{"list":"other","total":65,"rows":[{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1903.12261","title":"Benchmarking Neural Network Robustness to Common Corruptions and Perturbations","created":"2019-03-28","cited_by_count":2877},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"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":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"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":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"2109.08238","title":"Habitat-Matterport 3D Dataset (HM3D): 1000 Large-scale 3D Environments for Embodied AI","created":"2021-09-16","cited_by_count":592},{"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":"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":"2311.18259","title":"Ego-Exo4D: Understanding Skilled Human Activity from First- and Third-Person Perspectives","created":"2023-11-30","cited_by_count":490},{"id":"1705.08168","title":"Look, Listen and Learn","created":"2017-05-23","cited_by_count":458},{"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":"1803.02276","title":"GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Pose","created":"2018-03-06","cited_by_count":342},{"id":"1804.03641","title":"Audio-Visual Scene Analysis with Self-Supervised Multisensory Features","created":"2018-04-10","cited_by_count":335},{"id":"2301.04856","title":"Multimodal Deep Learning","created":"2023-01-12","cited_by_count":258},{"id":"1807.00230","title":"Cooperative Learning of Audio and Video Models from Self-Supervised Synchronization","created":"2018-06-30","cited_by_count":249},{"id":"1809.00461","title":"YouTube-VOS: Sequence-to-Sequence Video Object Segmentation","created":"2018-09-03","cited_by_count":232},{"id":"2310.13724","title":"Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots","created":"2023-10-19","cited_by_count":228},{"id":"2412.04463","title":"MegaSaM: Accurate, Fast, and Robust Structure and Motion from Casual Dynamic Videos","created":"2024-12-05","cited_by_count":228},{"id":"2005.00343","title":"The EPIC-KITCHENS Dataset: Collection, Challenges and Baselines","created":"2020-04-29","cited_by_count":225},{"id":"2308.13561","title":"Project Aria: A New Tool for Egocentric Multi-Modal AI Research","created":"2023-08-24","cited_by_count":208},{"id":"2008.04237","title":"Self-Supervised Learning of Audio-Visual Objects from Video","created":"2020-08-10","cited_by_count":188},{"id":"2210.07839","title":"Contrastive Audio-Visual Masked Autoencoder","created":"2022-10-02","cited_by_count":146},{"id":"2503.01661","title":"MUSt3R: Multi-view Network for Stereo 3D Reconstruction","created":"2025-03-03","cited_by_count":141},{"id":"1512.08512","title":"Visually Indicated Sounds","created":"2015-12-28","cited_by_count":128},{"id":"2403.04765","title":"Efficient LoFTR: Semi-Dense Local Feature Matching with Sparse-Like Speed","created":"2024-03-07","cited_by_count":120},{"id":"2210.05494","title":"Map-free Visual Relocalization: Metric Pose Relative to a Single Image","created":"2022-10-11","cited_by_count":114},{"id":"2102.11273","title":"On Interaction Between Augmentations and Corruptions in Natural Corruption Robustness","created":"2021-02-22","cited_by_count":97},{"id":"1912.11684","title":"Look, Listen, and Act: Towards Audio-Visual Embodied Navigation","created":"2019-12-25","cited_by_count":96},{"id":"2011.01819","title":"Learning Representations from Audio-Visual Spatial Alignment","created":"2020-11-03","cited_by_count":95},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95},{"id":"1809.02587","title":"Self-Supervised Generation of Spatial Audio for 360 Video","created":"2018-09-07","cited_by_count":93},{"id":"1809.00716","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","created":"2018-09-03","cited_by_count":87},{"id":"2412.08376","title":"Reloc3r: Large-Scale Training of Relative Camera Pose Regression for Generalizable, Fast, and Accurate Visual Localization","created":"2024-12-11","cited_by_count":82},{"id":"1608.07017","title":"Ambient Sound Provides Supervision for Visual Learning","created":"2016-08-25","cited_by_count":78},{"id":"1812.04204","title":"2.5D Visual Sound","created":"2018-12-11","cited_by_count":63},{"id":"2212.08071","title":"MAViL: Masked Audio-Video Learners","created":"2022-12-15","cited_by_count":59},{"id":"2005.01616","title":"VisualEchoes: Spatial Image Representation Learning through Echolocation","created":"2020-05-04","cited_by_count":55},{"id":"2212.05922","title":"Audiovisual Masked Autoencoders","created":"2022-12-09","cited_by_count":49},{"id":"2006.06175","title":"Telling Left from Right: Learning Spatial Correspondence of Sight and Sound","created":"2020-06-11","cited_by_count":43},{"id":"1903.01292","title":"The StreetLearn Environment and Dataset","created":"2019-03-04","cited_by_count":42},{"id":"2301.08730","title":"Novel-View Acoustic Synthesis","created":"2023-01-20","cited_by_count":33},{"id":"2012.15470","title":"Audio-Visual Floorplan Reconstruction","created":"2020-12-31","cited_by_count":32},{"id":"1912.07011","title":"BatVision: Learning to See 3D Spatial Layout with Two Ears","created":"2019-12-15","cited_by_count":26},{"id":"2303.11329","title":"Sound Localization from Motion: Jointly Learning Sound Direction and Camera Rotation","created":"2023-03-20","cited_by_count":18},{"id":"2503.23282","title":"AnyCam: Learning to Recover Camera Poses and Intrinsics from Casual Videos","created":"2025-03-30","cited_by_count":18},{"id":"2111.08046","title":"Beyond Mono to Binaural: Generating Binaural Audio from Mono Audio with Depth and Cross Modal Attention","created":"2021-11-15","cited_by_count":17},{"id":"2501.07574","title":"UnCommon Objects in 3D","created":"2025-01-13","cited_by_count":17},{"id":"2403.03221","title":"FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation","created":"2024-03-05","cited_by_count":12},{"id":"2501.07742","title":"RePoseD: Efficient Relative Pose Estimation With Known Depth Information","created":"2025-01-13","cited_by_count":10},{"id":"2503.07561","title":"Alligat0R: Pre-Training Through Co-Visibility Segmentation for Relative Camera Pose Regression","created":"2025-03-10","cited_by_count":10},{"id":"2307.04760","title":"Learning Spatial Features from Audio-Visual Correspondence in Egocentric Videos","created":"2023-07-10","cited_by_count":8},{"id":"2412.16155","title":"Can Generative Video Models Help Pose Estimation?","created":"2024-12-20","cited_by_count":7},{"id":"2407.18552","title":"Multimodal Emotion Recognition using Audio-Video Transformer Fusion with Cross Attention","created":"2024-07-26","cited_by_count":5},{"id":"2406.14367","title":"PoseBench: Benchmarking the Robustness of Pose Estimation Models under Corruptions","created":"2024-06-20","cited_by_count":4},{"id":"2404.17251","title":"Camera Motion Estimation from RGB-D-Inertial Scene Flow","created":"2024-04-26","cited_by_count":3}],"next_cursor":null}