{"list":"other","total":63,"rows":[{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","created":"2014-12-22","cited_by_count":37240},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"1312.6114","title":"Auto-Encoding Variational Bayes","created":"2013-12-20","cited_by_count":4053},{"id":"1512.03012","title":"ShapeNet: An Information-Rich 3D Model Repository","created":"2015-12-09","cited_by_count":2897},{"id":"1603.08155","title":"Perceptual Losses for Real-Time Style Transfer and Super-Resolution","created":"2016-03-27","cited_by_count":2694},{"id":"1704.00028","title":"Improved Training of Wasserstein GANs","created":"2017-03-31","cited_by_count":2235},{"id":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"1906.05797","title":"The Replica Dataset: A Digital Replica of Indoor Spaces","created":"2019-06-13","cited_by_count":904},{"id":"1906.01618","title":"Scene Representation Networks: Continuous 3D-Structure-Aware Neural Scene Representations","created":"2019-06-04","cited_by_count":864},{"id":"1606.03657","title":"InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets","created":"2016-06-12","cited_by_count":860},{"id":"1804.04732","title":"Multimodal Unsupervised Image-to-Image Translation","created":"2018-04-12","cited_by_count":795},{"id":"1704.07813","title":"Unsupervised Learning of Depth and Ego-Motion from Video","created":"2017-04-25","cited_by_count":782},{"id":"1907.10786","title":"Interpreting the Latent Space of GANs for Semantic Face Editing","created":"2019-07-25","cited_by_count":695},{"id":"1802.05983","title":"Disentangling by Factorising","created":"2018-02-16","cited_by_count":616},{"id":"1707.04993","title":"MoCoGAN: Decomposing Motion and Content for Video Generation","created":"2017-07-17","cited_by_count":524},{"id":"1812.01024","title":"DeepVoxels: Learning Persistent 3D Feature Embeddings","created":"2018-12-03","cited_by_count":405},{"id":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"1803.07549","title":"Learning Category-Specific Mesh Reconstruction from Image Collections","created":"2018-03-20","cited_by_count":317},{"id":"2004.03805","title":"State of the Art on Neural Rendering","created":"2020-04-08","cited_by_count":278},{"id":"2004.11364","title":"Single-View View Synthesis with Multiplane Images","created":"2020-04-23","cited_by_count":263},{"id":"1905.01270","title":"DRIT++: Diverse Image-to-Image Translation via Disentangled Representations","created":"2019-05-02","cited_by_count":244},{"id":"2007.00653","title":"Swapping Autoencoder for Deep Image Manipulation","created":"2020-07-01","cited_by_count":215},{"id":"1506.06825","title":"DeepStereo: Learning to Predict New Views from the World's Imagery","created":"2015-06-22","cited_by_count":185},{"id":"1704.06254","title":"Multi-view Supervision for Single-view Reconstruction via Differentiable Ray Consistency","created":"2017-04-20","cited_by_count":177},{"id":"1909.04656","title":"Video Representation Learning by Dense Predictive Coding","created":"2019-09-10","cited_by_count":175},{"id":"1605.03557","title":"View Synthesis by Appearance Flow","created":"2016-05-11","cited_by_count":172},{"id":"1506.02753","title":"Inverting Visual Representations with Convolutional Networks","created":"2015-06-09","cited_by_count":170},{"id":"2004.04467","title":"Adversarial Latent Autoencoders","created":"2020-04-09","cited_by_count":155},{"id":"1705.10915","title":"Unsupervised Learning of Disentangled Representations from Video","created":"2017-05-31","cited_by_count":139},{"id":"1909.05483","title":"3D Ken Burns Effect from a Single Image","created":"2019-09-12","cited_by_count":128},{"id":"1812.02725","title":"Visual Object Networks: Image Generation with Disentangled 3D Representation","created":"2018-12-06","cited_by_count":124},{"id":"1503.03167","title":"Deep Convolutional Inverse Graphics