{"list":"other","total":55,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"1512.03385","title":"Deep Residual Learning for Image Recognition","created":"2015-12-10","cited_by_count":52096},{"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":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1608.03983","title":"SGDR: Stochastic Gradient Descent with Warm Restarts","created":"2016-08-13","cited_by_count":5045},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2105.15203","title":"SegFormer: Simple and Efficient Design for Semantic Segmentation with Transformers","created":"2021-05-31","cited_by_count":2940},{"id":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"1812.03828","title":"Occupancy Networks: Learning 3D Reconstruction in Function Space","created":"2018-12-10","cited_by_count":2041},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2012.02190","title":"pixelNeRF: Neural Radiance Fields from One or Few Images","created":"2020-12-03","cited_by_count":1584},{"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":"2011.00931","title":"Point Transformer","created":"2020-11-02","cited_by_count":1470},{"id":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1903.07291","title":"Semantic Image Synthesis with Spatially-Adaptive Normalization","created":"2019-03-18","cited_by_count":1299},{"id":"1812.02822","title":"Learning Implicit Fields for Generative Shape Modeling","created":"2018-12-06","cited_by_count":1060},{"id":"2010.07492","title":"NeRF++: Analyzing and Improving Neural Radiance Fields","created":"2020-10-15","cited_by_count":861},{"id":"1609.03677","title":"Unsupervised Monocular Depth Estimation with Left-Right Consistency","created":"2016-09-13","cited_by_count":820},{"id":"2103.15595","title":"MVSNeRF: Fast Generalizable Radiance Field Reconstruction from Multi-View Stereo","created":"2021-03-29","cited_by_count":740},{"id":"2012.09688","title":"PCT: Point cloud transformer","created":"2020-12-17","cited_by_count":732},{"id":"2102.13090","title":"IBRNet: Learning Multi-View Image-Based Rendering","created":"2021-02-25","cited_by_count":703},{"id":"2201.08845","title":"Point-NeRF: Point-based Neural Radiance Fields","created":"2022-01-21","cited_by_count":503},{"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":"1906.08240","title":"Neural Point-Based Graphics","created":"2019-06-19","cited_by_count":327},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2004.11364","title":"Single-View View Synthesis with Multiplane Images","created":"2020-04-23","cited_by_count":263},{"id":"1906.07316","title":"DeepView: View Synthesis with Learned Gradient Descent","created":"2019-06-18","cited_by_count":253},{"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":"1904.00830","title":"Depth-Aware Video Frame Interpolation","created":"2019-04-01","cited_by_count":234},{"id":"1705.02894","title":"Geometric GAN","created":"2017-05-08","cited_by_count":233},{"id":"2111.01007","title":"Projected GANs Converge Faster","created":"2021-11-01","cited_by_count":208},{"id":"2004.04727","title":"3D Photography using Context-aware Layered Depth Inpainting","created":"2020-04-09","cited_by_count":206},{"id":"1905.00413","title":"Pushing the Boundaries of View Extrapolation with Multiplane Images","created":"2019-05-01","cited_by_count":191},{"id":"1605.03557","title":"View Synthesis by Appearance Flow","created":"2016-05-11","cited_by_count":172},{"id":"1712.00175","title":"Learning Depth from Monocular Videos using Direct Methods","created":"2017-12-01","cited_by_count":154},{"id":"1904.03375","title":"Modeling Point Clouds with Self-Attention and Gumbel Subset Sampling","created":"2019-04-06","cited_by_count":151},{"id":"1904.04290","title":"Neural Rerendering in the Wild","created":"2019-04-08","cited_by_count":121},{"id":"2112.04702","title":"Fast Point Transformer","created":"2021-12-09","cited_by_count":104},{"id":"1811.02565","title":"Point2Sequence: Learning the Shape Representation of 3D Point Clouds with an Attention-based Sequence to Sequence Network","created":"2018-11-06","cited_by_count":100},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100},{"id":"1807.10264","title":"Layer-structured 3D Scene Inference via View Synthesis","created":"2018-07-26","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":"2207.11148","title":"InfiniteNature-Zero: Learning Perpetual View Generation of Natural Scenes from Single Images","created":"2022-07-22","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":"1708.03292","title":"Learning to Synthesize a 4D RGBD Light Field from a Single Image","created":"2017-08-10","cited_by_count":60},{"id":"1511.06702","title":"Multi-view 3D Models from Single Images with a Convolutional Network","created":"2015-11-20","cited_by_count":58},{"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":"2109.01068","title":"SLIDE: Single Image 3D Photography with Soft Layering and Depth-aware Inpainting","created":"2021-09-02","cited_by_count":48},{"id":"2204.02960","title":"Simple and Effective Synthesis of Indoor 3D Scenes","created":"2022-04-06","cited_by_count":33},{"id":"1904.06458","title":"Transformable Bottleneck Networks","created":"2019-04-13","cited_by_count":23},{"id":"2201.05023","title":"Stereo Magnification with Multi-Layer Images","created":"2022-01-13","cited_by_count":11},{"id":"2101.01619","title":"Novel View Synthesis via Depth-guided Skip Connections","created":"2021-01-05","cited_by_count":5}],"next_cursor":null}