{"list":"other","total":89,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1612.00593","title":"PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation","created":"2016-12-02","cited_by_count":5248},{"id":"1903.11027","title":"nuScenes: A multimodal dataset for autonomous driving","created":"2019-03-26","cited_by_count":4523},{"id":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"1802.02611","title":"Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation","created":"2018-02-07","cited_by_count":3223},{"id":"1803.10122","title":"World Models","created":"2018-03-27","cited_by_count":1513},{"id":"1604.07379","title":"Context Encoders: Feature Learning by Inpainting","created":"2016-04-25","cited_by_count":1428},{"id":"1805.04687","title":"BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning","created":"2018-05-12","cited_by_count":1288},{"id":"1811.04551","title":"Learning Latent Dynamics for Planning from Pixels","created":"2018-11-12","cited_by_count":1264},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"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":"2010.02193","title":"Mastering Atari with Discrete World Models","created":"2020-10-05","cited_by_count":1007},{"id":"1710.02298","title":"Rainbow: Combining Improvements in Deep Reinforcement Learning","created":"2017-10-06","cited_by_count":786},{"id":"2110.06922","title":"DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queries","created":"2021-10-13","cited_by_count":658},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1806.03589","title":"Free-Form Image Inpainting with Gated Convolution","created":"2018-06-10","cited_by_count":594},{"id":"1801.07892","title":"Generative Image Inpainting with Contextual Attention","created":"2018-01-24","cited_by_count":580},{"id":"2109.13410","title":"KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D","created":"2021-09-28","cited_by_count":575},{"id":"1804.07723","title":"Image Inpainting for Irregular Holes Using Partial Convolutions","created":"2018-04-20","cited_by_count":505},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"1812.07179","title":"Pseudo-LiDAR from Visual Depth Estimation: Bridging the Gap in 3D Object Detection for Autonomous Driving","created":"2018-12-18","cited_by_count":457},{"id":"1905.02693","title":"3D Packing for Self-Supervised Monocular Depth Estimation","created":"2019-05-06","cited_by_count":439},{"id":"1701.05517","title":"PixelCNN++: Improving the PixelCNN with Discretized Logistic Mixture Likelihood and Other Modifications","created":"2017-01-19","cited_by_count":417},{"id":"1901.11390","title":"MONet: Unsupervised Scene Decomposition and Representation","created":"2019-01-22","cited_by_count":392},{"id":"1806.06923","title":"Implicit Quantile Networks for Distributional Reinforcement Learning","created":"2018-06-14","cited_by_count":369},{"id":"1703.04309","title":"End-to-End Learning of Geometry and Context for Deep Stereo Regression","created":"2017-03-13","cited_by_count":360},{"id":"2111.13679","title":"NeRF in the Dark: High Dynamic Range View Synthesis from Noisy Raw Images","created":"2021-11-26","cited_by_count":336},{"id":"2103.01100","title":"Categorical Depth Distribution Network for Monocular 3D Object Detection","created":"2021-03-01","cited_by_count":327},{"id":"1602.02282","title":"Ladder Variational Autoencoders","created":"2016-02-06","cited_by_count":318},{"id":"2011.10379","title":"Neural Scene Graphs for Dynamic Scenes","created":"2020-11-20","cited_by_count":298},{"id":"2107.06307","title":"HDMapNet: An Online HD Map Construction and Evaluation Framework","created":"2021-07-13","cited_by_count":281},{"id":"2011.10650","title":"Very Deep VAEs Generalize Autoregressive Models and Can Outperform Them on Images","created":"2020-11-20","cited_by_count":264},{"id":"2111.14643","title":"Urban Radiance Fields","created":"2021-11-29","cited_by_count":263},{"id":"1604.07446","title":"A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehicles","created":"2016-04-25","cited_by_count":254},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"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":"1710.11252","title":"Stochastic Variational Video Prediction","created":"2017-10-30","cited_by_count":234},{"id":"2101.06806","title":"MP3: A Unified Model to Map, Perceive, Predict and Plan","created":"2021-01-18","cited_by_count":212},{"id":"1911.12247","title":"Contrastive Learning of Structured World Models","created":"2019-11-27","cited_by_count":209},{"id":"1605.08104","title":"Deep Predictive Coding Networks for Video Prediction and Unsupervised Learning","created":"2016-05-25","cited_by_count":204},{"id":"1811.08188","title":"Orthographic Feature Transform for Monocular 3D Object Detection","created":"2018-11-20","cited_by_count":202},{"id":"2004.09548","title":"AANet: Adaptive Aggregation Network for Efficient Stereo Matching","created":"2020-04-20","cited_by_count":202},{"id":"1803.06184","title":"The ApolloScape Open Dataset for Autonomous Driving and its Application","created":"2018-03-16","cited_by_count":190},{"id":"1906.06310","title":"Pseudo-LiDAR++: Accurate Depth for 3D Object Detection in Autonomous Driving","created":"2019-06-14","cited_by_count":188},{"id":"2003.13402","title":"Predicting Semantic Map Representations from Images using Pyramid Occupancy Networks","created":"2020-03-30","cited_by_count":175},{"id":"2109.04456","title":"NEAT: Neural Attention Fields for End-to-End Autonomous Driving","created":"2021-09-09","cited_by_count":174},{"id":"1903.04227","title":"Pluralistic