{"list":"other","total":218,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"2312.00752","title":"Mamba: Linear-Time Sequence Modeling with Selective State Spaces","created":"2023-12-01","cited_by_count":4718},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"2307.04725","title":"AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning","created":"2023-07-10","cited_by_count":1433},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2405.21060","title":"Transformers are SSMs: Generalized Models and Efficient Algorithms Through Structured State Space Duality","created":"2024-05-31","cited_by_count":1336},{"id":"2203.03605","title":"DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection","created":"2022-03-07","cited_by_count":1319},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2111.08897","title":"ARKitScenes: A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data","created":"2021-11-17","cited_by_count":454},{"id":"2410.03825","title":"MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motion","created":"2024-10-04","cited_by_count":442},{"id":"2405.10314","title":"CAT3D: Create Anything in 3D with Multi-View Diffusion Models","created":"2024-05-16","cited_by_count":432},{"id":"2409.02048","title":"ViewCrafter: Taming Video Diffusion Models for High-fidelity Novel View Synthesis","created":"2024-09-03","cited_by_count":403},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"2509.13414","title":"MapAnything: Universal Feed-Forward Metric 3D Reconstruction","created":"2025-09-16","cited_by_count":314},{"id":"2408.16061","title":"3D Reconstruction with Spatial Memory","created":"2024-08-28","cited_by_count":277},{"id":"2410.24207","title":"No Pose, No Problem: Surprisingly Simple 3D Gaussian Splats from Sparse Unposed Images","created":"2024-10-31","cited_by_count":248},{"id":"2505.23716","title":"AnySplat: Feed-forward 3D Gaussian Splatting from Unconstrained Views","created":"2025-05-29","cited_by_count":243},{"id":"2403.02151","title":"TripoSR: Fast 3D Object Reconstruction from a Single Image","created":"2024-03-04","cited_by_count":232},{"id":"2505.23747","title":"Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence","created":"2025-05-29","cited_by_count":217},{"id":"2408.13912","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","created":"2024-08-25","cited_by_count":178},{"id":"2405.14793","title":"SEA-RAFT: Simple, Efficient, Accurate RAFT for Optical Flow","created":"2024-05-23","cited_by_count":174},{"id":"2505.20279","title":"VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction","created":"2025-05-26","cited_by_count":166},{"id":"2507.11539","title":"Streaming 4D Visual Geometry Transformer","created":"2025-07-15","cited_by_count":161},{"id":"2412.06974","title":"MV-DUSt3R+: Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds","created":"2024-12-09","cited_by_count":141},{"id":"2404.12385","title":"MeshLRM: Large Reconstruction Model for High-Quality Meshes","created":"2024-04-18","cited_by_count":139},{"id":"2505.12549","title":"VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold","created":"2025-05-18","cited_by_count":136},{"id":"2506.05284","title":"Video World Models with Long-term Spatial Memory","created":"2025-06-05","cited_by_count":136},{"id":"2509.26645","title":"TTT3R: 3D Reconstruction as Test-Time Training","created":"2025-09-30","cited_by_count":129},{"id":"2505.24625","title":"Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors","created":"2025-05-30","cited_by_count":120},{"id":"2406.04343","title":"Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image","created":"2024-06-06","cited_by_count":116},{"id":"2410.12781","title":"Long-LRM: Long-sequence Large Reconstruction Model for Wide-coverage Gaussian Splats","created":"2024-10-16","cited_by_count":114},{"id":"2507.10496","title":"Cameras as Relative Positional Encoding","created":"2025-07-14","cited_by_count":105},{"id":"2506.04225","title":"Voyager: Long-Range and World-Consistent Video Diffusion for Explorable 3D Scene Generation","created":"2025-06-04","cited_by_count":101},{"id":"2509.02560","title":"FastVGGT: