion Reconstruction from Egocentric Videos","created":"2025-01-06","cited_by_count":66,"area":null},{"id":"2406.07547","title":"Zero-shot Image Editing with Reference Imitation","created":"2024-06-11","cited_by_count":65,"area":null},{"id":"2409.16160","title":"MIMO: Controllable Character Video Synthesis with Spatial Decomposed Modeling","created":"2024-09-24","cited_by_count":64,"area":null},{"id":"2405.02280","title":"DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos","created":"2024-05-03","cited_by_count":63,"area":null},{"id":"2503.19108","title":"Your ViT is Secretly an Image Segmentation Model","created":"2025-03-24","cited_by_count":63,"area":null},{"id":"2410.22128","title":"PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting","created":"2024-10-29","cited_by_count":62,"area":null},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"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":"2407.20179","title":"Theia: Distilling Diverse Vision Foundation Models for Robot Learning","created":"2024-07-29","cited_by_count":61,"area":null},{"id":"2410.15067","title":"A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends","created":"2024-10-19","cited_by_count":60,"area":null},{"id":"2406.11819","title":"MegaScenes: Scene-Level View Synthesis at Scale","created":"2024-06-17","cited_by_count":58,"area":null},{"id":"2507.00416","title":"Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding","created":"2025-07-01","cited_by_count":58,"area":"vla"},{"id":"2410.10815","title":"Depth Any Video with Scalable Synthetic Data","created":"2024-10-14","cited_by_count":57,"area":"diffusion"},{"id":"2404.11613","title":"InFusion: Inpainting 3D Gaussians via Learning Depth Completion from Diffusion Prior","created":"2024-04-17","cited_by_count":56,"area":"diffusion"},{"id":"2406.10373","title":"Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections","created":"2024-06-14","cited_by_count":56,"area":null},{"id":"2403.13438","title":"SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors","created":"2024-03-18","cited_by_count":54,"area":"lr"},{"id":"2409.18121","title":"Robot See Robot Do: Imitating Articulated Object Manipulation with Monocular 4D Reconstruction","created":"2024-09-26","cited_by_count":54,"area":null},{"id":"2410.10777","title":"UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation","created":"2024-10-14","cited_by_count":54,"area":null},{"id":"2501.09466","title":"DEFOM-Stereo: Depth Foundation Model Based Stereo Matching","created":"2025-01-16","cited_by_count":52,"area":null},{"id":"2505.17015","title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models","created":"2025-05-22","cited_by_count":52,"area":"mllm"},{"id":"2406.00434","title":"MoDGS: Dynamic Gaussian Splatting from Casually-captured Monocular Videos with Depth Priors","created":"2024-06-01","cited_by_count":51,"area":null},{"id":"2510.07316","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers","created":"2025-10-08","cited_by_count":51,"area":"diffusion"},{"id":"2406.17601","title":"Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text","created":"2024-06-25","cited_by_count":50,"area":"diffusion"}],"next_cursor":"100"}