Network","created":"2015-03-11","cited_by_count":121},{"id":"1806.04166","title":"Learning to Decompose and Disentangle Representations for Video Prediction","created":"2018-06-11","cited_by_count":121},{"id":"1806.07823","title":"Unsupervised Learning of Object Landmarks through Conditional Image Generation","created":"2018-06-20","cited_by_count":114},{"id":"1505.01596","title":"Learning to See by Moving","created":"2015-05-07","cited_by_count":102},{"id":"1906.07889","title":"Unsupervised Learning of Object Structure and Dynamics from Videos","created":"2019-06-19","cited_by_count":92},{"id":"2008.10599","title":"The Hessian Penalty: A Weak Prior for Unsupervised Disentanglement","created":"2020-08-24","cited_by_count":92},{"id":"2108.05892","title":"PixelSynth: Generating a 3D-Consistent Experience from a Single Image","created":"2021-08-12","cited_by_count":82},{"id":"2012.09854","title":"Worldsheet: Wrapping the World in a 3D Sheet for View Synthesis from a Single Image","created":"2020-12-17","cited_by_count":77},{"id":"1607.00662","title":"Unsupervised Learning of 3D Structure from Images","created":"2016-07-03","cited_by_count":67},{"id":"2005.13532","title":"4D Visualization of Dynamic Events from Unconstrained Multi-View Videos","created":"2020-05-27","cited_by_count":66},{"id":"1511.06702","title":"Multi-view 3D Models from Single Images with a Convolutional Network","created":"2015-11-20","cited_by_count":58},{"id":"1603.05631","title":"Generative Image Modeling using Style and Structure Adversarial Networks","created":"2016-03-17","cited_by_count":50},{"id":"1804.10469","title":"Disentangling Factors of Variation with Cycle-Consistent Variational Auto-Encoders","created":"2018-04-27","cited_by_count":49},{"id":"1607.02586","title":"Visual Dynamics: Probabilistic Future Frame Synthesis via Cross Convolutional Networks","created":"2016-07-09","cited_by_count":46},{"id":"1808.06882","title":"Self-supervised learning of a facial attribute embedding from video","created":"2018-08-21","cited_by_count":45},{"id":"1505.02206","title":"Learning image representations tied to ego-motion","created":"2015-05-08","cited_by_count":42},{"id":"1511.06811","title":"Learning visual groups from co-occurrences in space and time","created":"2015-11-21","cited_by_count":42},{"id":"2007.07696","title":"P$^{2}$Net: Patch-match and Plane-regularization for Unsupervised Indoor Depth Estimation","created":"2020-07-15","cited_by_count":41},{"id":"2008.02796","title":"Learning to Factorize and Relight a City","created":"2020-08-06","cited_by_count":36},{"id":"1901.00003","title":"Learning Spatial Common Sense with Geometry-Aware Recurrent Networks","created":"2018-12-31","cited_by_count":35},{"id":"1910.08898","title":"Moving Indoor: Unsupervised Video Depth Learning in Challenging Environments","created":"2019-10-20","cited_by_count":31},{"id":"1506.04714","title":"Slow and steady feature analysis: higher order temporal coherence in video","created":"2015-06-15","cited_by_count":28},{"id":"2003.08791","title":"High-Resolution Daytime Translation Without Domain Labels","created":"2020-03-19","cited_by_count":28},{"id":"1411.5928","title":"Learning to Generate Chairs, Tables and Cars with Convolutional Networks","created":"2014-11-21","cited_by_count":26},{"id":"2004.01793","title":"Self-Supervised Viewpoint Learning From Image Collections","created":"2020-04-03","cited_by_count":23},{"id":"1808.10002","title":"Interpretable Intuitive Physics Model","created":"2018-08-29","cited_by_count":19},{"id":"2011.03367","title":"Disentangling 3D Prototypical Networks For Few-Shot Concept Learning","created":"2020-11-06","cited_by_count":15},{"id":"2008.01295","title":"Tracking Emerges by Looking Around Static Scenes, with Neural 3D Mapping","created":"2020-08-04","cited_by_count":6},{"id":"1912.10321","title":"Deep Automodulators","created":"2019-12-21","cited_by_count":4}],"next_cursor":null}