{"list":"other","total":66,"rows":[{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"1905.11946","title":"EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks","created":"2019-05-28","cited_by_count":6442},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1912.04838","title":"Scalability in Perception for Autonomous Driving: Waymo Open Dataset","created":"2019-12-10","cited_by_count":2451},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2303.01469","title":"Consistency Models","created":"2023-03-02","cited_by_count":1822},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"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":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"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":"1603.08511","title":"Colorful Image Colorization","created":"2016-03-28","cited_by_count":1114},{"id":"1504.06852","title":"FlowNet: Learning Optical Flow with Convolutional Networks","created":"2015-04-26","cited_by_count":1059},{"id":"1709.02371","title":"PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume","created":"2017-09-07","cited_by_count":968},{"id":"1512.02134","title":"A Large Dataset to Train Convolutional Networks for Disparity, Optical Flow, and Scene Flow Estimation","created":"2015-12-07","cited_by_count":881},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"1612.01925","title":"FlowNet 2.0: Evolution of Optical Flow Estimation with Deep Networks","created":"2016-12-06","cited_by_count":784},{"id":"2210.03142","title":"On Distillation of Guided Diffusion Models","created":"2022-10-06","cited_by_count":725},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"2107.14795","title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","created":"2021-07-30","cited_by_count":629},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"1511.06732","title":"Sequence Level Training with Recurrent Neural Networks","created":"2015-11-20","cited_by_count":576},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1411.4734","title":"Predicting Depth, Surface Normals and Semantic Labels with a Common Multi-Scale Convolutional Architecture","created":"2014-11-18","cited_by_count":483},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"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":"2203.03570","title":"Kubric: A scalable dataset generator","created":"2022-03-07","cited_by_count":381},{"id":"1609.05473","title":"SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient","created":"2016-09-18","cited_by_count":376},{"id":"2208.04202","title":"Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning","created":"2022-08-08","cited_by_count":373},{"id":"1603.04992","title":"Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescue","created":"2016-03-16","cited_by_count":368},{"id":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"2111.13680","title":"GMFlow: Learning Optical Flow via Global Matching","created":"2021-11-26","cited_by_count":327},{"id":"2203.16194","title":"FlowFormer: A Transformer Architecture for Optical Flow","created":"2022-03-30","cited_by_count":275},{"id":"1603.06668","title":"Learning Representations for Automatic Colorization","created":"2016-03-22","cited_by_count":251},{"id":"2012.09855","title":"Infinite Nature: Perpetual View Generation of Natural Scenes from a Single Image","created":"2020-12-17","cited_by_count":243},{"id":"2212.06909","title":"Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting","created":"2022-12-13","cited_by_count":233},{"id":"1610.09038","title":"Professor Forcing: A New Algorithm for Training Recurrent Networks","created":"2016-10-27","cited_by_count":216},{"id":"2004.04727","title":"3D Photography using Context-aware Layered Depth Inpainting","created":"2020-04-09","cited_by_count":206},{"id":"1709.07322","title":"Playing for Benchmarks","created":"2017-09-21","cited_by_count":169},{"id":"2204.00987","title":"BinsFormer: Revisiting Adaptive Bins for Monocular Depth Estimation","created":"2022-04-03","cited_by_count":168},{"id":"1904.05290","title":"Iterative Residual Refinement for Joint Optical Flow and Occlusion Estimation","created":"2019-04-10","cited_by_count":131},{"id":"2205.13543","title":"Revealing the Dark Secrets of Masked Image Modeling","created":"2022-05-26","cited_by_count":117},{"id":"2104.14544","title":"AutoFlow: Learning a Better Training Set for Optical Flow","created":"2021-04-29","cited_by_count":102},{"id":"2112.06749","title":"Step-unrolled Denoising Autoencoders for Text Generation","created":"2021-12-13","cited_by_count":102},{"id":"2210.06366","title":"A Generalist Framework for Panoptic Segmentation of Images and Videos","created":"2022-10-12","cited_by_count":99},{"id":"2210.09071","title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention","created":"2022-10-17","cited_by_count":93},{"id":"1605.02305","title":"Estimating Depth from Monocular Images as Classification Using Deep Fully Convolutional Residual Networks","created":"2016-05-08","cited_by_count":91},{"id":"2203.16896","title":"CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow","created":"2022-03-31","cited_by_count":82},{"id":"1711.09082","title":"Cross-Domain Self-supervised Multi-task Feature Learning using Synthetic Imagery","created":"2017-11-24","cited_by_count":56},{"id":"2205.14623","title":"SKFlow: Learning Optical Flow with Super Kernels","created":"2022-05-29","cited_by_count":56},{"id":"2301.02229","title":"All in Tokens: Unifying Output Space of Visual Tasks via Soft Token","created":"2023-01-05","cited_by_count":52},{"id":"2110.04722","title":"Transformer-based Dual Relation Graph for Multi-label Image Recognition","created":"2021-10-10","cited_by_count":41},{"id":"1804.04259","title":"Learning Rigidity in Dynamic Scenes with a Moving Camera for 3D Motion Field Estimation","created":"2018-04-12","cited_by_count":38},{"id":"2202.03857","title":"Learning Optical Flow with Adaptive Graph Reasoning","created":"2022-02-08","cited_by_count":33},{"id":"2203.10712","title":"Disentangling Architecture and Training for Optical Flow","created":"2022-03-21","cited_by_count":32},{"id":"1511.07041","title":"SceneNet: Understanding Real World Indoor Scenes With Synthetic Data","created":"2015-11-22","cited_by_count":29},{"id":"2204.07262","title":"Imposing Consistency for Optical Flow Estimation","created":"2022-04-14","cited_by_count":24},{"id":"1708.05355","title":"MirrorFlow: Exploiting Symmetries in Joint Optical Flow and Occlusion Estimation","created":"2017-08-17","cited_by_count":21},{"id":"2006.10172","title":"Sky Optimization: Semantically aware image processing of skies in low-light photography","created":"2020-06-15","cited_by_count":9}],"next_cursor":null}