{"list":"other","total":116,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2012.12877","title":"Training data-efficient image transformers & distillation through attention","created":"2020-12-23","cited_by_count":4586},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1703.04977","title":"What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?","created":"2017-03-15","cited_by_count":2352},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2103.15691","title":"ViViT: A Video Vision Transformer","created":"2021-03-29","cited_by_count":1620},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"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":"2309.16588","title":"Vision Transformers Need Registers","created":"2023-09-28","cited_by_count":871},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"1804.02505","title":"MVSNet: Depth Inference for Unstructured Multi-view Stereo","created":"2018-04-07","cited_by_count":788},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2103.17239","title":"Going deeper with Image Transformers","created":"2021-03-31","cited_by_count":764},{"id":"2402.05054","title":"LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation","created":"2024-02-07","cited_by_count":739},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1912.07372","title":"Differentiable Volumetric Rendering: Learning Implicit 3D Representations without 3D Supervision","created":"2019-12-16","cited_by_count":700},{"id":"2108.10869","title":"DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras","created":"2021-08-24","cited_by_count":687},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2306.13643","title":"LightGlue: Local Feature Matching at Light Speed","created":"2023-06-23","cited_by_count":590},{"id":"2501.12387","title":"Continuous 3D Perception Model with Persistent State","created":"2025-01-21","cited_by_count":548},{"id":"2312.16256","title":"DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision","created":"2023-12-26","cited_by_count":537},{"id":"2307.07635","title":"CoTracker: It is Better to Track Together","created":"2023-07-14","cited_by_count":522},{"id":"2407.08608","title":"FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision","created":"2024-07-11","cited_by_count":519},{"id":"2106.14405","title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","created":"2021-06-28","cited_by_count":511},{"id":"1911.10127","title":"BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks","created":"2019-11-22","cited_by_count":490},{"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":"1912.06378","title":"Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching","created":"2019-12-13","cited_by_count":417},{"id":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"2501.13928","title":"Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass","created":"2025-01-23","cited_by_count":367},{"id":"2312.13150","title":"Splatter Image: Ultra-Fast Single-View 3D Reconstruction","created":"2023-12-20","cited_by_count":364},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2404.19702","title":"GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting","created":"2024-04-30","cited_by_count":349},{"id":"1905.03561","title":"D2-Net: A Trainable CNN for Joint Detection and Description of Local Features","created":"2019-05-09","cited_by_count":326},{"id":"2006.13566","title":"DISK: Learning local features with policy gradient","created":"2020-06-24","cited_by_count":312},{"id":"1603.09114","title":"LIFT: Learned Invariant Feature Transform","created":"2016-03-30","cited_by_count":306},{"id":"2305.15404","title":"RoMa: Robust Dense Feature Matching","created":"2023-05-24","cited_by_count":302},{"id":"2403.14621","title":"GRM: Large Gaussian Reconstruction Model for Efficient 3D Reconstruction and Generation","created":"2024-03-21","cited_by_count":301},{"id":"2410.19115","title":"MoGe: Unlocking Accurate Monocular Geometry Estimation for Open-Domain Images with Optimal Training Supervision","created":"2024-10-24","cited_by_count":299},{"id":"2306.08637","title":"TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement","created":"2023-06-14","cited_by_count":287},{"id":"2010.04245","title":"Query-Key Normalization for Transformers","created":"2020-10-08","cited_by_count":280},{"id":"1804.00650","title":"DeepMVS: Learning Multi-view Stereopsis","created":"2018-04-02","cited_by_count":277},{"id":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"2211.03726","title":"TAP-Vid: