{"total":73,"rows":[{"id":"2505.20279","title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","created":"2025-05-26","cited_by_count":166,"area":"mllm"},{"id":"2508.02095","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","created":"2025-08-04","cited_by_count":46,"area":"lr"},{"id":"2510.23607","title":"Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations","created":"2025-10-27","cited_by_count":45,"area":null},{"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":"2411.16877","title":"PreF3R: Pose-Free Feed-Forward 3D Gaussian Splatting from Variable-length Image Sequence","created":"2024-11-25","cited_by_count":28,"area":null},{"id":"2510.22706","title":"IGGT: Instance-Grounded Geometry Transformer for Semantic 3D Reconstruction","created":"2025-10-26","cited_by_count":28,"area":null},{"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":"2508.03643","title":"Uni3R: Unified 3D Reconstruction and Semantic Understanding via Generalizable Gaussian Splatting from Unposed Multi-View Images","created":"2025-08-05","cited_by_count":26,"area":null},{"id":"2503.06271","title":"SplatTalk: 3D VQA with Gaussian Splatting","created":"2025-03-08","cited_by_count":24,"area":null},{"id":"2512.04021","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","created":"2025-12-03","cited_by_count":21,"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":"2411.06390","title":"SplatFormer: Point Transformer for Robust 3D Gaussian Splatting","created":"2024-11-10","cited_by_count":16,"area":null},{"id":"2507.02705","title":"SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment","created":"2025-07-03","cited_by_count":16,"area":null},{"id":"2506.09378","title":"UniForward: Unified 3D Scene and Semantic Field Reconstruction via Feed-Forward Gaussian Splatting from Only Sparse-View Images","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2506.09565","title":"SemanticSplat: Feed-Forward 3D Scene Understanding with Language-Aware Gaussian Fields","created":"2025-06-11","cited_by_count":14,"area":null},{"id":"2512.04686","title":"Towards Cross-View Point Correspondence in Vision-Language Models","created":"2025-12-04","cited_by_count":14,"area":"mllm"},{"id":"2503.20776","title":"Feature4X: Bridging Any Monocular Video to 4D Agentic AI with Versatile Gaussian Feature Fields","created":"2025-03-26","cited_by_count":13,"area":null},{"id":"2505.23044","title":"SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images","created":"2025-05-29","cited_by_count":13,"area":null},{"id":"2508.05254","title":"CF3: Compact and Fast 3D Feature Fields","created":"2025-08-07","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":"2503.07507","title":"PE3R: Perception-Efficient 3D Reconstruction","created":"2025-03-10","cited_by_count":9,"area":null},{"id":"2505.02178","title":"Sparfels: Fast Reconstruction from Sparse Unposed Imagery","created":"2025-05-04","cited_by_count":8,"area":null},{"id":"2507.21960","title":"PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction","created":"2025-07-29","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":"2510.24907","title":"Understanding Multi-View Transformers","created":"2025-10-28","cited_by_count":8,"area":null},{"id":"2512.14364","title":"Unified Semantic Transformer for 3D Scene Understanding","created":"2025-12-16","cited_by_count":8,"area":null},{"id":"2504.13159","title":"Digital Twin Generation from Visual Data: A Survey","created":"2025-04-17","cited_by_count":7,"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":"2506.02112","title":"SAB3R: Semantic-Augmented Backbone in 3D Reconstruction","created":"2025-06-02","cited_by_count":6,"area":null},{"id":"2507.02813","title":"LangScene-X: Reconstruct Generalizable 3D Language-Embedded Scenes with TriMap Video Diffusion","created":"2025-07-03","cited_by_count":6,"area":"diffusion"},{"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":"2412.02245","title":"SparseLGS: Sparse View Language Embedded Gaussian Splatting","created":"2024-12-03","cited_by_count":4,"area":null},{"id":"2510.25146","title":"EA3D: Online Open-World 3D Object Extraction from Streaming Videos","created":"2025-10-29","cited_by_count":4,"area":null},{"id":"2511.05449","title":"How Many Tokens Do 3D Point Cloud Transformer Architectures Really Need?","created":"2025-11-07","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":"2601.08831","title":"3AM: 3egment Anything with Geometric Consistency in Videos","created":"2026-01-13","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":"2509.25603","title":"GaussianLens: Localized High-Resolution Reconstruction via On-Demand Gaussian Densification","created":"2025-09-29","cited_by_count":3,"area":null},{"id":"2603.19926","title":"SegVGGT: Joint 3D Reconstruction and Instance Segmentation from Multi-View Images","created":"2026-03-20","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":"2604.09862","title":"FF3R: Feedforward Feature 3D Reconstruction from Unconstrained views","created":"2026-04-10","cited_by_count":3,"area":null},{"id":"2606.08980","title":"EPS3D: End-to-End Feed-Forward 3D Panoptic Segmentation","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2512.25071","title":"Edit3r: Instant 3D Scene Editing from Sparse Unposed Images","created":"2025-12-31","cited_by_count":2,"area":null},{"id":"2605.23287","title":"LangFlash: Feed-forward 3D Language Gaussian Splatting from Sparse Unposed Images","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2605.31595","title":"Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction","created":"2026-05-29","cited_by_count":2,"area":null},{"id":"2607.19228","title":"IGGT4D: Streaming 4D Instance-Grounded Geometry Transformer","created":"2026-07-21","cited_by_count":2,"area":null},{"id":"2511.18386","title":"SegSplat: Feed-forward Gaussian Splatting and Open-Set Semantic Segmentation","created":"2025-11-23","cited_by_count":1,"area":null},{"id":"2603.04254","title":"EmbodiedSplat: Online Feed-Forward Semantic 3DGS for Open-Vocabulary 3D Scene Understanding","created":"2026-03-04","cited_by_count":1,"area":null},{"id":"2603.14150","title":"CIPHER: Culvert Inspection through Pairwise Frame Selection and High-Efficiency Reconstruction","created":"2026-03-14","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":"2606.14307","title":"Pano3D: Unified 3D Reconstruction and Panoptic Segmentation","created":"2026-06-12","cited_by_count":1,"area":null},{"id":"2606.29513","title":"Scenes as Objects, Not Primitives: Instance-Structured 3D Tokenization from Unposed Views","created":"2026-06-28","cited_by_count":1,"area":null},{"id":"2607.01633","title":"Bridging 3D Gaussians and Semantic Occupancy for Comprehensive Open-Vocabulary Scene Understanding from Unposed Images","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2609.22687","title":"PanoSeg3R: Feed-Forward 3D Semantic Segmentation for Panoramic Images with an Automatic Data Curation Pipeline","created":"2026-09-19","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":"2511.00468","title":"HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation","created":"2025-11-01","cited_by_count":0,"area":null},{"id":"2603.14232","title":"S2GS: Streaming Semantic Gaussian Splatting for Online Scene Understanding and Reconstruction","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.14639","title":"Seeing Where to Deploy: Metric RGB-Based Traversability Analysis for Aerial-to-Ground Hidden Space Inspection","created":"2026-03-15","cited_by_count":0,"area":null},{"id":"2603.17519","title":"UniSem: Generalizable Semantic 3D Reconstruction from Sparse Unposed Images","created":"2026-03-18","cited_by_count":0,"area":null},{"id":"2604.09903","title":"PointSplat: Efficient Geometry-Driven Pruning and Transformer Refinement for 3D Gaussian Splatting","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2604.14706","title":"NG-GS: NeRF-Guided 3D Gaussian Splatting Segmentation","created":"2026-04-16","cited_by_count":0,"area":null},{"id":"2605.15186","title":"VGGT-Edit: Feed-forward Native 3D Scene Editing with Residual Field Prediction","created":"2026-05-14","cited_by_count":0,"area":null},{"id":"2607.01290","title":"AnchorSplat: Fast and Structure Consistent Detail Synthesis for Gaussian Splatting","created":"2026-07-01","cited_by_count":0,"area":null},{"id":"2607.08711","title":"LTM: Large-scale Terrain Model for Wildfire-prone Landscapes","created":"2026-07-09","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":"2608.07144","title":"InstanceSplat: Instance-Aware Feed-Forward 3D Gaussian Splatting for Scene Understanding","created":"2026-08-07","cited_by_count":0,"area":null},{"id":"2608.15024","title":"MotionGS-SLAM: Event-Modulated Gaussian Splatting for Motion-Blur Robust SLAM","created":"2026-08-15","cited_by_count":0,"area":null},{"id":"2608.17420","title":"SPVC: Structured and Panoptic Video Fixing for Cross-Dataset Driving Scene Rendering","created":"2026-08-18","cited_by_count":0,"area":null},{"id":"2608.17535","title":"GroupForward: Building Referable 3D Scenes via Instance-Grouped Feed-Forward Gaussian Splatting","created":"2026-08-18","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":"2609.33616","title":"SpatialSpeak: QA-Native Reconstruction with Local and Global Context for Spatial Chain-of-Thought Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.36875","title":"S4VY: Segment Anything in Feed-Forward 4D Visual Geometry","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}