{"list":"other","total":60,"rows":[{"id":"1810.04805","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","created":"2018-10-11","cited_by_count":40399},{"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":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"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":"1612.01474","title":"Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles","created":"2016-12-05","cited_by_count":3926},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"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":"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":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"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":"2111.09886","title":"SimMIM: A Simple Framework for Masked Image Modeling","created":"2021-11-18","cited_by_count":1153},{"id":"1703.02910","title":"Deep Bayesian Active Learning with Image Data","created":"2017-03-08","cited_by_count":819},{"id":"1805.12114","title":"Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models","created":"2018-05-30","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":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2302.03011","title":"Structure and Content-Guided Video Synthesis with Diffusion Models","created":"2023-02-06","cited_by_count":590},{"id":"2204.01697","title":"MaxViT: Multi-Axis Vision Transformer","created":"2022-04-04","cited_by_count":476},{"id":"2301.11445","title":"3DShape2VecSet: A 3D Shape Representation for Neural Fields and Generative Diffusion Models","created":"2023-01-26","cited_by_count":458},{"id":"1906.08158","title":"BatchBALD: Efficient and Diverse Batch Acquisition for Deep Bayesian Active Learning","created":"2019-06-19","cited_by_count":432},{"id":"1907.10326","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","created":"2019-07-24","cited_by_count":382},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286},{"id":"2303.02153","title":"Unleashing Text-to-Image Diffusion Models for Visual Perception","created":"2023-03-03","cited_by_count":269},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"2203.15270","title":"MAT: Mask-Aware Transformer for Large Hole Image Inpainting","created":"2022-03-29","cited_by_count":218},{"id":"2007.10042","title":"Non-Local Spatial Propagation Network for Depth Completion","created":"2020-07-20","cited_by_count":195},{"id":"1709.07492","title":"Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image","created":"2017-09-21","cited_by_count":161},{"id":"2303.17559","title":"DDP: Diffusion Model for Dense Visual Prediction","created":"2023-03-30","cited_by_count":148},{"id":"1810.02695","title":"Learning Depth with Convolutional Spatial Propagation Network","created":"2018-10-04","cited_by_count":136},{"id":"2207.13751","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","created":"2022-07-27","cited_by_count":136},{"id":"2103.14031","title":"High-Fidelity Pluralistic Image Completion with Transformers","created":"2021-03-25","cited_by_count":134},{"id":"2306.01923","title":"The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation","created":"2023-06-02","cited_by_count":116},{"id":"1808.00150","title":"Depth Estimation via Affinity Learned with Convolutional Spatial Propagation Network","created":"2018-08-01","cited_by_count":110},{"id":"2304.13030","title":"CompletionFormer: Depth Completion with Convolutions and Vision Transformers","created":"2023-04-25","cited_by_count":93},{"id":"2312.07536","title":"FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition","created":"2023-12-12","cited_by_count":91},{"id":"1608.05137","title":"IM2CAD","created":"2016-08-18","cited_by_count":78},{"id":"1604.03650","title":"Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks","created":"2016-04-13","cited_by_count":73},{"id":"2104.06977","title":"Discrete Cosine Transform Network for Guided Depth Map Super-Resolution","created":"2021-04-14","cited_by_count":71},{"id":"2104.06174","title":"Towards Fast and Accurate Real-World Depth Super-Resolution: Benchmark Dataset and Baseline","created":"2021-04-13","cited_by_count":61},{"id":"2310.08956","title":"LRRU: Long-short Range Recurrent Updating Networks for Depth Completion","created":"2023-10-13","cited_by_count":49},{"id":"2211.11592","title":"Guided Depth Super-Resolution by Deep Anisotropic Diffusion","created":"2022-11-21","cited_by_count":46},{"id":"2403.18807","title":"ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation","created":"2024-03-27","cited_by_count":45},{"id":"2407.16698","title":"Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions","created":"2024-07-23","cited_by_count":29},{"id":"2303.08942","title":"Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution","created":"2023-03-15","cited_by_count":28},{"id":"2212.00790","title":"Sparsity Agnostic Depth Completion","created":"2022-12-01","cited_by_count":27},{"id":"2412.18153","title":"DepthLab: From Partial to Complete","created":"2024-12-24","cited_by_count":27},{"id":"2405.11867","title":"Depth Prompting for Sensor-Agnostic Depth Estimation","created":"2024-05-20","cited_by_count":26},{"id":"2204.13635","title":"SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion","created":"2022-04-28","cited_by_count":23},{"id":"2310.06347","title":"JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling","created":"2023-10-10","cited_by_count":23},{"id":"2406.18580","title":"Shedding Light on Large Generative Networks: Estimating Epistemic Uncertainty in Diffusion Models","created":"2024-06-05","cited_by_count":22},{"id":"2408.04718","title":"Zero-Shot Uncertainty Quantification using Diffusion Probabilistic Models","created":"2024-08-08","cited_by_count":14},{"id":"2302.01312","title":"Normalizing Flow Ensembles for Rich Aleatoric and Epistemic Uncertainty Modeling","created":"2023-02-02","cited_by_count":10},{"id":"2404.19294","title":"Masked Spatial Propagation Network for Sparsity-Adaptive Depth Refinement","created":"2024-04-30","cited_by_count":5}],"next_cursor":null}