A Benchmark for Tracking Any Point in a Video","created":"2022-11-07","cited_by_count":263},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"id":"2003.01587","title":"Image Matching across Wide Baselines: From Paper to Practice","created":"2020-03-03","cited_by_count":225},{"id":"2407.20219","title":"Global Structure-from-Motion Revisited","created":"2024-07-29","cited_by_count":218},{"id":"2204.04153","title":"Particle Video Revisited: Tracking Through Occlusions Using Point Trajectories","created":"2022-04-08","cited_by_count":217},{"id":"2205.15848","title":"Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction","created":"2022-05-31","cited_by_count":212},{"id":"2012.01411","title":"PatchmatchNet: Learned Multi-View Patchmatch Stereo","created":"2020-12-02","cited_by_count":207},{"id":"1612.02401","title":"DeMoN: Depth and Motion Network for Learning Monocular Stereo","created":"2016-12-07","cited_by_count":201},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"2109.01129","title":"NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-view Stereo","created":"2021-09-02","cited_by_count":192},{"id":"2410.17242","title":"LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias","created":"2024-10-22","cited_by_count":189},{"id":"1812.04605","title":"DeepV2D: Video to Depth with Differentiable Structure from Motion","created":"2018-12-11","cited_by_count":185},{"id":"2404.04319","title":"SpatialTracker: Tracking Any 2D Pixels in 3D Space","created":"2024-04-05","cited_by_count":181},{"id":"2502.12138","title":"FLARE: Feed-forward Geometry, Appearance and Camera Estimation from Uncalibrated Sparse Views","created":"2025-02-17","cited_by_count":180},{"id":"2202.00667","title":"DKM: Dense Kernelized Feature Matching for Geometry Estimation","created":"2022-02-01","cited_by_count":177},{"id":"1806.04807","title":"BA-Net: Dense Bundle Adjustment Network","created":"2018-06-13","cited_by_count":175},{"id":"2306.06362","title":"Aria Digital Twin: A New Benchmark Dataset for Egocentric 3D Machine Perception","created":"2023-06-10","cited_by_count":167},{"id":"2311.12024","title":"PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction","created":"2023-11-20","cited_by_count":165},{"id":"2409.19152","title":"MASt3R-SfM: a Fully-Integrated Solution for Unconstrained Structure-from-Motion","created":"2024-09-27","cited_by_count":162},{"id":"2303.06296","title":"Stabilizing Transformer Training by Preventing Attention Entropy Collapse","created":"2023-03-11","cited_by_count":161},{"id":"1701.08493","title":"A Survey of Structure from Motion","created":"2017-01-30","cited_by_count":158},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"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":"1509.05909","title":"Modelling Uncertainty in Deep Learning for Camera Relocalization","created":"2015-09-19","cited_by_count":134},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"2304.03608","title":"ALIKED: A Lighter Keypoint and Descriptor Extraction Network via Deformable Transformation","created":"2023-04-07","cited_by_count":121},{"id":"2402.00847","title":"BootsTAP: Bootstrapped Training for Tracking-Any-Point","created":"2024-02-01","cited_by_count":120},{"id":"2401.12592","title":"RGBD Objects in the Wild: Scaling Real-World 3D Object Learning from RGB-D Videos","created":"2024-01-23","cited_by_count":115},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102},{"id":"2108.08771","title":"Learning to Match Features with Seeded Graph Matching Network","created":"2021-08-19","cited_by_count":92},{"id":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87},{"id":"2201.01501","title":"Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation","created":"2022-01-05","cited_by_count":82},{"id":"2407.15420","title":"Local All-Pair Correspondence for Point Tracking","created":"2024-07-22","cited_by_count":80},{"id":"2404.14351","title":"Scene Coordinate Reconstruction: Posing of Image Collections via Incremental Learning of a Relocalizer","created":"2024-04-22","cited_by_count":73},{"id":"2306.15669","title":"Detector-Free Structure from Motion","created":"2023-06-27","cited_by_count":71},{"id":"1912.09697","title":"DeepSFM: Structure From Motion Via Deep Bundle Adjustment","created":"2019-12-20","cited_by_count":70},{"id":"2207.09442","title":"Theseus: A Library for Differentiable Nonlinear Optimization","created":"2022-07-19","cited_by_count":65}],"next_cursor":"100"}