{"total":116,"rows":[{"id":"2410.13862","title":"DepthSplat: Connecting Gaussian Splatting and Depth","created":"2024-10-17","cited_by_count":286,"area":null},{"id":"2406.09394","title":"WonderWorld: Interactive 3D Scene Generation from a Single Image","created":"2024-06-13","cited_by_count":202,"area":null},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189,"area":null},{"id":"2408.13912","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","created":"2024-08-25","cited_by_count":178,"area":null},{"id":"2407.12781","title":"VD3D: Taming Large Video Diffusion Transformers for 3D Camera Control","created":"2024-07-17","cited_by_count":156,"area":"diffusion"},{"id":"2411.18673","title":"AC3D: Analyzing and Improving 3D Camera Control in Video Diffusion Transformers","created":"2024-11-27","cited_by_count":154,"area":"diffusion"},{"id":"2408.16767","title":"ReconX: Reconstruct Any Scene from Sparse Views with Video Diffusion Model","created":"2024-08-29","cited_by_count":143,"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":"2506.18903","title":"VMem: Consistent Interactive Video Scene Generation with Surfel-Indexed View Memory","created":"2025-06-23","cited_by_count":109,"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":"2412.12091","title":"Wonderland: Navigating 3D Scenes from a Single Image","created":"2024-12-16","cited_by_count":99,"area":"diffusion"},{"id":"2503.17316","title":"Pow3R: Empowering Unconstrained 3D Reconstruction with Camera and Scene Priors","created":"2025-03-21","cited_by_count":72,"area":null},{"id":"2504.07961","title":"Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction","created":"2025-04-10","cited_by_count":67,"area":"diffusion"},{"id":"2503.14445","title":"Bolt3D: Generating 3D Scenes in Seconds","created":"2025-03-18","cited_by_count":59,"area":"diffusion"},{"id":"2501.00602","title":"STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes","created":"2024-12-31","cited_by_count":55,"area":null},{"id":"2412.13193","title":"GaussTR: Foundation Model-Aligned Gaussian Transformer for Self-Supervised 3D Spatial Understanding","created":"2024-12-17","cited_by_count":46,"area":null},{"id":"2604.13036","title":"Lyra 2.0: Explorable Generative 3D Worlds","created":"2026-04-14","cited_by_count":44,"area":null},{"id":"2503.21219","title":"GenFusion: Closing the Loop between Reconstruction and Generation via Videos","created":"2025-03-27","cited_by_count":41,"area":null},{"id":"2509.19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation","created":"2025-09-23","cited_by_count":41,"area":"diffusion"},{"id":"2503.13265","title":"FlexWorld: Progressively Expanding 3D Scenes for Flexiable-View Synthesis","created":"2025-03-17","cited_by_count":37,"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":"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":"2411.14384","title":"Baking Gaussian Splatting into Diffusion Denoiser for Fast and Scalable Single-stage Image-to-3D Generation and Reconstruction","created":"2024-11-21","cited_by_count":32,"area":"diffusion"},{"id":"2411.16157","title":"MVGenMaster: Scaling Multi-View Generation from Any Image via 3D Priors Enhanced Diffusion Model","created":"2024-11-25","cited_by_count":32,"area":"diffusion"},{"id":"2412.06273","title":"Omni-Scene: Omni-Gaussian Representation for Ego-Centric Sparse-View Scene Reconstruction","created":"2024-12-09","cited_by_count":32,"area":null},{"id":"2412.09043","title":"DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving","created":"2024-12-12","cited_by_count":29,"area":"wm"},{"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":"2503.22677","title":"DSO: Aligning 3D Generators with Simulation Feedback for Physical Soundness","created":"2025-03-28","cited_by_count":25,"area":null},{"id":"2412.06250","title":"Splatter-360: Generalizable 360$^{\\circ}$ Gaussian Splatting for Wide-baseline Panoramic Images","created":"2024-12-09","cited_by_count":24,"area":null},{"id":"2412.12096","title":"PanSplat: 4K Panorama Synthesis with Feed-Forward Gaussian Splatting","created":"2024-12-16","cited_by_count":24,"area":null},{"id":"2503.20168","title":"EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis","created":"2025-03-26","cited_by_count":21,"area":null},{"id":"2512.10685","title":"Sharp Monocular View Synthesis in Less Than a Second","created":"2025-12-11","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":"2408.15235","title":"Learning-based Multi-View Stereo: A Survey","created":"2024-08-27","cited_by_count":18,"area":null},{"id":"2412.06234","title":"Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D