{"total":189,"rows":[{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539,"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":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314,"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":"2503.14489","title":"Stable Virtual Camera: Generative View Synthesis with Diffusion Models","created":"2025-03-18","cited_by_count":182,"area":"diffusion"},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2505.23884","title":"Test-Time Training Done Right","created":"2025-05-29","cited_by_count":130,"area":"diffusion"},{"id":"2411.04924","title":"MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views","created":"2024-11-07","cited_by_count":116,"area":null},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105,"area":null},{"id":"2412.12091","title":"Wonderland: Navigating 3D Scenes from a Single Image","created":"2024-12-16","cited_by_count":99,"area":"diffusion"},{"id":"2412.07760","title":"SynCamMaster: Synchronizing Multi-Camera Video Generation from Diverse Viewpoints","created":"2024-12-10","cited_by_count":93,"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":"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":"2412.13188","title":"StreetCrafter: Street View Synthesis with Controllable Video Diffusion Models","created":"2024-12-17","cited_by_count":49,"area":"wm"},{"id":"2507.16290","title":"Dens3R: A Foundation Model for 3D Geometry Prediction","created":"2025-07-22","cited_by_count":46,"area":null},{"id":"2503.16979","title":"Instant Gaussian Stream: Fast and Generalizable Streaming of Dynamic Scene Reconstruction via Gaussian Splatting","created":"2025-03-21","cited_by_count":36,"area":null},{"id":"2506.09278","title":"UFM: A Simple Path towards Unified Dense Correspondence with Flow","created":"2025-06-10","cited_by_count":36,"area":null},{"id":"2510.18313","title":"OmniNWM: Omniscient Driving Navigation World Models","created":"2025-10-21","cited_by_count":33,"area":"wm"},{"id":"2601.04090","title":"Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction","created":"2026-01-07","cited_by_count":31,"area":"diffusion"},{"id":"2412.09606","title":"Feat2GS: Probing Visual Foundation Models with Gaussian Splatting","created":"2024-12-12","cited_by_count":27,"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":"2505.21925","title":"RenderFormer: Transformer-based Neural Rendering of Triangle Meshes with Global Illumination","created":"2025-05-28","cited_by_count":23,"area":null},{"id":"2412.14166","title":"MegaSynth: Scaling Up 3D Scene Reconstruction with Synthesized Data","created":"2024-12-18","cited_by_count":21,"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":"2510.19400","title":"Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes","created":"2025-10-22","cited_by_count":20,"area":"lr"},{"id":"2510.20385","title":"Positional Encoding Field","created":"2025-10-23","cited_by_count":20,"area":"diffusion"},{"id":"2512.10685","title":"Sharp Monocular View Synthesis in Less Than a Second","created":"2025-12-11","cited_by_count":20,"area":null},{"id":"2503.13272","title":"Generative Gaussian Splatting: Generating 3D Scenes with Video Diffusion Priors","created":"2025-03-17","cited_by_count":19,"area":"diffusion"},{"id":"2507.23277","title":"iLRM: An Iterative Large 3D Reconstruction Model","created":"2025-07-31","cited_by_count":19,"area":null},{"id":"2510.08575","title":"ReSplat: Learning Recurrent Gaussian Splatting","created":"2025-10-09","cited_by_count":15,"area":null},{"id":"2510.13063","title":"True Self-Supervised Novel View Synthesis is Transferable","created":"2025-10-15","cited_by_count":15,"area":null},{"id":"2604.15239","title":"TokenGS: Decoupling 3D Gaussian Prediction from Pixels with Learnable Tokens","created":"2026-04-16","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":"2506.18890","title":"4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time","created":"2025-06-23","cited_by_count":14,"area":null},{"id":"2601.15275","title":"RayRoPE: Projective Ray Positional Encoding for Multi-view Attention","created":"2026-01-21","cited_by_count":14,"area":null},{"id":"2511.11563","title":"LARM: A Large Articulated-Object Reconstruction Model","created":"2025-11-14","cited_by_count":12,"area":null},{"id":"2602.20160","title":"tttLRM: Test-Time Training for Long Context and Autoregressive 3D Reconstruction","created":"2026-02-23","cited_by_count":12,"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":"2511.19827","title":"ReDirector: Creating Any-Length Video Retakes with Rotary Camera Encoding","created":"2025-11-25","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":"2512.25075","title":"SpaceTimePilot: Generative Rendering of Dynamic Scenes Across Space and Time","created":"2025-12-31","cited_by_count":11,"area":"diffusion"},{"id":"2503.07596","title":"Denoising Hamiltonian Network for Physical Reasoning","created":"2025-03-10","cited_by_count":10,"area":null},{"id":"2503.21082","title":"Can Video Diffusion Model Reconstruct 4D Geometry?","created":"2025-03-27","cited_by_count":10,"area":"diffusion"},{"id":"2506.10980","title":"InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model","created":"2025-06-12","cited_by_count":10,"area":null},{"id":"2508.11952","title":"UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding","created":"2025-08-16","cited_by_count":10,"area":null},{"id":"2508.13911","title":"PhysGM: Large Physical Gaussian Model for Feed-Forward 4D Synthesis","created":"2025-08-19","cited_by_count":10,"area":null},{"id":"2602.18882","title":"SceneTok: A Compressed, Diffusable Token Space for 3D Scenes","created":"2026-02-21","cited_by_count":10,"area":null},{"id":"2506.03118","title":"HumanRAM: Feed-forward Human Reconstruction and Animation Model using Transformers","created":"2025-06-03","cited_by_count":9,"area":null},{"id":"2512.14671","title":"ART: Articulated Reconstruction Transformer","created":"2025-12-16","cited_by_count":9,"area":null},{"id":"2602.21341","title":"Scaling View Synthesis Transformers","created":"2026-02-24","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":"2412.13547","title":"Turbo-GS: Accelerating 3D Gaussian Fitting for High-Quality Radiance Fields","created":"2024-12-18","cited_by_count":8,"area":null},{"id":"2509.17985","title":"VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models","created":"2025-09-22","cited_by_count":8,"area":"diffusion"},{"id":"2510.04236","title":"Scaling Sequence-to-Sequence Generative Neural Rendering","created":"2025-10-05","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":"2603.05868","title":"AnyCamVLA: Zero-Shot Camera Adaptation for Viewpoint Robust Vision-Language-Action Models","created":"2026-03-06","cited_by_count":8,"area":"vla"},{"id":"2411.13549","title":"KFC-W: Generating 3D-Consistent Videos from Unposed Internet Photos","created":"2024-11-20","cited_by_count":7,"area":null},{"id":"2508.17811","title":"MeshSplat: Generalizable Sparse-View Surface Reconstruction via Gaussian Splatting","created":"2025-08-25","cited_by_count":7,"area":null},{"id":"2508.19754","title":"FastAvatar: Towards Unified and Fast 3D Avatar Reconstruction with Large Gaussian Reconstruction Transformers","created":"2025-08-27","cited_by_count":7,"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":"2412.02631","title":"Sharp-It: A Multi-view to Multi-view Diffusion Model for 3D Synthesis and Manipulation","created":"2024-12-03","cited_by_count":6,"area":"diffusion"},{"id":"2506.13766","title":"LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D","created":"2025-06-16","cited_by_count":6,"area":null},{"id":"2509.06579","title":"CausNVS: Autoregressive Multi-view Diffusion for Flexible 3D Novel View Synthesis","created":"2025-09-08","cited_by_count":6,"area":"diffusion"},{"id":"2509.25001","title":"LVT: Large-Scale Scene Reconstruction via Local View Transformers","created":"2025-09-29","cited_by_count":6,"area":null},{"id":"2602.06478","title":"Efficient-LVSM: Faster, Cheaper, and Better Large View Synthesis Model via Decoupled Co-Refinement Attention","created":"2026-02-06","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":"2503.14698","title":"Learning Efficient Fuse-and-Refine for Feed-Forward 3D Gaussian Splatting","created":"2025-03-18","cited_by_count":5,"area":null},{"id":"2506.05285","title":"RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion","created":"2025-06-05","cited_by_count":5,"area":null},{"id":"2506.11924","title":"Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation","created":"2025-06-13","cited_by_count":5,"area":null},{"id":"2507.08776","title":"CLiFT: Compressive Light-Field Tokens for Compute-Efficient and Adaptive Neural Rendering","created":"2025-07-11","cited_by_count":5,"area":null},{"id":"2509.23258","title":"OracleGS: Grounding Generative Priors for Sparse-View Gaussian Splatting","created":"2025-09-27","cited_by_count":5,"area":null},{"id":"2510.00978","title":"A Scene is Worth a Thousand Features: Feed-Forward Camera Localization from a Collection of Image Features","created":"2025-10-01","cited_by_count":5,"area":null},{"id":"2601.05116","title":"From Rays to Projections: Better Inputs for Feed-Forward View Synthesis","created":"2026-01-08","cited_by_count":5,"area":null},{"id":"2508.03118","title":"H3R: Hybrid Multi-view Correspondence for Generalizable 3D Reconstruction","created":"2025-08-05","cited_by_count":4,"area":null},{"id":"2509.06950","title":"Scaling Transformer-Based Novel View Synthesis Models with Token Disentanglement and Synthetic Data","created":"2025-09-08","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":"2512.10267","title":"Long-LRM++: Preserving Fine Details in Feed-Forward Wide-Coverage Reconstruction","created":"2025-12-11","cited_by_count":4,"area":null},{"id":"2512.10940","title":"OmniView: An All-Seeing Diffusion Model for 3D and 4D View Synthesis","created":"2025-12-11","cited_by_count":4,"area":"diffusion"},{"id":"2512.20107","title":"UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis","created":"2025-12-23","cited_by_count":4,"area":null},{"id":"2601.10716","title":"WildRayZer: Self-supervised Large View Synthesis in Dynamic Environments","created":"2026-01-15","cited_by_count":4,"area":null},{"id":"2602.20685","title":"RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space","created":"2026-02-24","cited_by_count":4,"area":"wm"},{"id":"2604.08500","title":"FrameCrafter: Novel View Synthesis as Video Completion","created":"2026-04-09","cited_by_count":4,"area":"diffusion"},{"id":"2605.08712","title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","created":"2026-05-09","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":"2512.09923","title":"Splatent: Splatting Diffusion Latents for Novel View Synthesis","created":"2025-12-10","cited_by_count":3,"area":"diffusion"},{"id":"2601.16296","title":"Memory-V2V: Memory-Augmented Video-to-Video Diffusion for Consistent Multi-Turn Editing","created":"2026-01-22","cited_by_count":3,"area":"diffusion"},{"id":"2603.22851","title":"UniQueR: Unified Query-based Feedforward 3D Reconstruction","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2603.22893","title":"SLARM: Streaming and Language-Aligned Reconstruction Model for Dynamic Scenes","created":"2026-03-24","cited_by_count":3,"area":null},{"id":"2604.04707","title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","created":"2026-04-06","cited_by_count":3,"area":"wm"},{"id":"2604.07350","title":"Fast Spatial Memory with Elastic Test-Time Training","created":"2026-04-08","cited_by_count":3,"area":null},{"id":"2604.11331","title":"Any 3D Scene is Worth 1K Tokens: 3D-Grounded Representation for Scene Generation at Scale","created":"2026-04-13","cited_by_count":3,"area":"diffusion"},{"id":"2605.15305","title":"WorldParticle: Unified World Simulation of Lagrangian Particle Dynamics via Transformer","created":"2026-05-14","cited_by_count":3,"area":null},{"id":"2502.05175","title":"Fillerbuster: Unified Generative Scene Completion Model for Casual Captures","created":"2025-02-07","cited_by_count":2,"area":"diffusion"},{"id":"2505.19813","title":"GoLF-NRT: Integrating Global Context and Local Geometry for Few-Shot View Synthesis","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2506.09885","title":"The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge","created":"2025-06-11","cited_by_count":2,"area":null},{"id":"2511.19437","title":"LumiTex: Towards High-Fidelity PBR Texture Generation with Illumination Context","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2512.10947","title":"Towards Efficient and Effective Multi-Camera Encoding for End-to-End Driving","created":"2025-12-11","cited_by_count":2,"area":"driving"},{"id":"2603.01194","title":"RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations","created":"2026-03-01","cited_by_count":2,"area":null}],"next_cursor":"100"}