{"list":"other","total":59,"rows":[{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1711.00937","title":"Neural Discrete Representation Learning","created":"2017-11-02","cited_by_count":4712},{"id":"1611.07004","title":"Image-to-Image Translation with Conditional Adversarial Networks","created":"2016-11-21","cited_by_count":4527},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2007.14062","title":"Big Bird: Transformers for Longer Sequences","created":"2020-07-28","cited_by_count":1684},{"id":"2203.17270","title":"BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformers","created":"2022-03-31","cited_by_count":1218},{"id":"2202.04200","title":"MaskGIT: Masked Generative Image Transformer","created":"2022-02-08","cited_by_count":1099},{"id":"2008.05711","title":"Lift, Splat, Shoot: Encoding Images From Arbitrary Camera Rigs by Implicitly Unprojecting to 3D","created":"2020-08-13","cited_by_count":1044},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"1606.05328","title":"Conditional Image Generation with PixelCNN Decoders","created":"2016-06-16","cited_by_count":862},{"id":"1601.06759","title":"Pixel Recurrent Neural Networks","created":"2016-01-25","cited_by_count":816},{"id":"1605.05396","title":"Generative Adversarial Text to Image Synthesis","created":"2016-05-17","cited_by_count":735},{"id":"1911.02620","title":"Argoverse: 3D Tracking and Forecasting with Rich Maps","created":"2019-11-06","cited_by_count":732},{"id":"1703.10593","title":"Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks","created":"2017-03-30","cited_by_count":707},{"id":"2301.00493","title":"Argoverse 2: Next Generation Datasets for Self-Driving Perception and Forecasting","created":"2023-01-02","cited_by_count":707},{"id":"2105.13290","title":"CogView: Mastering Text-to-Image Generation via Transformers","created":"2021-05-26","cited_by_count":694},{"id":"1909.11065","title":"Segmentation Transformer: Object-Contextual Representations for Semantic Segmentation","created":"2019-09-24","cited_by_count":576},{"id":"2203.13131","title":"Make-A-Scene: Scene-Based Text-to-Image Generation with Human Priors","created":"2022-03-24","cited_by_count":487},{"id":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"1804.01622","title":"Image Generation from Scene Graphs","created":"2018-04-04","cited_by_count":324},{"id":"2109.12674","title":"MetaDrive: Composing Diverse Driving Scenarios for Generalizable Reinforcement Learning","created":"2021-09-26","cited_by_count":290},{"id":"2205.02833","title":"Cross-view Transformers for real-time Map-view Semantic Segmentation","created":"2022-05-05","cited_by_count":264},{"id":"2104.10490","title":"FIERY: Future Instance Prediction in Bird's-Eye View from Surround Monocular Cameras","created":"2021-04-21","cited_by_count":239},{"id":"2207.02202","title":"CoBEVT: Cooperative Bird's Eye View Semantic Segmentation with Sparse Transformers","created":"2022-07-05","cited_by_count":227},{"id":"2205.09743","title":"BEVerse: Unified Perception and Prediction in Birds-Eye-View for Vision-Centric Autonomous Driving","created":"2022-05-19","cited_by_count":191},{"id":"2002.08988","title":"BlockGAN: Learning 3D Object-aware Scene Representations from Unlabelled Images","created":"2020-02-20","cited_by_count":166},{"id":"2104.15060","title":"DriveGAN: Towards a Controllable High-Quality Neural Simulation","created":"2021-04-30","cited_by_count":125},{"id":"2103.06818","title":"Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization","created":"2021-03-11","cited_by_count":113},{"id":"2210.06609","title":"TrafficGen: Learning to Generate Diverse and Realistic Traffic Scenarios","created":"2022-10-12","cited_by_count":106},{"id":"1801.05091","title":"Inferring Semantic Layout for Hierarchical Text-to-Image Synthesis","created":"2018-01-16","cited_by_count":101},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100},{"id":"1612.02709","title":"Predicting Ground-Level Scene Layout from Aerial Imagery","created":"2016-12-08","cited_by_count":90},{"id":"2004.03677","title":"Semantic Image Manipulation Using Scene Graphs","created":"2020-04-07","cited_by_count":82},{"id":"2108.05892","title":"PixelSynth: Generating a 3D-Consistent Experience from a Single Image","created":"2021-08-12","cited_by_count":82},{"id":"1704.03952","title":"Virtual to Real Reinforcement Learning for Autonomous Driving","created":"2017-04-13","cited_by_count":80},{"id":"1812.01608","title":"Generating High Fidelity Images with Subscale Pixel Networks and Multidimensional Upscaling","created":"2018-12-04","cited_by_count":74},{"id":"1803.03396","title":"Cross-View Image Synthesis using Conditional GANs","created":"2018-03-09","cited_by_count":69},{"id":"2007.08509","title":"World-Consistent Video-to-Video Synthesis","created":"2020-07-16","cited_by_count":69},{"id":"1704.08292","title":"Deep Cross-Modal Audio-Visual Generation","created":"2017-04-26","cited_by_count":63},{"id":"2203.09457","title":"Look Outside the Room: Synthesizing A Consistent Long-Term 3D Scene Video from A Single Image","created":"2022-03-17","cited_by_count":55},{"id":"2103.12474","title":"On Exposing the Challenging Long Tail in Future Prediction of Traffic Actors","created":"2021-03-23","cited_by_count":48},{"id":"2108.03227","title":"Bird's-Eye-View Panoptic Segmentation Using Monocular Frontal View Images","created":"2021-08-06","cited_by_count":48},{"id":"2203.13641","title":"StretchBEV: Stretching Future Instance Prediction Spatially and Temporally","created":"2022-03-25","cited_by_count":47},{"id":"2203.14668","title":"Diverse Plausible 360-Degree Image Outpainting for Efficient 3DCG Background Creation","created":"2022-03-28","cited_by_count":47},{"id":"2103.01623","title":"Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery","created":"2021-03-02","cited_by_count":41},{"id":"2205.02837","title":"BlobGAN: Spatially Disentangled Scene Representations","created":"2022-05-05","cited_by_count":35},{"id":"1808.08483","title":"Painting Outside the Box: Image Outpainting with GANs","created":"2018-08-25","cited_by_count":30},{"id":"2102.05897","title":"Corner Cases for Visual Perception in Automated Driving: Some Guidance on Detection Approaches","created":"2021-02-11","cited_by_count":27},{"id":"2012.06628","title":"Sat2Vid: Street-view Panoramic Video Synthesis from a Single Satellite Image","created":"2020-12-11","cited_by_count":25},{"id":"2204.07733","title":"GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation","created":"2022-04-16","cited_by_count":24},{"id":"1901.03762","title":"Using Scene Graph Context to Improve Image Generation","created":"2019-01-11","cited_by_count":12},{"id":"1912.10960","title":"Image Outpainting and Harmonization using Generative Adversarial Networks","created":"2019-12-23","cited_by_count":12},{"id":"2004.03413","title":"Direct Speech-to-image Translation","created":"2020-04-07","cited_by_count":12},{"id":"2205.02958","title":"Scene Graph Expansion for Semantics-Guided Image Outpainting","created":"2022-05-05","cited_by_count":11},{"id":"2205.15667","title":"ViT-BEVSeg: A Hierarchical Transformer Network for Monocular Birds-Eye-View Segmentation","created":"2022-05-31","cited_by_count":7}],"next_cursor":null}