Reconstruction","created":"2024-12-09","cited_by_count":18,"area":null},{"id":"2512.04939","title":"LiteVGGT: Boosting Vanilla VGGT via Geometry-aware Cached Token Merging","created":"2025-12-04","cited_by_count":17,"area":"inference"},{"id":"2411.07765","title":"Novel View Synthesis with Pixel-Space Diffusion Models","created":"2024-11-12","cited_by_count":16,"area":"diffusion"},{"id":"2505.15185","title":"MonoSplat: Generalizable 3D Gaussian Splatting from Monocular Depth Foundation Models","created":"2025-05-21","cited_by_count":16,"area":null},{"id":"2411.12788","title":"Efficient Scene Modeling via Structure-Aware and Region-Prioritized 3D Gaussians","created":"2024-11-19","cited_by_count":15,"area":null},{"id":"2412.16932","title":"GSemSplat: Generalizable Semantic 3D Gaussian Splatting from Uncalibrated Image Pairs","created":"2024-12-22","cited_by_count":15,"area":null},{"id":"2510.08575","title":"ReSplat: Learning Recurrent Gaussian Splatting","created":"2025-10-09","cited_by_count":15,"area":null},{"id":"2503.15855","title":"VideoRFSplat: Direct Scene-Level Text-to-3D Gaussian Splatting Generation with Flexible Pose and Multi-View Joint Modeling","created":"2025-03-20","cited_by_count":14,"area":null},{"id":"2504.02764","title":"Scene Splatter: Momentum 3D Scene Generation from Single Image with Video Diffusion Model","created":"2025-04-03","cited_by_count":13,"area":"diffusion"},{"id":"2507.06230","title":"Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion","created":"2025-07-08","cited_by_count":13,"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":"2602.19766","title":"One2Scene: Geometric Consistent Explorable 3D Scene Generation from a Single Image","created":"2026-02-23","cited_by_count":11,"area":null},{"id":"2506.21117","title":"CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization","created":"2025-06-26","cited_by_count":10,"area":null},{"id":"2412.00623","title":"A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision","created":"2024-12-01","cited_by_count":9,"area":"diffusion"},{"id":"2503.09733","title":"I2V3D: Controllable image-to-video generation with 3D guidance","created":"2025-03-12","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":"2502.09080","title":"BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization","created":"2025-02-13","cited_by_count":8,"area":null},{"id":"2504.18424","title":"LaRI: Layered Ray Intersections for Single-view 3D Geometric Reasoning","created":"2025-04-25","cited_by_count":8,"area":null},{"id":"2412.12906","title":"CATSplat: Context-Aware Transformer with Spatial Guidance for Generalizable 3D Gaussian Splatting from A Single-View Image","created":"2024-12-17","cited_by_count":7,"area":null},{"id":"2506.09479","title":"TinySplat: Feedforward Approach for Generating Compact 3D Scene Representation","created":"2025-06-11","cited_by_count":7,"area":null},{"id":"2504.10001","title":"GaussVideoDreamer: 3D Scene Generation with Video Diffusion and Inconsistency-Aware Gaussian Splatting","created":"2025-04-14","cited_by_count":6,"area":"diffusion"},{"id":"2508.01464","title":"Can3Tok: Canonical 3D Tokenization and Latent Modeling of Scene-Level 3D Gaussians","created":"2025-08-02","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":"2411.12309","title":"DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes","created":"2024-11-19","cited_by_count":5,"area":null},{"id":"2512.05060","title":"4DLangVGGT: 4D Language-Visual Geometry Grounded Transformer","created":"2025-12-04","cited_by_count":5,"area":null},{"id":"2603.26661","title":"GaussianGPT: Towards Autoregressive 3D Gaussian Scene Generation","created":"2026-03-27","cited_by_count":5,"area":"diffusion"},{"id":"2606.05102","title":"ZipSplat: Fewer Gaussians, Better Splats","created":"2026-06-03","cited_by_count":5,"area":null},{"id":"2503.12553","title":"Niagara: Normal-Integrated Geometric Affine Field for Scene Reconstruction from a Single View","created":"2025-03-16","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":"2512.20107","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":"2501.06714","title":"F3D-Gaus: Feed-forward 3D-aware Generation on ImageNet with Cycle-Aggregative Gaussian Splatting","created":"2025-01-12","cited_by_count":3,"area":null},{"id":"2503.15742","title":"Uncertainty-Aware Diffusion Guided Refinement of 3D Scenes","created":"2025-03-19","cited_by_count":3,"area":null},{"id":"2507.21311","title":"VoluMe -- Authentic 3D Video Calls from Live Gaussian Splat Prediction","created":"2025-07-28","cited_by_count":3,"area":null},{"id":"2509.25603","title":"GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification","created":"2025-09-29","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":"2512.17547","title":"G3Splat: Geometrically Consistent Generalizable Gaussian Splatting","created":"2025-12-19","cited_by_count":3,"area":null},{"id":"2602.20943","title":"UFO: Unifying Feed-Forward and Optimization-based Methods for Large Driving Scene Modeling","created":"2026-02-24","cited_by_count":3,"area":"driving"},{"id":"2503.08485","title":"Test-Time 3D Occupancy Prediction","created":"2025-03-11","cited_by_count":2,"area":null},{"id":"2508.21542","title":"Complete Gaussian Splats from a Single Image with Denoising Diffusion Models","created":"2025-08-29","cited_by_count":2,"area":"diffusion"},{"id":"2601.03362","title":"Guardians of the Hair: Rescuing Soft Boundaries in Depth, Stereo, and Novel Views","created":"2026-01-06","cited_by_count":2,"area":null},{"id":"2603.05908","title":"Pano3DComposer: Feed-Forward Compositional 3D Scene Generation from Single Panoramic Image","created":"2026-03-06","cited_by_count":2,"area":null},{"id":"2605.29891","title":"DVSM: Decoder-only View Synthesis Model Done Right","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2606.07514","title":"UniSHARP: Universal Sharp Monocular View Synthesis","created":"2026-06-05","cited_by_count":2,"area":null},{"id":"2411.01048","title":"MultiDepth: Multi-Sample Priors for Refining Monocular Metric Depth Estimations in Indoor Scenes","created":"2024-11-01","cited_by_count":1,"area":null},{"id":"2502.04318","title":"sshELF: Single-Shot Hierarchical Extrapolation of Latent Features for 3D Reconstruction from Sparse-Views","created":"2025-02-06","cited_by_count":1,"area":null},{"id":"2505.05848","title":"RefRef: A Dataset and Benchmark for Reconstructing Refractive and Reflective Objects","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2505.22978","title":"Pose-free 3D Gaussian splatting via shape-ray estimation","created":"2025-05-29","cited_by_count":1,"area":null},{"id":"2509.23555","title":"From Fields to Splats: A Cross-Domain Survey of Real-Time Neural Scene Representations","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2509.24423","title":"Rethinking Unsupervised Cross-modal Flow Estimation: Learning from Decoupled Optimization and Consistency Constraint","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2510.18101","title":"From Volume Rendering to 3D Gaussian Splatting: Theory and Applications","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2512.09164","title":"WonderZoom: Multi-Scale 3D World Generation","created":"2025-12-09","cited_by_count":1,"area":null},{"id":"2512.18655","title":"SplatBright: Generalizable Low-Light Scene Reconstruction from Sparse Views via Physically-Guided Gaussian Enhancement","created":"2025-12-21","cited_by_count":1,"area":null},{"id":"2601.00678","title":"Pixel-to-4D: Camera-Controlled Image-to-Video Generation with Dynamic 3D Gaussians","created":"2026-01-02","cited_by_count":1,"area":null},{"id":"2604.20155","title":"GSCompleter: A Distillation-Free Plugin for Metric-Aware 3D Gaussian Splatting Completion in Seconds","created":"2026-04-22","cited_by_count":1,"area":null},{"id":"2605.13018","title":"OCH3R: Object-Centric Holistic 3D Reconstruction","created":"2026-05-13","cited_by_count":1,"area":null},{"id":"2606.25430","title":"PRISM: Feed-Forward Single-Image 3D Reconstruction via Geometric Warp-Residual Modeling","created":"2026-06-24","cited_by_count":1,"area":"diffusion"},{"id":"2609.03931","title":"Sparse auto-regressive modeling for scene generation from multi-view images","created":"2026-09-03","cited_by_count":1,"area":null},{"id":"2503.00726","title":"Enhancing Monocular 3D Scene Completion with Diffusion Model","created":"2025-03-02","cited_by_count":0,"area":"diffusion"},{"id":"2506.03713","title":"Pl\\\"uckeRF: A Line-based 3D Representation for Few-view Reconstruction","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2507.00916","title":"Masks make discriminative models great again!","created":"2025-07-01","cited_by_count":0,"area":null},{"id":"2508.10688","title":"Novel View Synthesis using DDIM Inversion","created":"2025-08-14","cited_by_count":0,"area":"diffusion"},{"id":"2509.13652","title":"Gaussian Alignment for Relative Camera Pose Estimation via Single-View Reconstruction","created":"2025-09-17","cited_by_count":0,"area":null},{"id":"2511.03970","title":"Room Envelopes: A Synthetic Dataset for Indoor Layout Reconstruction from Images","created":"2025-11-06","cited_by_count":0,"area":null},{"id":"2603.23488","title":"One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation","created":"2026-03-24","cited_by_count":0,"area":null}],"next_cursor":"100"}