{"total":71,"rows":[{"id":"2506.01946","title":"3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding","created":"2025-06-02","cited_by_count":70,"area":"lr"},{"id":"2504.03886","title":"WildGS-SLAM: Monocular Gaussian Splatting SLAM in Dynamic Environments","created":"2025-04-04","cited_by_count":50,"area":null},{"id":"2508.02095","title":"VLM4D: Towards Spatiotemporal Awareness in Vision Language Models","created":"2025-08-04","cited_by_count":46,"area":"lr"},{"id":"2411.11921","title":"DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes","created":"2024-11-18","cited_by_count":45,"area":"wm"},{"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":"2412.06016","title":"Track4Gen: Teaching Video Diffusion Models to Track Points Improves Video Generation","created":"2024-12-08","cited_by_count":44,"area":"diffusion"},{"id":"2410.14462","title":"LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes","created":"2024-10-18","cited_by_count":37,"area":null},{"id":"2503.14405","title":"DUNE: Distilling a Universal Encoder from Heterogeneous 2D and 3D Teachers","created":"2025-03-18","cited_by_count":32,"area":"distill"},{"id":"2410.08208","title":"SPA: 3D Spatial-Awareness Enables Effective Embodied Representation","created":"2024-10-10","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":"2512.04021","title":"C3G: Learning Compact 3D Representations with 2K Gaussians","created":"2025-12-03","cited_by_count":21,"area":null},{"id":"2411.17385","title":"DepthCues: Evaluating Monocular Depth Perception in Large Vision Models","created":"2024-11-26","cited_by_count":19,"area":null},{"id":"2512.03453","title":"GeoVideo: Introducing Geometric Regularization into Video Generation Model","created":"2025-12-03","cited_by_count":19,"area":"diffusion"},{"id":"2408.16325","title":"P2P-Bridge: Diffusion Bridges for 3D Point Cloud Denoising","created":"2024-08-29","cited_by_count":18,"area":null},{"id":"2412.07746","title":"LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models","created":"2024-12-10","cited_by_count":18,"area":null},{"id":"2412.17635","title":"LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding","created":"2024-12-23","cited_by_count":17,"area":null},{"id":"2411.19458","title":"Multiview Equivariance Improves 3D Correspondence Understanding with Minimal Feature Finetuning","created":"2024-11-29","cited_by_count":14,"area":null},{"id":"2507.06230","title":"Feed-Forward SceneDINO for Unsupervised Semantic Scene Completion","created":"2025-07-08","cited_by_count":13,"area":null},{"id":"2506.09229","title":"Cross-Frame Representation Alignment for Fine-Tuning Video Diffusion Models","created":"2025-06-10","cited_by_count":12,"area":"diffusion"},{"id":"2603.28480","title":"INSID3: Training-Free In-Context Segmentation with DINOv3","created":"2026-03-30","cited_by_count":12,"area":null},{"id":"2411.19492","title":"Diorama: Unleashing Zero-shot Single-view 3D Indoor Scene Modeling","created":"2024-11-29","cited_by_count":11,"area":null},{"id":"2504.08125","title":"Gen3DEval: Using vLLMs for Automatic Evaluation of Generated 3D Objects","created":"2025-04-10","cited_by_count":11,"area":null},{"id":"2508.05254","title":"CF3: Compact and Fast 3D Feature Fields","created":"2025-08-07","cited_by_count":11,"area":null},{"id":"2603.19076","title":"DROID-SLAM in the Wild","created":"2026-03-19","cited_by_count":10,"area":null},{"id":"2501.01409","title":"JOG3R: Towards 3D-Consistent Video Generators","created":"2025-01-02","cited_by_count":9,"area":null},{"id":"2512.03210","title":"Flux4D: Flow-based Unsupervised 4D Reconstruction","created":"2025-12-02","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":"2410.13924","title":"ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding","created":"2024-10-17","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":"2508.00746","title":"GECO: Geometrically Consistent Embedding with Lightspeed Inference","created":"2025-08-01","cited_by_count":6,"area":null},{"id":"2503.15470","title":"EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining","created":"2025-03-19","cited_by_count":5,"area":null},{"id":"2505.04835","title":"Are Synthetic Corruptions A Reliable Proxy For Real-World Corruptions?","created":"2025-05-07","cited_by_count":5,"area":null},{"id":"2506.09883","title":"3D-Aware Vision-Language Models Fine-Tuning with Geometric Distillation","created":"2025-06-11","cited_by_count":5,"area":"mllm"},{"id":"2503.08417","title":"AnyMoLe: Any Character Motion In-betweening Leveraging Video Diffusion Models","created":"2025-03-11","cited_by_count":4,"area":"diffusion"},{"id":"2505.08124","title":"SLAG: Scalable Language-Augmented Gaussian Splatting","created":"2025-05-12","cited_by_count":4,"area":null},{"id":"2507.00392","title":"Learning Dense Feature Matching via Lifting Single 2D Image to 3D Space","created":"2025-07-01","cited_by_count":4,"area":null},{"id":"2511.18991","title":"View-Consistent Diffusion Representations for 3D-Consistent Video Generation","created":"2025-11-24","cited_by_count":4,"area":"diffusion"},{"id":"2503.16413","title":"M3: 3D-Spatial MultiModal Memory","created":"2025-03-20","cited_by_count":3,"area":null},{"id":"2511.19235","title":"IDSplat: Instance-Decomposed 3D Gaussian Splatting for Driving