{"total":455,"rows":[{"id":"2511.15706","title":"RoMa v2: Harder Better Faster Denser Feature Matching","created":"2025-11-19","cited_by_count":51,"area":null},{"id":"2606.17846","title":"Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models","created":"2026-06-16","cited_by_count":50,"area":null},{"id":"2604.13036","title":"Lyra 2.0: Explorable Generative 3D Worlds","created":"2026-04-14","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":"2604.14141","title":"LingBot-Map: Geometric Context Transformer for Streaming 3D Reconstruction","created":"2026-04-15","cited_by_count":37,"area":null},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2602.10094","title":"4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere","created":"2026-02-10","cited_by_count":22,"area":null},{"id":"2603.03283","title":"Utonia: Toward One Encoder for All Point Clouds","created":"2026-03-03","cited_by_count":21,"area":null},{"id":"2512.23437","title":"RealX3D: A Physically-Degraded 3D Benchmark for Multi-view Visual Restoration and Reconstruction","created":"2025-12-29","cited_by_count":19,"area":null},{"id":"2603.11633","title":"MV-SAM3D: Adaptive Multi-View Fusion for Layout-Aware 3D Generation","created":"2026-03-12","cited_by_count":19,"area":null},{"id":"2603.16195","title":"S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresight","created":"2026-03-17","cited_by_count":17,"area":null},{"id":"2604.01001","title":"EgoSim: Egocentric World Simulator for Embodied Interaction Generation","created":"2026-04-01","cited_by_count":14,"area":null},{"id":"2607.09024","title":"Video Generation Models are General-Purpose Vision Learners","created":"2026-07-10","cited_by_count":14,"area":null},{"id":"2603.02573","title":"Track4World: Feedforward World-centric Dense 3D Tracking of All Pixels","created":"2026-03-03","cited_by_count":13,"area":null},{"id":"2604.15284","title":"GlobalSplat: Efficient Feed-Forward 3D Gaussian Splatting via Global Scene Tokens","created":"2026-04-16","cited_by_count":12,"area":null},{"id":"2512.15508","title":"Off The Grid: Detection of Primitives for Feed-Forward 3D Gaussian Splatting","created":"2025-12-17","cited_by_count":11,"area":null},{"id":"2604.04135","title":"NTIRE 2026 3D Restoration and Reconstruction in Real-world Adverse Conditions: RealX3D Challenge Results","created":"2026-04-05","cited_by_count":11,"area":null},{"id":"2604.04931","title":"LoMa: Local Feature Matching Revisited","created":"2026-04-06","cited_by_count":11,"area":null},{"id":"2604.24764","title":"World-R1: Reinforcing 3D Constraints for Text-to-Video Generation","created":"2026-04-27","cited_by_count":11,"area":null},{"id":"2601.22054","title":"MetricAnything: Scaling Metric Depth Pretraining with Noisy Heterogeneous Sources","created":"2026-01-29","cited_by_count":10,"area":null},{"id":"2602.05827","title":"Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation","created":"2026-02-05","cited_by_count":10,"area":null},{"id":"2602.05508","title":"VGGT-Motion: Motion-Aware Calibration-Free Monocular SLAM for Long-Range Consistency","created":"2026-02-05","cited_by_count":8,"area":null},{"id":"2604.21921","title":"Context Unrolling in Omni Models","created":"2026-04-23","cited_by_count":8,"area":null},{"id":"2607.05247","title":"Vision Pretraining for Dense Spatial Perception","created":"2026-07-06","cited_by_count":8,"area":null},{"id":"2607.17967","title":"MoGe-3: Fine-Detail Monocular Geometry Estimation with Self-Guided Sparse Volumetric Refinement","created":"2026-07-20","cited_by_count":8,"area":null},{"id":"2512.07806","title":"Multi-view Pyramid Transformer: Look Coarser to See Broader","created":"2025-12-08","cited_by_count":7,"area":null},{"id":"2512.11508","title":"On Geometric Understanding and Learned Priors in Feed-forward 3D Reconstruction