Training-Free Acceleration of Visual Geometry Transformer","created":"2025-09-02","cited_by_count":98},{"id":"2507.07982","title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","created":"2025-07-10","cited_by_count":96},{"id":"2504.11451","title":"PARTFIELD: Learning 3D Feature Fields for Part Segmentation and Beyond","created":"2025-04-15","cited_by_count":95},{"id":"2503.24391","title":"Easi3R: Estimating Disentangled Motion from DUSt3R Without Training","created":"2025-03-31","cited_by_count":91},{"id":"2507.02863","title":"Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory","created":"2025-07-03","cited_by_count":87},{"id":"2403.15624","title":"Semantic Gaussians: Open-Vocabulary Scene Understanding with 3D Gaussian Splatting","created":"2024-03-22","cited_by_count":82},{"id":"2508.10893","title":"STream3R: Scalable Sequential 3D Reconstruction with Causal Transformer","created":"2025-08-14","cited_by_count":82},{"id":"2506.01946","title":"3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding","created":"2025-06-02","cited_by_count":70},{"id":"2210.06575","title":"GraspNeRF: Multiview-based 6-DoF Grasp Detection for Transparent and Specular Objects Using Generalizable NeRF","created":"2022-10-12","cited_by_count":67},{"id":"2510.10726","title":"WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting","created":"2025-10-12","cited_by_count":67},{"id":"2410.22128","title":"PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting","created":"2024-10-29","cited_by_count":62},{"id":"2503.14445","title":"Bolt3D: Generating 3D Scenes in Seconds","created":"2025-03-18","cited_by_count":59},{"id":"2410.06245","title":"HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction","created":"2024-10-08","cited_by_count":57},{"id":"2412.03934","title":"InfiniCube: Unbounded and Controllable Dynamic 3D Driving Scene Generation with World-Guided Video Models","created":"2024-12-05","cited_by_count":56},{"id":"2601.02281","title":"InfiniteVGGT: Visual Geometry Grounded Transformer for Endless Streams","created":"2026-01-05","cited_by_count":56},{"id":"2501.00602","title":"STORM: Spatio-Temporal Reconstruction Model for Large-Scale Outdoor Scenes","created":"2024-12-31","cited_by_count":55},{"id":"2401.04099","title":"AGG: Amortized Generative 3D Gaussians for Single Image to 3D","created":"2024-01-08","cited_by_count":53},{"id":"2412.03526","title":"Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos","created":"2024-12-04","cited_by_count":49},{"id":"2506.08015","title":"4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos","created":"2025-06-09","cited_by_count":49},{"id":"2509.19297","title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","created":"2025-09-23","cited_by_count":48},{"id":"2507.16290","title":"Dens3R: A Foundation Model for 3D Geometry Prediction","created":"2025-07-22","cited_by_count":46},{"id":"2601.00393","title":"NeoVerse: Enhancing 4D World Model with in-the-wild Monocular Videos","created":"2026-01-01","cited_by_count":46},{"id":"2511.21688","title":"G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning","created":"2025-11-26","cited_by_count":44},{"id":"2509.19296","title":"Lyra: Generative 3D Scene Reconstruction via Video Diffusion Model Self-Distillation","created":"2025-09-23","cited_by_count":41},{"id":"2512.15716","title":"Spatia: Video Generation with Updatable Spatial Memory","created":"2025-12-17","cited_by_count":40},{"id":"2306.00180","title":"FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow","created":"2023-05-31","cited_by_count":39},{"id":"2603.03269","title":"LoGeR: Long-Context Geometric Reconstruction with Hybrid Memory","created":"2026-03-03","cited_by_count":39},{"id":"2509.21657","title":"FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction","created":"2025-09-25","cited_by_count":38},{"id":"2510.06219","title":"Human3R: Everyone Everywhere All at Once","created":"2025-10-07","cited_by_count":37},{"id":"2511.07321","title":"YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting","created":"2025-11-10","cited_by_count":37},{"id":"2507.10065","title":"MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second","created":"2025-07-14","cited_by_count":35},{"id":"2509.05296","title":"WinT3R: Window-Based Streaming Reconstruction with Camera Token Pool","created":"2025-09-05","cited_by_count":35},{"id":"2512.10935","title":"Any4D: Unified Feed-Forward Metric 4D Reconstruction","created":"2025-12-11","cited_by_count":35},{"id":"2508.13154","title":"4DNeX: Feed-Forward 4D Generative Modeling Made Easy","created":"2025-08-18","cited_by_count":34},{"id":"2601.09499","title":"V-DPM: 4D Video Reconstruction with Dynamic Point Maps","created":"2026-01-14","cited_by_count":34},{"id":"2209.02417","title":"Volume Rendering Digest (for NeRF)","created":"2022-08-29","cited_by_count":32},{"id":"2504.02261","title":"WonderTurbo: Generating Interactive 3D World in 0.72 Seconds","created":"2025-04-03","cited_by_count":32},{"id":"2505.23734","title":"ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS","created":"2025-05-29","cited_by_count":32},{"id":"2601.04090","title":"Gen3R: 3D Scene Generation Meets Feed-Forward Reconstruction","created":"2026-01-07","cited_by_count":31},{"id":"2412.06777","title":"Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving","created":"2024-12-09","cited_by_count":29},{"id":"2412.09043","title":"DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving","created":"2024-12-12","cited_by_count":29},{"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},{"id":"2511.19971","title":"VGGT4D: Mining Motion Cues in Visual Geometry Transformers for 4D Scene Reconstruction","created":"2025-11-25","cited_by_count":28},{"id":"2507.14501","title":"Advances in Feed-Forward 3D Reconstruction and View Synthesis: A Survey","created":"2025-07-19","cited_by_count":27},{"id":"2412.19584","title":"DAS3R: Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction","created":"2024-12-27","cited_by_count":26},{"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},{"id":"2603.04385","title":"ZipMap: Linear-Time Stateful 3D Reconstruction via Test-Time Training","created":"2026-03-04","cited_by_count":26},{"id":"2508.17437","title":"Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels","created":"2025-08-20","cited_by_count":24},{"id":"2509.07120","title":"Block-Sparse Global Attention for Efficient Multi-View Geometry Transformers","created":"2025-09-08","cited_by_count":23},{"id":"2510.07313","title":"WristWorld: Generating Wrist-Views via 4D World Models for Robotic Manipulation","created":"2025-10-08","cited_by_count":23},{"id":"2602.13172","title":"LongStream: Long-Sequence Streaming Autoregressive Visual Geometry","created":"2026-02-13","cited_by_count":23},{"id":"2511.10560","title":"OmniVGGT: Omni-Modality Driven Visual Geometry Grounded Transformer","created":"2025-11-13","cited_by_count":22},{"id":"2512.04012","title":"Emergent Outlier View Rejection in Visual Geometry Grounded Transformers","created":"2025-12-03","cited_by_count":22},{"id":"2512.10950","title":"E-RayZer: Self-supervised 3D Reconstruction as Spatial Visual Pre-training","created":"2025-12-11","cited_by_count":22},{"id":"2602.10094","title":"4RC: 4D Reconstruction via Conditional Querying Anytime and Anywhere","created":"2026-02-10","cited_by_count":22},{"id":"2510.06208","title":"ShapeGen4D: Towards High Quality 4D Shape Generation from Videos","created":"2025-10-07","cited_by_count":21},{"id":"2510.27234","title":"MoRE: 3D Visual Geometry Reconstruction Meets Mixture-of-Experts","created":"2025-10-31","cited_by_count":21},{"id":"2508.17972","title":"SAIL-Recon: Large SfM by Augmenting Scene Regression with Localization","created":"2025-08-25","cited_by_count":20},{"id":"2510.01183","title":"EvoWorld: Evolving Panoramic World Generation with Explicit 3D Memory","created":"2025-10-01","cited_by_count":20},{"id":"2511.20343","title":"AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend","created":"2025-11-25","cited_by_count":20},{"id":"2410.18979","title":"PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views","created":"2024-10-24","cited_by_count":19}],"next_cursor":"100"}