{"total":180,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"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":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2505.23716","title":"AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views","created":"2025-05-29","cited_by_count":243,"area":null},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161,"area":null},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136,"area":"wm"},{"id":"2503.10592","title":"CameraCtrl II: Dynamic Scene Exploration via Camera-controlled Video Diffusion Models","created":"2025-03-13","cited_by_count":98,"area":"diffusion"},{"id":"2509.02560","title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","created":"2025-09-02","cited_by_count":98,"area":"inference"},{"id":"2507.07982","title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","created":"2025-07-10","cited_by_count":96,"area":"wm"},{"id":"2505.00702","title":"RayZer: A Self-supervised Large View Synthesis Model","created":"2025-05-01","cited_by_count":77,"area":null},{"id":"2506.01946","title":"3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding","created":"2025-06-02","cited_by_count":70,"area":"lr"},{"id":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67,"area":null},{"id":"2509.12201","title":"OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling","created":"2025-09-15","cited_by_count":62,"area":"wm"},{"id":"2503.14445","title":"Bolt3D: Generating 3D Scenes in Seconds","created":"2025-03-18","cited_by_count":59,"area":"diffusion"},{"id":"2508.15769","title":"SceneGen: Single-Image 3D Scene Generation in One Feedforward Pass","created":"2025-08-21","cited_by_count":54,"area":null},{"id":"2601.00393","title":"NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos","created":"2026-01-01","cited_by_count":46,"area":"wm"},{"id":"2507.18255","title":"LONG3R: Long Sequence Streaming 3D Reconstruction","created":"2025-07-24","cited_by_count":45,"area":null},{"id":"2511.21688","title":"G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning","created":"2025-11-26","cited_by_count":44,"area":"lr"},{"id":"2604.14268","title":"HY-World 2.0: A Multi-Modal World Model for Reconstructing, Generating, and Simulating 3D Worlds","created":"2026-04-15","cited_by_count":44,"area":"wm"},{"id":"2509.21657","title":"FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction","created":"2025-09-25","cited_by_count":38,"area":"wm"},{"id":"2511.07321","title":"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting","created":"2025-11-10","cited_by_count":37,"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":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35,"area":null},{"id":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","created":"2025-09-05","cited_by_count":35,"area":null},{"id":"2601.09499","title":"V-DPM: 4D Video Reconstruction with Dynamic Point Maps","created":"2026-01-14","cited_by_count":34,"area":null},{"id":"2604.08542","title":"Scal3R: Scalable Test-Time Training for Large-Scale 3D Reconstruction","created":"2026-04-09","cited_by_count":31,"area":null},{"id":"2511.19971","title":"VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction","created":"2025-11-25","cited_by_count":28,"area":null},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27,"area":null},{"id":"2603.04385","title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","created":"2026-03-04","cited_by_count":26,"area":null},{"id":"2605.15195","title":"VGGT-$\\Omega$","created":"2026-05-14","cited_by_count":26,"area":null},{"id":"2509.07120","title":"Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers","created":"2025-09-08","cited_by_count":23,"area":null},{"id":"2510.27234","title":"MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts","created":"2025-10-31","cited_by_count":21,"area":"moe"},{"id":"2508.17972","title":"SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization","created":"2025-08-25","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":"2507.23277","title":"iLRM: An Iterative Large 3D Reconstruction Model","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2508.09977","title":"A Survey on 3D Gaussian Splatting Applications: Segmentation, Editing, and Generation","created":"2025-08-13","cited_by_count":19,"area":null},{"id":"2602.23361","title":"VGG-T$^3$: Offline Feed-Forward 3D Reconstruction at