Scenes","created":"2025-11-24","cited_by_count":3,"area":null},{"id":"2512.20907","title":"PanoGrounder: Bridging 2D and 3D with Panoramic Scene Representations for VLM-based 3D Visual Grounding","created":"2025-12-24","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":"2604.22339","title":"Flow4DGS-SLAM: Optical Flow-Guided 4D Gaussian Splatting SLAM","created":"2026-04-24","cited_by_count":3,"area":null},{"id":"2503.12535","title":"SPC-GS: Gaussian Splatting with Semantic-Prompt Consistency for Indoor Open-World Free-view Synthesis from Sparse Inputs","created":"2025-03-16","cited_by_count":2,"area":null},{"id":"2503.13429","title":"Interpretable 3D Neural Object Volumes for Robust Conceptual Reasoning","created":"2025-03-17","cited_by_count":2,"area":null},{"id":"2508.02172","title":"GaussianCross: Cross-modal Self-supervised 3D Representation Learning via Gaussian Splatting","created":"2025-08-04","cited_by_count":2,"area":null},{"id":"2508.13601","title":"Unleashing Semantic and Geometric Priors for 3D Scene Completion","created":"2025-08-19","cited_by_count":2,"area":null},{"id":"2508.21529","title":"Maybe you don't need a U-Net: convolutional feature upsampling for materials micrograph segmentation","created":"2025-08-29","cited_by_count":2,"area":null},{"id":"2512.15708","title":"Multi-View Foundation Models","created":"2025-12-17","cited_by_count":2,"area":null},{"id":"2601.13886","title":"Revisiting Multi-Task Visual Representation Learning","created":"2026-01-20","cited_by_count":2,"area":"mllm"},{"id":"2605.10485","title":"VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models","created":"2026-05-11","cited_by_count":2,"area":"lr"},{"id":"2510.07856","title":"XYZCylinder: Towards Compatible Feed-Forward 3D Gaussian Splatting for Driving Scenes via Unified Cylinder Lifting Method","created":"2025-10-09","cited_by_count":1,"area":null},{"id":"2511.06632","title":"DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splatting","created":"2025-11-10","cited_by_count":1,"area":null},{"id":"2602.06032","title":"Splat and Distill: Augmenting Teachers with Feed-Forward 3D Reconstruction For 3D-Aware Distillation","created":"2026-02-05","cited_by_count":1,"area":"distill"},{"id":"2604.21631","title":"DualSplat: Robust 3D Gaussian Splatting via Pseudo-Mask Bootstrapping from Reconstruction Failures","created":"2026-04-23","cited_by_count":1,"area":null},{"id":"2606.17564","title":"Geometric Consistency Protocol for Foundation Model Features in Multi-View Satellite Imagery","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2503.08344","title":"DIV-FF: Dynamic Image-Video Feature Fields For Environment Understanding in Egocentric Videos","created":"2025-03-11","cited_by_count":0,"area":null},{"id":"2503.19947","title":"Vanishing Depth: Training Generalized Depth Adapters with Sinusoidal Depth Preprocessing for Pretrained RGB Encoders","created":"2025-03-25","cited_by_count":0,"area":null},{"id":"2505.05091","title":"DispBench: Benchmarking Disparity Estimation to Synthetic Corruptions","created":"2025-05-08","cited_by_count":0,"area":null},{"id":"2511.02830","title":"Densemarks: Learning Canonical Embeddings for Human Heads Images via Point Tracks","created":"2025-11-04","cited_by_count":0,"area":null},{"id":"2511.21265","title":"Unlocking Zero-shot Potential of Semi-dense Image Matching via Gaussian Splatting","created":"2025-11-26","cited_by_count":0,"area":null},{"id":"2602.12524","title":"LiDAR-Anchored Collaborative Distillation for Robust 2D Representations","created":"2026-02-13","cited_by_count":0,"area":null},{"id":"2603.06459","title":"Do Foundation Models Know Geometry? Probing Frozen Features for Continuous Physical Measurement","created":"2026-03-06","cited_by_count":0,"area":"mllm"},{"id":"2603.21936","title":"Cross-Instance Gaussian Splatting Registration via Geometry-Aware Feature-Guided Alignment","created":"2026-03-23","cited_by_count":0,"area":null},{"id":"2603.29185","title":"Hierarchical Visual Relocalization with Nearest View Synthesis from Feature Gaussian Splatting","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2604.11992","title":"ReefMapGS: Enabling Large-Scale Underwater Reconstruction by Closing the Loop Between Multimodal SLAM and Gaussian Splatting","created":"2026-04-13","cited_by_count":0,"area":null},{"id":"2606.03314","title":"TASE: Truncation-Aware Semantic Embeddings for 3D Scene Understanding and Editing","created":"2026-06-02","cited_by_count":0,"area":null},{"id":"2607.01708","title":"Consistent Scene Understanding in 3D Gaussian Splatting via Multi-Cue Mask Refinement","created":"2026-07-02","cited_by_count":0,"area":null},{"id":"2608.23850","title":"DDMS: Discriminative Distillation of Multi-view Foundational Features into Single-view Models","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2608.30858","title":"GAFT: Geo-Anchored Fine-Tuning for Hazard Identification from Rare Failures","created":"2026-08-31","cited_by_count":0,"area":null},{"id":"2609.14634","title":"SCOUT-SLAM: Structurally-Coupled Dual Uncertainty-Aware 3DGS SLAM in the Wild","created":"2026-09-13","cited_by_count":0,"area":null},{"id":"2610.16988","title":"Self-Supervised Learning of Semantically Consistent Visual Features via a Simple 3D Prior","created":"2026-10-12","cited_by_count":0,"area":"diffusion"}],"next_cursor":null}