{"list":"other","total":57,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2110.08207","title":"Multitask Prompted Training Enables Zero-Shot Task Generalization","created":"2021-10-15","cited_by_count":1470},{"id":"1911.11763","title":"SuperGlue: Learning Feature Matching with Graph Neural Networks","created":"2019-11-26","cited_by_count":1443},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1608.05442","title":"Semantic Understanding of Scenes through the ADE20K Dataset","created":"2016-08-18","cited_by_count":1069},{"id":"1502.00956","title":"ORB-SLAM: a Versatile and Accurate Monocular SLAM System","created":"2015-02-03","cited_by_count":988},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"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":"2312.10035","title":"Point Transformer V3: Simpler, Faster, Stronger","created":"2023-12-15","cited_by_count":589},{"id":"2211.15654","title":"OpenScene: 3D Scene Understanding with Open Vocabularies","created":"2022-11-28","cited_by_count":559},{"id":"2202.11094","title":"GroupViT: Semantic Segmentation Emerges from Text Supervision","created":"2022-02-22","cited_by_count":531},{"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":"1912.08830","title":"ScanRefer: 3D Object Localization in RGB-D Scans using Natural Language","created":"2019-12-18","cited_by_count":452},{"id":"2103.15875","title":"In-Place Scene Labelling and Understanding with Implicit Scene Representation","created":"2021-03-29","cited_by_count":415},{"id":"1606.05830","title":"Past, Present, and Future of Simultaneous Localization And Mapping: Towards the Robust-Perception Age","created":"2016-06-19","cited_by_count":411},{"id":"2312.03203","title":"Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distilled Feature Fields","created":"2023-12-06","cited_by_count":364},{"id":"2210.03105","title":"Mask3D: Mask Transformer for 3D Semantic Instance Segmentation","created":"2022-10-06","cited_by_count":303},{"id":"2312.04563","title":"Visual Geometry Grounded Deep Structure From Motion","created":"2023-12-07","cited_by_count":227},{"id":"2108.08291","title":"Pixel-Perfect Structure-from-Motion with Featuremetric Refinement","created":"2021-08-18","cited_by_count":200},{"id":"2209.03494","title":"Neural Feature Fusion Fields: 3D Distillation of Self-Supervised 2D Image Representations","created":"2022-09-07","cited_by_count":196},{"id":"2212.09802","title":"Panoptic Lifting for 3D Scene Understanding with Neural Fields","created":"2022-12-19","cited_by_count":174},{"id":"2211.14813","title":"SegCLIP: Patch Aggregation with Learnable Centers for Open-Vocabulary Semantic Segmentation","created":"2022-11-27","cited_by_count":164},{"id":"2306.15667","title":"PoseDiffusion: Solving Pose Estimation via Diffusion-aided Bundle Adjustment","created":"2023-06-27","cited_by_count":147},{"id":"2208.03543","title":"MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformer","created":"2022-08-06","cited_by_count":136},{"id":"2309.12311","title":"LLM-Grounder: Open-Vocabulary 3D Visual Grounding with Large Language Model as an Agent","created":"2023-09-21","cited_by_count":135},{"id":"2402.14817","title":"Cameras as Rays: Pose Estimation via Ray Diffusion","created":"2024-02-22","cited_by_count":131},{"id":"2212.00785","title":"Learning to Generate Text-grounded Mask for Open-world Semantic Segmentation from Only Image-Text Pairs","created":"2022-12-01","cited_by_count":130},{"id":"2308.07931","title":"Distilled Feature Fields Enable Few-Shot Language-Guided Manipulation","created":"2023-07-27","cited_by_count":130},{"id":"2105.11450","title":"SAT: 2D Semantics Assisted Training for 3D Visual Grounding","created":"2021-05-24","cited_by_count":124},{"id":"2403.10516","title":"FeatUp: A Model-Agnostic Framework for Features at Any Resolution","created":"2024-03-15","cited_by_count":116},{"id":"2208.05963","title":"RelPose: Predicting Probabilistic Relative Rotation for Single Objects in the Wild","created":"2022-08-11","cited_by_count":102},{"id":"2301.09121","title":"Learning Open-vocabulary Semantic Segmentation Models From Natural Language Supervision","created":"2023-01-22","cited_by_count":99},{"id":"2305.04926","title":"RelPose++: Recovering 6D Poses from Sparse-view Observations","created":"2023-05-08","cited_by_count":87},{"id":"2210.09996","title":"Perceptual Grouping in Contrastive Vision-Language Models","created":"2022-10-18","cited_by_count":82},{"id":"2410.18956","title":"Large Spatial Model: End-to-end Unposed Images to Semantic 3D","created":"2024-10-24","cited_by_count":73},{"id":"2209.08776","title":"NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes","created":"2022-09-19","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":"2405.11442","title":"Unifying 3D Vision-Language Understanding via Promptable Queries","created":"2024-05-19","cited_by_count":70},{"id":"2105.11610","title":"Unsupervised Scale-consistent Depth Learning from Video","created":"2021-05-25","cited_by_count":69},{"id":"2207.08455","title":"Open-world Semantic Segmentation via Contrasting and Clustering Vision-Language Embedding","created":"2022-07-18","cited_by_count":67},{"id":"2211.03660","title":"SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes","created":"2022-11-07","cited_by_count":52},{"id":"2302.10307","title":"ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency","created":"2023-01-31","cited_by_count":51},{"id":"2006.02708","title":"Auto-Rectify Network for Unsupervised Indoor Depth Estimation","created":"2020-06-04","cited_by_count":39},{"id":"2406.10224","title":"EFM3D: A Benchmark for Measuring Progress Towards 3D Egocentric Foundation Models","created":"2024-06-14","cited_by_count":26},{"id":"2401.02416","title":"ODIN: A Single Model for 2D and 3D Segmentation","created":"2024-01-04","cited_by_count":25},{"id":"2307.10713","title":"Kick Back & Relax: Learning to Reconstruct the World by Watching SlowTV","created":"2023-07-20","cited_by_count":21},{"id":"2304.02847","title":"Robustmix: Improving Robustness by Regularizing the Frequency Bias of Deep Nets","created":"2023-04-06","cited_by_count":4}],"next_cursor":null}