{"list":"other","total":67,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"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":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"1709.01507","title":"Squeeze-and-Excitation Networks","created":"2017-09-05","cited_by_count":4789},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"id":"2201.03545","title":"A ConvNet for the 2020s","created":"2022-01-10","cited_by_count":3579},{"id":"1606.08415","title":"Gaussian Error Linear Units (GELUs)","created":"2016-06-27","cited_by_count":3502},{"id":"2303.15343","title":"Sigmoid Loss for Language Image Pre-Training","created":"2023-03-27","cited_by_count":3109},{"id":"1611.05431","title":"Aggregated Residual Transformations for Deep Neural Networks","created":"2016-11-16","cited_by_count":2546},{"id":"1311.3618","title":"Describing Textures in the Wild","created":"2013-11-14","cited_by_count":2125},{"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":"1907.01341","title":"Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer","created":"2019-07-02","cited_by_count":1495},{"id":"1811.12231","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","created":"2018-11-29","cited_by_count":1432},{"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":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2111.07832","title":"iBOT: Image BERT Pre-Training with Online Tokenizer","created":"2021-11-15","cited_by_count":903},{"id":"2311.04400","title":"LRM: Large Reconstruction Model for Single Image to 3D","created":"2023-11-08","cited_by_count":849},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2404.08471","title":"Revisiting Feature Prediction for Learning Visual Representations from Video","created":"2024-02-15","cited_by_count":531},{"id":"2204.07118","title":"DeiT III: Revenge of the ViT","created":"2022-04-14","cited_by_count":419},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"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":"2409.18125","title":"LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awareness","created":"2024-09-26","cited_by_count":183},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"2404.08636","title":"Probing the 3D Awareness of Visual Foundation Models","created":"2024-04-12","cited_by_count":177},{"id":"1904.04998","title":"Depth from Videos in the Wild: Unsupervised Monocular Depth Learning from Unknown Cameras","created":"2019-04-10","cited_by_count":170},{"id":"2210.10716","title":"CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion","created":"2022-10-19","cited_by_count":160},{"id":"2401.08541","title":"Scalable Pre-training of Large Autoregressive Image Models","created":"2024-01-16","cited_by_count":115},{"id":"2203.10981","title":"MonoDTR: Monocular 3D Object Detection with Depth-Aware Transformer","created":"2022-03-21","cited_by_count":109},{"id":"1509.01329","title":"Semantic Amodal Segmentation","created":"2015-09-04","cited_by_count":103},{"id":"2403.13788","title":"DepthFM: Fast Monocular Depth Estimation with Flow Matching","created":"2024-03-20","cited_by_count":76},{"id":"2407.20229","title":"Improving 2D Feature Representations by 3D-Aware Fine-Tuning","created":"2024-07-29","cited_by_count":71},{"id":"2401.11673","title":"MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo","created":"2024-01-22","cited_by_count":50},{"id":"2409.03757","title":"Lexicon3D: Probing Visual Foundation Models for Complex 3D Scene Understanding","created":"2024-09-05","cited_by_count":49},{"id":"1911.07034","title":"Instance Shadow Detection","created":"2019-11-16","cited_by_count":37},{"id":"2312.13216","title":"Improving Semantic Correspondence with Viewpoint-Guided Spherical Maps","created":"2023-12-20","cited_by_count":34},{"id":"2310.06836","title":"A General Protocol to Probe Large Vision Models for 3D Physical Understanding","created":"2023-10-10","cited_by_count":32},{"id":"1604.02129","title":"Horizon Lines in the Wild","created":"2016-04-07","cited_by_count":30},{"id":"1608.05684","title":"Detecting Vanishing Points using Global Image Context in a Non-Manhattan World","created":"2016-08-19","cited_by_count":27},{"id":"2406.09613","title":"ImageNet3D: Towards General-Purpose Object-Level 3D Understanding","created":"2024-06-13","cited_by_count":25},{"id":"2208.01489","title":"Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Matter","created":"2022-08-02","cited_by_count":18},{"id":"2406.04138","title":"The 3D-PC: a benchmark for visual perspective taking in humans and machines","created":"2024-06-06","cited_by_count":16},{"id":"2311.11325","title":"MoVideo: Motion-Aware Video Generation with Diffusion Models","created":"2023-11-19","cited_by_count":15},{"id":"2409.05862","title":"Evaluating Multiview Object Consistency in Humans and Image Models","created":"2024-09-09","cited_by_count":13},{"id":"1608.04267","title":"Detecting Dominant Vanishing Points in Natural Scenes with Application to Composition-Sensitive Image Retrieval","created":"2016-08-15","cited_by_count":11},{"id":"2408.17027","title":"ConDense: Consistent 2D/3D Pre-training for Dense and Sparse Features from Multi-View Images","created":"2024-08-30","cited_by_count":9},{"id":"1907.10014","title":"Temporally Consistent Horizon Lines","created":"2019-07-23","cited_by_count":8},{"id":"2310.00986","title":"Multi-task Learning with 3D-Aware Regularization","created":"2023-10-02","cited_by_count":8},{"id":"2408.11748","title":"Understanding Depth and Height Perception in Large Visual-Language Models","created":"2024-08-21","cited_by_count":8},{"id":"2308.11300","title":"Approaching human 3D shape perception with neurally mappable models","created":"2023-08-22","cited_by_count":6},{"id":"2406.12671","title":"GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models","created":"2024-06-18","cited_by_count":5},{"id":"2204.10384","title":"Monocular Depth Estimation Using Cues Inspired by Biological Vision Systems","created":"2022-04-21","cited_by_count":4},{"id":"2403.15551","title":"Language-Based Depth Hints for Monocular Depth Estimation","created":"2024-03-22","cited_by_count":3},{"id":"2406.02535","title":"Enhancing 2D Representation Learning with a 3D Prior","created":"2024-06-04","cited_by_count":3}],"next_cursor":null}