Models","created":"2025-12-12","cited_by_count":7,"area":null},{"id":"2602.13444","title":"FlowHOI: Flow-based Semantics-Grounded Generation of Hand-Object Interactions for Dexterous Robot Manipulation","created":"2026-02-13","cited_by_count":7,"area":null},{"id":"2605.21472","title":"Stream3D: Sequential Multi-View 3D Generation via Evidential Memory","created":"2026-05-20","cited_by_count":7,"area":null},{"id":"2607.06560","title":"Vision as Unified Multimodal Generation","created":"2026-07-07","cited_by_count":7,"area":null},{"id":"2603.07660","title":"Holi-Spatial: Evolving Video Streams into Holistic 3D Spatial Intelligence","created":"2026-03-08","cited_by_count":6,"area":null},{"id":"2603.23502","title":"OccAny: Generalized Unconstrained Urban 3D Occupancy","created":"2026-03-24","cited_by_count":6,"area":null},{"id":"2604.14025","title":"Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective","created":"2026-04-15","cited_by_count":6,"area":null},{"id":"2604.18747","title":"URoPE: Universal Relative Position Embedding across Geometric Spaces","created":"2026-04-20","cited_by_count":6,"area":null},{"id":"2605.30215","title":"D\\'ej\\`a View: Looping Transformers for Multi-View 3D Reconstruction","created":"2026-05-28","cited_by_count":6,"area":null},{"id":"2606.13432","title":"OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data","created":"2026-06-11","cited_by_count":6,"area":null},{"id":"2606.31388","title":"One Video, One World: Turning Monocular Video into Physical 4D Scenes","created":"2026-06-30","cited_by_count":6,"area":null},{"id":"2607.20889","title":"Engine-Native Editable 3D World Reconstruction with Objects and Lighting","created":"2026-07-23","cited_by_count":6,"area":null},{"id":"2512.20770","title":"OccuFly: A 3D Vision Benchmark for Semantic Scene Completion from the Aerial Perspective","created":"2025-12-23","cited_by_count":5,"area":null},{"id":"2512.22581","title":"KV-Tracker: Real-Time Pose Tracking with Transformers","created":"2025-12-27","cited_by_count":5,"area":null},{"id":"2603.17840","title":"Video Understanding: From Geometry and Semantics to Unified Models","created":"2026-03-18","cited_by_count":5,"area":null},{"id":"2604.01479","title":"RecGen3D: Reconstruction-Guided 3D Generation in a Shared Canonical Space","created":"2026-04-01","cited_by_count":5,"area":null},{"id":"2604.09429","title":"Rays as Pixels: Learning A Joint Distribution of Videos and Camera Trajectories","created":"2026-04-10","cited_by_count":5,"area":null},{"id":"2605.22819","title":"Cambrian-P: Pose-Grounded Video Understanding","created":"2026-05-21","cited_by_count":5,"area":null},{"id":"2605.23888","title":"GenRecon: Bridging Generative Priors for Multi-View 3D Scene Reconstruction","created":"2026-05-22","cited_by_count":5,"area":null},{"id":"2606.05102","title":"ZipSplat: Fewer Gaussians, Better Splats","created":"2026-06-03","cited_by_count":5,"area":null},{"id":"2607.22534","title":"SM4RT: Learning Structured Motion Geometry for 4D Reconstruction","created":"2026-07-24","cited_by_count":5,"area":null},{"id":"2512.02006","title":"MV-TAP: Tracking Any Point in Multi-View Videos","created":"2025-12-01","cited_by_count":4,"area":null},{"id":"2512.10267","title":"Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2512.17541","title":"FLEG: Feed-Forward Language Embedded Gaussian Splatting from Any Views via Compact Semantic Representation","created":"2025-12-19","cited_by_count":4,"area":null},{"id":"2602.05321","title":"Wid3R: Wide Field-of-View 3D Reconstruction via Camera Model Conditioning","created":"2026-02-05","cited_by_count":4,"area":null},{"id":"2603.12265","title":"OmniStream: Mastering Perception, Reconstruction and Action in Continuous Streams","created":"2026-03-12","cited_by_count":4,"area":null},{"id":"2603.25993","title":"FAST3DIS: Feed-forward Anchored Scene Transformer for 3D Instance Segmentation","created":"2026-03-27","cited_by_count":4,"area":null},{"id":"2604.16272","title":"VEFX-Bench: A Holistic Benchmark for Generic Video Editing and Visual Effects","created":"2026-04-17","cited_by_count":4,"area":null},{"id":"2605.03359","title":"Mix3R: Mixing Feed-forward Reconstruction and Generative 3D Priors for Joint Multi-view Aligned 3D Reconstruction and Pose Estimation","created":"2026-05-05","cited_by_count":4,"area":null},{"id":"2605.05207","title":"Syn4D: A Multiview Synthetic 4D Dataset","created":"2026-05-06","cited_by_count":4,"area":null},{"id":"2607.17097","title":"HarmoHOI: Harmonizing Appearance and 3D Motion for Multi-view Hand-Object Interaction Synthesis","created":"2026-07-19","cited_by_count":4,"area":null},{"id":"2511.20620","title":"Wanderland: Geometrically Grounded Simulation for Open-World Embodied AI","created":"2025-11-25","cited_by_count":3,"area":null},{"id":"2511.23191","title":"GeoWorld: Providing Full-frame Geometry Features to Facilitate 3D Scene Generation","created":"2025-11-28","cited_by_count":3,"area":null},{"id":"2601.15951","title":"EVolSplat4D: Efficient Volume-based Gaussian Splatting for 4D Urban Scene Synthesis","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2601.16020","title":"Keyframe-Based Feed-Forward Visual Odometry","created":"2026-01-22","cited_by_count":3,"area":null},{"id":"2601.18923","title":"DeFM: Learning Foundation Representations from Depth for Robotics","created":"2026-01-26","cited_by_count":3,"area":null},{"id":"2601.22046","title":"PLANING: A Loosely Coupled Triangle-Gaussian Framework for Streaming 3D Reconstruction","created":"2026-01-29","cited_by_count":3,"area":null},{"id":"2603.10408","title":"Motion Forcing: A Decoupled Framework for Robust Video Generation in Motion Dynamics","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2603.11174","title":"GGPT: Geometry Grounded Point Transformer","created":"2026-03-11","cited_by_count":3,"area":null},{"id":"2603.14686","title":"MVHOI: Bridge Multi-view Condition to Complex Human-Object Interaction Video Reenactment via 3D Foundation Model","created":"2026-03-16","cited_by_count":3,"area":null},{"id":"2603.18493","title":"FILT3R: Latent State Adaptive Kalman Filter for Streaming 3D Reconstruction","created":"2026-03-19","cited_by_count":3,"area":null},{"id":"2603.20588","title":"RayMap3R: Inference-Time RayMap for Dynamic 3D Reconstruction","created":"2026-03-21","cited_by_count":3,"area":null},{"id":"2603.25707","title":"TRACE: Object Motion Editing in Videos with First-Frame Trajectory Guidance","created":"2026-03-26","cited_by_count":3,"area":null},{"id":"2603.28757","title":"SonoWorld: From One Image to a 3D Audio-Visual Scene","created":"2026-03-30","cited_by_count":3,"area":null},{"id":"2604.12929","title":"Grasp in Gaussians: Fast Monocular Reconstruction of Dynamic Hand-Object Interactions","created":"2026-04-14","cited_by_count":3,"area":null},{"id":"2604.26567","title":"AirZoo: A Unified Large-Scale Dataset for Grounding Aerial Geometric 3D Vision","created":"2026-04-29","cited_by_count":3,"area":null},{"id":"2605.17942","title":"UAVFF3D: A Geometry-Aware Benchmark for Feed-Forward UAV 3D Reconstruction","created":"2026-05-18","cited_by_count":3,"area":null},{"id":"2605.23903","title":"Geo-Align: Video Generation Alignment via Metric Geometry Reward","created":"2026-05-22","cited_by_count":3,"area":null},{"id":"2605.30060","title":"Towards Consistent Video Geometry Estimation","created":"2026-05-28","cited_by_count":3,"area":null},{"id":"2606.29716","title":"AerialMetric: Benchmarking and Adapting UAV Monocular Metric Depth Estimation in the Real World","created":"2026-06-29","cited_by_count":3,"area":null},{"id":"2606.31249","title":"Rethinking