{"total":1422,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"area":null},{"id":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044,"area":null},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692,"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":"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":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"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":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286,"area":null},{"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":"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":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204,"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":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"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":"2501.16411","title":"PhysBench: Benchmarking and Enhancing Vision-Language Models for Physical World Understanding","created":"2025-01-27","cited_by_count":160,"area":"mllm"},{"id":"2411.19167","title":"HOT3D: Hand and Object Tracking in 3D from Egocentric Multi-View Videos","created":"2024-11-28","cited_by_count":129,"area":null},{"id":"2503.05638","title":"TrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models","created":"2025-03-07","cited_by_count":125,"area":"diffusion"},{"id":"2503.16429","title":"Sonata: Self-Supervised Learning of Reliable Point Representations","created":"2025-03-20","cited_by_count":110,"area":null},{"id":"2503.14492","title":"Cosmos-Transfer1: Conditional World Generation with Adaptive Multimodal Control","created":"2025-03-18","cited_by_count":106,"area":null},{"id":"2412.07774","title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics","created":"2024-12-10","cited_by_count":102,"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":"2511.05491","title":"Visual Spatial Tuning","created":"2025-11-07","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":"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":"2412.03079","title":"Align3R: Aligned Monocular Depth Estimation for Dynamic Videos","created":"2024-12-04","cited_by_count":79,"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":"2602.08971","title":"WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models","created":"2026-02-09","cited_by_count":76,"area":"wm"},{"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":"2412.03548","title":"Perception Tokens Enhance Visual Reasoning in Multimodal Language Models","created":"2024-12-04","cited_by_count":71,"area":"lr"},{"id":"2504.20024","title":"SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning","created":"2025-04-28","cited_by_count":68,"area":"lr"},{"id":"2504.07961","title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","created":"2025-04-10","cited_by_count":67,"area":"diffusion"},{"id":"2509.07996","title":"3D and 4D World Modeling: A Survey","created":"2025-09-04","cited_by_count":67,"area":"wm"},{"id":"2503.16591","title":"UniK3D: Universal Camera Monocular 3D Estimation","created":"2025-03-20","cited_by_count":62,"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":"2409.00638","title":"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching","created":"2024-09-01","cited_by_count":59,"area":null},{"id":"2410.10815","title":"Depth Any Video with Scalable Synthetic Data","created":"2024-10-14","cited_by_count":57,"area":"diffusion"},{"id":"2502.10059","title":"RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control","created":"2025-02-14","cited_by_count":57,"area":null},{"id":"2412.03934","title":"InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models","created":"2024-12-05","cited_by_count":56,"area":"wm"},{"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":"2509.20360","title":"EditVerse: Unifying Image and Video Editing and Generation with In-Context Learning","created":"2025-09-24","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":"2510.07316","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers","created":"2025-10-08","cited_by_count":51,"area":"diffusion"},{"id":"2411.00771","title":"CityGaussianV2: Efficient and Geometrically Accurate Reconstruction for Large-Scale Scenes","created":"2024-11-01","cited_by_count":50,"area":null},{"id":"2411.02319","title":"GenXD: Generating Any 3D and 4D Scenes","created":"2024-11-04","cited_by_count":50,"area":null},{"id":"2412.10137","title":"Constraint-Aware Zero-Shot Vision-Language Navigation in Continuous Environments","created":"2024-12-13","cited_by_count":50,"area":null},{"id":"2412.13389","title":"Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion","created":"2024-12-18","cited_by_count":50,"area":"diffusion"},{"id":"2503.09595","title":"PISA Experiments: Exploring Physics Post-Training for Video Diffusion Models by Watching Stuff Drop","created":"2025-03-12","cited_by_count":50,"area":"diffusion"},{"id":"2603.20633","title":"Seed1.8 Model Card: Towards Generalized Real-World Agency","created":"2026-03-21","cited_by_count":50,"area":null},{"id":"2605.02881","title":"MolmoAct2: Action Reasoning Models for Real-world Deployment","created":"2026-05-04","cited_by_count":50,"area":"lr"},{"id":"2412.03526","title":"Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos","created":"2024-12-04","cited_by_count":49,"area":null},{"id":"2501.02341","title":"UAVs Meet LLMs: Overviews and Perspectives Toward Agentic Low-Altitude Mobility","created":"2025-01-04","cited_by_count":49,"area":"agents"},{"id":"2505.08712","title":"NavDP: Learning Sim-to-Real Navigation Diffusion Policy with Privileged Information Guidance","created":"2025-05-13","cited_by_count":49,"area":"diffusion"},{"id":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49,"area":null},{"id":"2504.02918","title":"Evaluating Newtonian Mechanics in Video Generative Models with Real Physical Systems","created":"2025-04-03","cited_by_count":48,"area":"wm"},{"id":"2509.19297","title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","created":"2025-09-23","cited_by_count":48,"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":"2507.23478","title":"3D-R1: Enhancing Reasoning in 3D VLMs for Unified Scene Understanding","created":"2025-07-31","cited_by_count":47,"area":"lr"},{"id":"2505.12448","title":"SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning","created":"2025-05-18","cited_by_count":46,"area":"lr"},{"id":"2510.13375","title":"DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoning","created":"2025-10-15","cited_by_count":46,"area":"lr"},{"id":"2412.04380","title":"EmbodiedOcc: Embodied 3D Occupancy Prediction for Vision-based Online Scene Understanding","created":"2024-12-05","cited_by_count":45,"area":null},{"id":"2412.11673","title":"DINO-Foresight: Looking into the Future with DINO","created":"2024-12-16","cited_by_count":45,"area":null},{"id":"2512.08765","title":"Wan-Move: Motion-controllable Video Generation via Latent Trajectory Guidance","created":"2025-12-09","cited_by_count":45,"area":null},{"id":"2503.16318","title":"Dynamic Point Maps: A Versatile Representation for Dynamic 3D Reconstruction","created":"2025-03-20","cited_by_count":44,"area":null},{"id":"2604.20329","title":"Image Generators are Generalist Vision Learners","created":"2026-04-22","cited_by_count":43,"area":null},{"id":"2408.08206","title":"WaterSplatting: Fast Underwater 3D Scene Reconstruction Using Gaussian Splatting","created":"2024-08-15","cited_by_count":41,"area":null},{"id":"2509.07979","title":"Visual Representation Alignment for Multimodal Large Language Models","created":"2025-09-09","cited_by_count":41,"area":"lr"},{"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":"2502.07685","title":"Matrix3D: Large Photogrammetry Model All-in-One","created":"2025-02-11","cited_by_count":40,"area":null},{"id":"2412.15214","title":"LeviTor: 3D Trajectory Oriented Image-to-Video Synthesis","created":"2024-12-19","cited_by_count":39,"area":null},{"id":"2501.02690","title":"GS-DiT: Advancing Video Generation with Pseudo 4D Gaussian Fields through Efficient Dense 3D Point Tracking","created":"2025-01-05","cited_by_count":39,"area":null},{"id":"2502.17157","title":"DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks","created":"2025-02-24","cited_by_count":39,"area":"diffusion"},{"id":"2504.07960","title":"VisualCloze: A Universal Image Generation Framework via Visual In-Context Learning","created":"2025-04-10","cited_by_count":39,"area":"diffusion"},{"id":"2509.01656","title":"Reinforced Visual Perception with Tools","created":"2025-09-01","cited_by_count":38,"area":"lr"},{"id":"2409.07447","title":"StereoCrafter: Diffusion-based Generation of Long and High-fidelity Stereoscopic 3D from Monocular Videos","created":"2024-09-11","cited_by_count":37,"area":"diffusion"},{"id":"2410.12669","title":"3DIS: Depth-Driven Decoupled Instance Synthesis for Text-to-Image Generation","created":"2024-10-16","cited_by_count":37,"area":null},{"id":"2502.08244","title":"FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis","created":"2025-02-12","cited_by_count":37,"area":"diffusion"},{"id":"2504.01016","title":"GeometryCrafter: Consistent Geometry Estimation for Open-world Videos with Diffusion Priors","created":"2025-04-01","cited_by_count":37,"area":"diffusion"},{"id":"2506.06199","title":"3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model","created":"2025-06-06","cited_by_count":37,"area":"wm"},{"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":"2505.10565","title":"Depth Anything with Any Prior","created":"2025-05-15","cited_by_count":36,"area":null},{"id":"2505.10696","title":"TartanGround: A Large-Scale Dataset for Ground Robot Perception and Navigation","created":"2025-05-15","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":"2503.09151","title":"Reangle-A-Video: 4D Video Generation as Video-to-Video Translation","created":"2025-03-12","cited_by_count":35,"area":"diffusion"},{"id":"2505.08787","title":"UniSkill: Imitating Human Videos via Cross-Embodiment Skill Representations","created":"2025-05-13","cited_by_count":35,"area":null},{"id":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35,"area":null},{"id":"2411.16443","title":"SplatFlow: Multi-View Rectified Flow Model for 3D Gaussian Splatting Synthesis","created":"2024-11-25","cited_by_count":34,"area":"diffusion"},{"id":"2412.21117","title":"Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation","created":"2024-12-30","cited_by_count":34,"area":"diffusion"},{"id":"2504.04158","title":"JarvisIR: Elevating Autonomous Driving Perception with Intelligent Image Restoration","created":"2025-04-05","cited_by_count":34,"area":"driving"},{"id":"2506.21526","title":"WAFT: Warping-Alone Field Transforms for Optical Flow","created":"2025-06-26","cited_by_count":34,"area":null},{"id":"2512.01989","title":"PAI-Bench: A Comprehensive Benchmark For Physical AI","created":"2025-12-01","cited_by_count":34,"area":"mllm"}],"next_cursor":"100"}