Scale","created":"2026-02-26","cited_by_count":18,"area":null},{"id":"2512.01540","title":"FlashVGGT: Efficient and Scalable Visual Geometry Transformers with Compressed Descriptor Attention","created":"2025-12-01","cited_by_count":17,"area":null},{"id":"2505.11992","title":"SpatialCrafter: Unleashing the Imagination of Video Diffusion Models for Scene Reconstruction from Limited Observations","created":"2025-05-17","cited_by_count":16,"area":"diffusion"},{"id":"2503.10286","title":"VicaSplat: A Single Run is All You Need for 3D Gaussian Splatting and Camera Estimation from Unposed Video Frames","created":"2025-03-13","cited_by_count":15,"area":null},{"id":"2506.18839","title":"4Real-Video-V2: Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation","created":"2025-06-18","cited_by_count":14,"area":null},{"id":"2508.12720","title":"Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting","created":"2025-08-18","cited_by_count":14,"area":null},{"id":"2506.05327","title":"Revisiting Depth Representations for Feed-Forward 3D Gaussian Splatting","created":"2025-06-05","cited_by_count":12,"area":null},{"id":"2510.13454","title":"Text-to-3D by Stitching a Multi-view Reconstruction Network to a Video Generator","created":"2025-10-15","cited_by_count":11,"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":"2503.21082","title":"Can Video Diffusion Model Reconstruct 4D Geometry?","created":"2025-03-27","cited_by_count":10,"area":"diffusion"},{"id":"2511.18416","title":"4D-VGGT: A General Foundation Model with SpatioTemporal Awareness for Dynamic Scene Geometry Estimation","created":"2025-11-23","cited_by_count":10,"area":null},{"id":"2512.02870","title":"Taming Camera-Controlled Video Generation with Verifiable Geometry Reward","created":"2025-12-02","cited_by_count":10,"area":"diffusion"},{"id":"2510.08551","title":"ARTDECO: Towards Efficient and High-Fidelity On-the-Fly 3D Reconstruction with Structured Scene Representation","created":"2025-10-09","cited_by_count":9,"area":null},{"id":"2601.01222","title":"UniSH: Unifying Scene and Human Reconstruction in a Feed-Forward Pass","created":"2026-01-03","cited_by_count":9,"area":null},{"id":"2603.05078","title":"MoRe: Motion-aware Feed-forward 4D Reconstruction Transformer","created":"2026-03-05","cited_by_count":9,"area":null},{"id":"2603.20176","title":"LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis","created":"2026-03-20","cited_by_count":9,"area":null},{"id":"2604.14267","title":"Enhancing LLM-based Search Agents via Contribution Weighted Group Relative Policy Optimization","created":"2026-04-15","cited_by_count":9,"area":"lr"},{"id":"2506.08862","title":"StreamSplat: Towards Online Dynamic 3D Reconstruction from Uncalibrated Video Streams","created":"2025-06-10","cited_by_count":8,"area":null},{"id":"2507.18541","title":"Unposed 3DGS Reconstruction with Probabilistic Procrustes Mapping","created":"2025-07-24","cited_by_count":8,"area":null},{"id":"2509.11003","title":"AD-GS: Alternating Densification for Sparse-Input 3D Gaussian Splatting","created":"2025-09-13","cited_by_count":8,"area":null},{"id":"2509.25191","title":"VGGT-X: When VGGT Meets Dense Novel View Synthesis","created":"2025-09-29","cited_by_count":8,"area":null},{"id":"2510.17568","title":"PAGE-4D: Disentangled pose and geometry estimation for vggt-4d perception","created":"2025-10-20","cited_by_count":8,"area":null},{"id":"2510.20776","title":"CUPID: Generative 3D Reconstruction via Joint Object and Pose Modeling","created":"2025-10-23","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":"2506.01933","title":"E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models","created":"2025-06-02","cited_by_count":7,"area":null},{"id":"2509.17246","title":"SPFSplatV2: Efficient Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views","created":"2025-09-21","cited_by_count":7,"area":null},{"id":"2509.24209","title":"Forge4D: Feed-Forward 4D Human Reconstruction and Interpolation from Uncalibrated Sparse-view Videos","created":"2025-09-29","cited_by_count":7,"area":null},{"id":"2603.04179","title":"NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction","created":"2026-03-04","cited_by_count":7,"area":null},{"id":"2603.25053","title":"GaussFusion: Improving 3D Reconstruction in the Wild with A Geometry-Informed Video Generator","created":"2026-03-26","cited_by_count":7,"area":null},{"id":"2604.22482","title":"Holo360D: A Large-Scale