the Role of Feature Engineering and Learning Strategies in Few-Shot Hidden Emotion Recognition","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2606.31946","title":"World Narrative Model for Highly Controllable Video Generation: A Paradigm Shift from Pixel Sampling to Physical World Orchestration","created":"2026-06-30","cited_by_count":3,"area":null},{"id":"2607.06555","title":"ProxyPose: 6-DoF Pose Tracking via Video-to-Video Translation","created":"2026-07-07","cited_by_count":3,"area":null},{"id":"2607.11588","title":"FoundationGeo: Learning Spatial Pixel-Wise Fields for Monocular Metric Geometry","created":"2026-07-13","cited_by_count":3,"area":null},{"id":"2607.12993","title":"X-Lens: Real-Time Metric Depth Estimation with Heterogeneous Cameras","created":"2026-07-14","cited_by_count":3,"area":null},{"id":"2607.20660","title":"Axolotl3D: a Unified Framework for Faithful 3D Shape Completion","created":"2026-07-22","cited_by_count":3,"area":null},{"id":"2608.01186","title":"QuerySplat: Decoupling Geometry and Appearance Representations in 3DGS Prediction","created":"2026-08-02","cited_by_count":3,"area":null},{"id":"2609.08848","title":"FIRE3D: Feed-forward Interactive 3D Scene Reconstruction Within A Minute","created":"2026-09-08","cited_by_count":3,"area":null},{"id":"2512.12774","title":"Fast 2DGS: Efficient Image Representation with Deep Gaussian Prior","created":"2025-12-14","cited_by_count":2,"area":null},{"id":"2601.03024","title":"SA-ResGS: Self-Augmented Residual 3D Gaussian Splatting for Next Best View Selection","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2601.05246","title":"Pixel-Perfect Visual Geometry Estimation","created":"2026-01-08","cited_by_count":2,"area":null},{"id":"2601.22039","title":"Understanding Multimodal Complementarity for Single-Frame Action Anticipation","created":"2026-01-29","cited_by_count":2,"area":null},{"id":"2602.01741","title":"Tail-Aware Post-Training Quantization for 3D Geometry Models","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.23224","title":"UniScale: Unified Scale-Aware 3D Reconstruction for Multi-View Understanding via Prior Injection for Robotic Perception","created":"2026-02-26","cited_by_count":2,"area":null},{"id":"2603.09896","title":"Stepping VLMs onto the Court: Benchmarking Spatial Intelligence in Sports","created":"2026-03-10","cited_by_count":2,"area":null},{"id":"2603.16099","title":"OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.16844","title":"M^3: Dense Matching Meets Multi-View Foundation Models for Monocular Gaussian Splatting SLAM","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2603.19547","title":"SeeClear: Reliable Transparent Object Depth Estimation via Generative Opacification","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2603.21064","title":"2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting","created":"2026-03-22","cited_by_count":2,"area":null},{"id":"2603.25265","title":"ViewSplat: View-Adaptive 3D Gaussian Splatting for Feed-Forward Synthesis","created":"2026-03-26","cited_by_count":2,"area":null},{"id":"2603.27542","title":"MV-RoMa: From Pairwise Matching into Multi-View Track Reconstruction","created":"2026-03-29","cited_by_count":2,"area":null},{"id":"2604.01030","title":"Diff3R: Feed-forward 3D Gaussian Splatting with Uncertainty-aware Differentiable Optimization","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.01207","title":"TRACE: High-Fidelity 3D Scene Editing via Tangible Reconstruction and Geometry-Aligned Contextual Video Masking","created":"2026-04-01","cited_by_count":2,"area":null},{"id":"2604.04887","title":"HorizonWeaver: Generalizable Multi-Level Semantic Editing for Driving Scenes","created":"2026-04-06","cited_by_count":2,"area":null}],"next_cursor":"100"}