{"total":38,"rows":[{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319,"area":null},{"id":"2508.10934","title":"ViPE: Video Pose Engine for 3D Geometric Perception","created":"2025-08-12","cited_by_count":170,"area":null},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129,"area":null},{"id":"2507.16869","title":"Controllable Video Generation: A Survey","created":"2025-07-22","cited_by_count":98,"area":null},{"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":"2505.17006","title":"CoMo: Learning Continuous Latent Motion from Internet Videos for Scalable Robot Learning","created":"2025-05-22","cited_by_count":40,"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":"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":"2506.09995","title":"PlayerOne: Egocentric World Simulator","created":"2025-06-11","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":"2506.08334","title":"iTACO: Interactable Digital Twins of Articulated Objects from Casually Captured RGBD Videos","created":"2025-06-10","cited_by_count":19,"area":null},{"id":"2507.21045","title":"Reconstructing 4D Spatial Intelligence: A Survey","created":"2025-07-28","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":"2602.10102","title":"VideoWorld 2: Learning Transferable Knowledge from Real-world Videos","created":"2026-02-10","cited_by_count":12,"area":null},{"id":"2512.19949","title":"How Much 3D Do Video Foundation Models Encode?","created":"2025-12-23","cited_by_count":11,"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":"2509.25191","title":"VGGT-X: When VGGT Meets Dense Novel View Synthesis","created":"2025-09-29","cited_by_count":8,"area":null},{"id":"2603.15330","title":"MeMix: Writing Less, Remembering More for Streaming 3D Reconstruction","created":"2026-03-16","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":"2512.07831","title":"UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation","created":"2025-12-08","cited_by_count":7,"area":null},{"id":"2511.20635","title":"iMontage: Unified, Versatile, Highly Dynamic Many-to-many Image Generation","created":"2025-11-25","cited_by_count":6,"area":null},{"id":"2508.19204","title":"LSD-3D: Large-Scale 3D Driving Scene Generation with Geometry Grounding","created":"2025-08-26","cited_by_count":5,"area":null},{"id":"2510.19255","title":"Advances in 4D Representation: Geometry, Motion, and Interaction","created":"2025-10-22","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":"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":"2601.08175","title":"CogniMap3D: Cognitive 3D Mapping and Rapid Retrieval","created":"2026-01-13","cited_by_count":3,"area":null},{"id":"2602.08961","title":"MotionCrafter: Dense Geometry and Motion Reconstruction with a 4D VAE","created":"2026-02-09","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":"2603.01194","title":"RnG: A Unified Transformer for Complete 3D Modeling from Partial Observations","created":"2026-03-01","cited_by_count":2,"area":null},{"id":"2603.16099","title":"OneWorld: Taming Scene Generation with 3D Unified Representation Autoencoder","created":"2026-03-17","cited_by_count":2,"area":null},{"id":"2606.08402","title":"SceneConductor: 3D Scene Generation from a Single Image with Multi-Agent Orchestration","created":"2026-06-07","cited_by_count":2,"area":null},{"id":"2609.17521","title":"PhysStream: Streaming Physics-Grounded Video Generation with Structured Scene Memory and Fine-Grained Motion Control","created":"2026-09-15","cited_by_count":2,"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":"2603.14765","title":"SSR: A Training-Free Approach for Streaming 3D Reconstruction","created":"2026-03-16","cited_by_count":0,"area":null},{"id":"2605.28132","title":"Which Pretraining Paradigm Better Serves Spatial Intelligence? An Empirical Comparison of Vision-Language and Video Generation Models","created":"2026-05-27","cited_by_count":0,"area":null},{"id":"2608.23549","title":"FixAnything: 3D-Consistent Rendering Refinement via Video Generative Priors","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.19518","title":"AMB3R-SLAM: Kilometer-scale SLAM with Hierarchical Backend","created":"2026-09-17","cited_by_count":0,"area":null},{"id":"2609.35023","title":"Proxy2World: Learning to Generate Worlds From Lightweight Proxies without Seeing Them","created":"2026-09-28","cited_by_count":0,"area":null}],"next_cursor":null}