Real-World Dataset with Continuous Trajectories for Advancing Panoramic 3D Reconstruction and Beyond","created":"2026-04-24","cited_by_count":7,"area":null},{"id":"2505.15235","title":"X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography","created":"2025-05-21","cited_by_count":6,"area":null},{"id":"2507.16535","title":"EarthCrafter: Scalable 3D Earth Generation via Dual-Sparse Latent Diffusion","created":"2025-07-22","cited_by_count":6,"area":"diffusion"},{"id":"2510.11473","title":"VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment","created":"2025-10-13","cited_by_count":6,"area":null},{"id":"2511.21945","title":"GENA3D: Generative Amodal 3D Modeling by Bridging 2D Priors and 3D Coherence","created":"2025-11-26","cited_by_count":6,"area":null},{"id":"2511.22429","title":"Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation","created":"2025-11-27","cited_by_count":6,"area":"distill"},{"id":"2511.22686","title":"Emergent Extreme-View Geometry in 3D Foundation Models","created":"2025-11-27","cited_by_count":6,"area":null},{"id":"2601.14161","title":"One-Shot Refiner: Boosting Feed-forward Novel View Synthesis via One-Step Diffusion","created":"2026-01-20","cited_by_count":6,"area":null},{"id":"2604.07279","title":"Mem3R: Streaming 3D Reconstruction with Hybrid Memory via Test-Time Training","created":"2026-04-08","cited_by_count":6,"area":null},{"id":"2506.23863","title":"Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction","created":"2025-06-30","cited_by_count":5,"area":null},{"id":"2510.18714","title":"PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-Forward Planar Splatting","created":"2025-10-21","cited_by_count":5,"area":null},{"id":"2602.24290","title":"UFO-4D: Unposed Feedforward 4D Reconstruction from Two Images","created":"2026-02-27","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":"2605.22819","title":"Cambrian-P: Pose-Grounded Video Understanding","created":"2026-05-21","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":"2507.22342","title":"UFV-Splatter: Pose-Free Feed-Forward 3D Gaussian Splatting Adapted to Unfavorable Views","created":"2025-07-30","cited_by_count":4,"area":null},{"id":"2509.24385","title":"Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy","created":"2025-09-29","cited_by_count":4,"area":"lr"},{"id":"2510.15072","title":"SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images","created":"2025-10-16","cited_by_count":4,"area":null},{"id":"2512.05131","title":"AREA3D: Active Reconstruction Agent with Unified Feed-Forward 3D Perception and Vision-Language Guidance","created":"2025-11-28","cited_by_count":4,"area":null},{"id":"2512.08930","title":"Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment","created":"2025-12-09","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":"2512.19402","title":"Real2Edit2Real: Generating Robotic Demonstrations via a 3D Control Interface","created":"2025-12-22","cited_by_count":4,"area":null},{"id":"2602.04439","title":"TrajVG: 3D Trajectory-Coupled Visual Geometry Learning","created":"2026-02-04","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":"2602.22571","title":"GIFSplat: Generative Prior-Guided Iterative Feed-Forward 3D Gaussian Splatting from Sparse Views","created":"2026-02-26","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":"2604.00548","title":"Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2604.08532","title":"Self-Improving 4D Perception via Self-Distillation","created":"2026-04-09","cited_by_count":4,"area":"distill"},{"id":"2604.22714","title":"Long-tail Internet photo reconstruction","created":"2026-04-24","cited_by_count":4,"area":null},{"id":"2505.13440","title":"Recollection from Pensieve: Novel View Synthesis via Learning from Uncalibrated Videos","created":"2025-05-19","cited_by_count":3,"area":null},{"id":"2510.14349","title":"Vision-Centric Activation and Coordination for Multimodal Large Language Models","created":"2025-10-16","cited_by_count":3,"area":"mllm"},{"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":"2512.17547","title":"G3Splat: Geometrically Consistent Generalizable Gaussian Splatting","created":"2025-12-19","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":"2602.00865","title":"Distill3R: A Pipeline for Democratizing 3D Foundation Models on Commodity Hardware","created":"2026-01-31","cited_by_count":3,"area":null}],"next_cursor":"100"}