{"list":"other","total":71,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1607.06450","title":"Layer Normalization","created":"2016-07-21","cited_by_count":5669},{"id":"2310.03744","title":"Improved Baselines with Visual Instruction Tuning","created":"2023-10-05","cited_by_count":4418},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"2201.03546","title":"Language-driven Semantic Segmentation","created":"2022-01-10","cited_by_count":717},{"id":"2312.12337","title":"pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction","created":"2023-12-19","cited_by_count":684},{"id":"2112.01071","title":"Extract Free Dense Labels from CLIP","created":"2021-12-02","cited_by_count":583},{"id":"2403.14627","title":"MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images","created":"2024-03-21","cited_by_count":566},{"id":"2312.16084","title":"LangSplat: 3D Language Gaussian Splatting","created":"2023-12-26","cited_by_count":415},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295},{"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":"2303.11797","title":"CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation","created":"2023-03-21","cited_by_count":219},{"id":"2111.13539","title":"GeoNeRF: Generalizing NeRF with Geometry Priors","created":"2021-11-26","cited_by_count":196},{"id":"1612.00404","title":"Learning Shape Abstractions by Assembling Volumetric Primitives","created":"2016-12-01","cited_by_count":181},{"id":"2408.13912","title":"Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs","created":"2024-08-25","cited_by_count":178},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"1904.09970","title":"Superquadrics Revisited: Learning 3D Shape Parsing beyond Cuboids","created":"2019-04-22","cited_by_count":124},{"id":"2207.10866","title":"Cost Aggregation with 4D Convolutional Swin Transformer for Few-Shot Segmentation","created":"2022-07-22","cited_by_count":114},{"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":"2304.08463","title":"Learning to Render Novel Views from Wide-Baseline Stereo Pairs","created":"2023-04-17","cited_by_count":104},{"id":"2405.17958","title":"FreeSplat: Generalizable 3D Gaussian Splatting Towards Free-View Synthesis of Indoor Scenes","created":"2024-05-28","cited_by_count":89},{"id":"2106.02520","title":"CATs: Cost Aggregation Transformers for Visual Correspondence","created":"2021-06-04","cited_by_count":77},{"id":"2408.13770","title":"TranSplat: Generalizable 3D Gaussian Splatting from Sparse Multi-View Images with Transformers","created":"2024-08-25","cited_by_count":75},{"id":"2410.18956","title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","created":"2024-10-24","cited_by_count":73},{"id":"2004.01176","title":"Learning Unsupervised Hierarchical Part Decomposition of 3D Objects from a Single RGB Image","created":"2020-04-02","cited_by_count":72},{"id":"2312.04565","title":"MuRF: Multi-Baseline Radiance Fields","created":"2023-12-07","cited_by_count":71},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71},{"id":"2410.22128","title":"PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting","created":"2024-10-29","cited_by_count":62},{"id":"2202.06817","title":"CATs++: Boosting Cost Aggregation with Convolutions and Transformers","created":"2022-02-14","cited_by_count":53},{"id":"2502.16652","title":"Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding Registration","created":"2025-02-23","cited_by_count":51},{"id":"2509.19297","title":"VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction","created":"2025-09-23","cited_by_count":48},{"id":"2507.07136","title":"LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS","created":"2025-07-09","cited_by_count":41},{"id":"2508.01171","title":"No Pose at All: Self-Supervised Pose-Free 3D Gaussian Splatting from Sparse Views","created":"2025-08-02","cited_by_count":40},{"id":"2307.05473","title":"Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives","created":"2023-07-11","cited_by_count":38},{"id":"2312.07246","title":"Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs","created":"2023-12-12","cited_by_count":37},{"id":"2410.14462","title":"LUDVIG: Learning-Free Uplifting of 2D Visual Features to Gaussian Splatting Scenes","created":"2024-10-18","cited_by_count":37},{"id":"2403.09413","title":"Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting","created":"2024-03-14","cited_by_count":34},{"id":"2210.02689","title":"Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence","created":"2022-10-06","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":"2503.18944","title":"DINO in the Room: Leveraging 2D Foundation Models for 3D Segmentation","created":"2025-03-24","cited_by_count":31},{"id":"2106.03090","title":"Deep Matching Prior: Test-Time Optimization for Dense Correspondence","created":"2021-06-06","cited_by_count":30},{"id":"2412.09072","title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","created":"2024-12-12","cited_by_count":30},{"id":"2510.12764","title":"AnyUp: Universal Feature Upsampling","created":"2025-10-14","cited_by_count":28},{"id":"2503.16338","title":"Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images","created":"2025-03-20","cited_by_count":27},{"id":"2509.18096","title":"Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers","created":"2025-09-22","cited_by_count":24},{"id":"2503.20168","title":"EVolSplat: Efficient Volume-based Gaussian Splatting for Urban View Synthesis","created":"2025-03-26","cited_by_count":21},{"id":"2504.00992","title":"SuperDec: 3D Scene Decomposition with Superquadric Primitives","created":"2025-04-01","cited_by_count":21},{"id":"2409.19846","title":"Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels","created":"2024-09-30","cited_by_count":19},{"id":"2412.01807","title":"Occam's LGS: An Efficient Approach for Language Gaussian Splatting","created":"2024-12-02","cited_by_count":16},{"id":"2403.11120","title":"Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence","created":"2024-03-17","cited_by_count":14},{"id":"2505.23044","title":"SpatialSplat: Efficient Semantic 3D from Sparse Unposed Images","created":"2025-05-29","cited_by_count":13},{"id":"2507.16144","title":"LongSplat: Online Generalizable 3D Gaussian Splatting from Long Sequence Images","created":"2025-07-22","cited_by_count":13},{"id":"2508.05254","title":"CF3: Compact and Fast 3D Feature Fields","created":"2025-08-07","cited_by_count":11}],"next_cursor":null}