{"total":63,"rows":[{"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":"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":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22,"area":null},{"id":"2507.23277","title":"iLRM: An Iterative Large 3D Reconstruction Model","created":"2025-07-31","cited_by_count":19,"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":"2511.20186","title":"Exo2EgoSyn: Unlocking Foundation Video Generation Models for Exocentric-to-Egocentric Video Synthesis","created":"2025-11-25","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":"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":"2602.18882","title":"SceneTok: A Compressed, Diffusable Token Space for 3D Scenes","created":"2026-02-21","cited_by_count":10,"area":null},{"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":"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":"2512.07806","title":"Multi-view Pyramid Transformer: Look Coarser to See Broader","created":"2025-12-08","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":"2506.05285","title":"RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion","created":"2025-06-05","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":"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":"2512.08930","title":"Selfi: Self Improving Reconstruction Engine via 3D Geometric Feature Alignment","created":"2025-12-09","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":"2604.00548","title":"Reliev3R: Relieving Feed-forward Reconstruction from Multi-View Geometric Annotations","created":"2026-04-01","cited_by_count":4,"area":null},{"id":"2604.07350","title":"Fast Spatial Memory with Elastic Test-Time Training","created":"2026-04-08","cited_by_count":3,"area":null},{"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},{"id":"2603.15433","title":"Real-Time Human Frontal View Synthesis from a Single Image","created":"2026-03-16","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":"2603.23413","title":"I3DM: Implicit 3D-aware Memory Retrieval and Injection for Consistent Video Scene Generation","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2603.27455","title":"From None to All: Self-Supervised 3D Reconstruction via Novel View Synthesis","created":"2026-03-29","cited_by_count":2,"area":null},{"id":"2604.21776","title":"Reshoot-Anything: A Self-Supervised Model for In-the-Wild Video Reshooting","created":"2026-04-23","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":"2606.28321","title":"StructSplat: Generalizable 3D Gaussian Splatting from Uncalibrated Sparse Views","created":"2026-06-26","cited_by_count":2,"area":null},{"id":"2603.25129","title":"AirSplat: Alignment and Rating for Robust Feed-Forward 3D Gaussian Splatting","created":"2026-03-26","cited_by_count":1,"area":null},{"id":"2604.10512","title":"FreeScale: Scaling 3D Scenes via Certainty-Aware Free-View Generation","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2604.10573","title":"Learning 3D Representations for Spatial Intelligence from Unposed Multi-View Images","created":"2026-04-12","cited_by_count":1,"area":null},{"id":"2604.28193","title":"Generalizable Sparse-View 3D Reconstruction from Unconstrained Images","created":"2026-04-30","cited_by_count":1,"area":null},{"id":"2605.10341","title":"PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents","created":"2026-05-11","cited_by_count":1,"area":null},{"id":"2606.02937","title":"BEAST3D: Animal behavioral analysis and neural encoding from multi-view video via Gaussian splatting","created":"2026-06-01","cited_by_count":1,"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":"2512.10840","title":"PoseGAM: Robust Unseen Object Pose Estimation via Geometry-Aware Multi-View Reasoning","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2603.14915","title":"ILV: Iterative Latent Volumes for Fast and Accurate Sparse-View CT Reconstruction","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2603.21166","title":"Training-Free Instance-Aware 3D Scene Reconstruction and Diffusion-Based View Synthesis from Sparse Images","created":"2026-03-22","cited_by_count":0,"area":null},{"id":"2603.25827","title":"Fus3D: Decoding Consolidated 3D Geometry from Feed-forward Geometry Transformer Latents","created":"2026-03-26","cited_by_count":0,"area":null},{"id":"2603.29734","title":"GRVS: a Generalizable and Recurrent Approach to Monocular Dynamic View Synthesis","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.10095","title":"Mining Attribute Subspaces for Efficient Fine-tuning of 3D Foundation Models","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2604.27448","title":"LA-Pose: Latent Action Pretraining Meets Pose Estimation","created":"2026-04-30","cited_by_count":0,"area":null},{"id":"2605.18599","title":"Resolving Representation Ambiguity in Feedforward Novel View Synthesis Transformer via Semantic-Spatial Decoupling","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.18735","title":"PIXLRelight: Controllable Relighting via Intrinsic Conditioning","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2605.31535","title":"RayDer: Scalable Self-Supervised Novel View Synthesis from Real-World Video","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.30045","title":"Walking in the Implicit: Interactive World Exploration via Neural Scene Representation","created":"2026-06-29","cited_by_count":0,"area":null},{"id":"2606.31258","title":"WarpHammer: Densifying Scene Warps with 3D Object Priors for Extreme View Synthesis","created":"2026-06-30","cited_by_count":0,"area":null},{"id":"2607.13481","title":"GPOcc++: Unified Sparse Gaussian Occupancy Prediction with Visual Geometry Priors","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.19765","title":"Extending a Large View Synthesis Model for Multi-view Panoptic Segmentation","created":"2026-07-22","cited_by_count":0,"area":null},{"id":"2607.24852","title":"Hold-Out Self-Validation Cannot Certify Photogrammetric Accuracy: Saturation and Blindness to Coherent Distortion","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2608.16863","title":"SplatGuide: Geometric Priors from 3D Gaussians for Pose-Free Novel View Synthesis","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.18215","title":"LumiTokens: 3D Relighting via Token-Space Lighting Transformation","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.18593","title":"ReX-Shot: Single-Image Rephotography via Geometry- and Camera-Grounded Generation","created":"2026-08-19","cited_by_count":0,"area":null},{"id":"2608.29177","title":"Dynamic-Robust Photometric-Semantic Reconstruction for Open-Vocabulary 3D Scene Understanding","created":"2026-08-29","cited_by_count":0,"area":null},{"id":"2609.04174","title":"Zero-Shot Novel Depth Synthesis Using 3D Foundation Models Scene Representations","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2609.25907","title":"NaCR: Visual Localization via NeRF-aided Camera Ray Regression","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2610.03717","title":"Less Decoder is More Encoder: Geometric Representation Learning from Novel View Synthesis","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.10960","title":"LVSPM: Long Sequence View Synthesis and Pose Estimation Model","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.18446","title":"CoTL: Compact Token Learning for 3D Scene Representation","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}