Image Completion","created":"2019-03-11","cited_by_count":162},{"id":"1607.07539","title":"Semantic Image Inpainting with Deep Generative Models","created":"2016-07-26","cited_by_count":157},{"id":"1807.03653","title":"Handling Incomplete Heterogeneous Data using VAEs","created":"2018-07-10","cited_by_count":149},{"id":"2002.12319","title":"Semantically-Guided Representation Learning for Self-Supervised Monocular Depth","created":"2020-02-27","cited_by_count":134},{"id":"2209.15397","title":"KISS-ICP: In Defense of Point-to-Point ICP -- Simple, Accurate, and Robust Registration If Done the Right Way","created":"2022-09-30","cited_by_count":132},{"id":"2002.12655","title":"A U-Net Based Discriminator for Generative Adversarial Networks","created":"2020-02-28","cited_by_count":128},{"id":"2103.10022","title":"Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE","created":"2021-03-18","cited_by_count":106},{"id":"1706.01433","title":"Visual Interaction Networks","created":"2017-06-05","cited_by_count":95},{"id":"1907.00182","title":"Continual Learning for Robotics: Definition, Framework, Learning Strategies, Opportunities and Challenges","created":"2019-06-29","cited_by_count":93},{"id":"1511.02386","title":"Hierarchical Variational Models","created":"2015-11-07","cited_by_count":89},{"id":"1807.08865","title":"StereoNet: Guided Hierarchical Refinement for Real-Time Edge-Aware Depth Prediction","created":"2018-07-24","cited_by_count":88},{"id":"1809.11142","title":"EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAE","created":"2018-09-28","cited_by_count":87},{"id":"1804.02176","title":"Monocular Semantic Occupancy Grid Mapping with Convolutional Variational Encoder-Decoder Networks","created":"2018-04-06","cited_by_count":84},{"id":"2004.03080","title":"End-to-End Pseudo-LiDAR for Image-Based 3D Object Detection","created":"2020-04-07","cited_by_count":80},{"id":"2005.04078","title":"A Sim2Real Deep Learning Approach for the Transformation of Images from Multiple Vehicle-Mounted Cameras to a Semantically Segmented Image in Bird's Eye View","created":"2020-05-08","cited_by_count":72},{"id":"1806.02382","title":"Variational Autoencoder with Arbitrary Conditioning","created":"2018-06-06","cited_by_count":68},{"id":"2007.07627","title":"Fast and Robust Iterative Closest Point","created":"2020-07-15","cited_by_count":67},{"id":"2006.11941","title":"VAEM: a Deep Generative Model for Heterogeneous Mixed Type Data","created":"2020-06-21","cited_by_count":66},{"id":"1807.09341","title":"Learning Plannable Representations with Causal InfoGAN","created":"2018-07-24","cited_by_count":57},{"id":"1905.09275","title":"COBRA: Data-Efficient Model-Based RL through Unsupervised Object Discovery and Curiosity-Driven Exploration","created":"2019-05-22","cited_by_count":57},{"id":"2006.09917","title":"FISHING Net: Future Inference of Semantic Heatmaps In Grids","created":"2020-06-17","cited_by_count":55},{"id":"2002.08394","title":"MonoLayout: Amodal scene layout from a single image","created":"2020-02-19","cited_by_count":49},{"id":"1905.04411","title":"Learning Robotic Manipulation through Visual Planning and Acting","created":"2019-05-11","cited_by_count":41},{"id":"2103.16690","title":"Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion","created":"2021-03-30","cited_by_count":39},{"id":"1702.02779","title":"On-the-Fly Adaptation of Regression Forests for Online Camera Relocalisation","created":"2017-02-09","cited_by_count":38},{"id":"1803.10870","title":"Learning to Look around Objects for Top-View Representations of Outdoor Scenes","created":"2018-03-28","cited_by_count":37},{"id":"1909.06319","title":"Flow Models for Arbitrary Conditional Likelihoods","created":"2019-09-13","cited_by_count":30},{"id":"2006.05301","title":"VAEs in the Presence of Missing Data","created":"2020-06-09","cited_by_count":30},{"id":"2003.06129","title":"LIBRE: The Multiple 3D LiDAR Dataset","created":"2020-03-13","cited_by_count":26},{"id":"2102.04426","title":"Arbitrary Conditional Distributions with Energy","created":"2021-02-08","cited_by_count":22},{"id":"2011.07464","title":"Predictive Coding, Variational Autoencoders, and Biological Connections","created":"2020-11-15","cited_by_count":21},{"id":"1802.04325","title":"Efficient Model-Based Deep Reinforcement Learning with Variational State Tabulation","created":"2018-02-12","cited_by_count":20},{"id":"2202.04599","title":"Missing Data Imputation and Acquisition with Deep Hierarchical Models and Hamiltonian Monte Carlo","created":"2022-02-09","cited_by_count":19},{"id":"1912.01834","title":"PiiGAN: Generative Adversarial Networks for Pluralistic Image Inpainting","created":"2019-12-04","cited_by_count":17},{"id":"1807.01521","title":"Curiosity Driven Exploration of Learned Disentangled Goal Spaces","created":"2018-07-04","cited_by_count":16},{"id":"1304.3111","title":"Estimating Uncertain Spatial Relationships in Robotics","created":"2013-03-27","cited_by_count":14},{"id":"2106.12994","title":"SGTBN: Generating Dense Depth Maps from Single-Line LiDAR","created":"2021-06-24","cited_by_count":6},{"id":"2201.12414","title":"Posterior Matching for Arbitrary Conditioning","created":"2022-01-28","cited_by_count":4},{"id":"2002.11477","title":"Learning a Directional Soft Lane Affordance Model for Road Scenes Using Self-Supervision","created":"2020-02-17","cited_by_count":3},{"id":"2107.01784","title":"Learning a Model for Inferring a Spatial Road Lane Network Graph using Self-Supervision","created":"2021-07-05","cited_by_count":2}],"next_cursor":null}