{"list":"other","total":69,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"1505.04597","title":"U-Net: Convolutional Networks for Biomedical Image Segmentation","created":"2015-05-18","cited_by_count":19713},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2103.14030","title":"Swin Transformer: Hierarchical Vision Transformer using Shifted Windows","created":"2021-03-25","cited_by_count":12139},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"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":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"1512.00567","title":"Rethinking the Inception Architecture for Computer Vision","created":"2015-12-02","cited_by_count":5475},{"id":"1907.05600","title":"Generative Modeling by Estimating Gradients of the Data Distribution","created":"2019-07-12","cited_by_count":4101},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2003.12039","title":"RAFT: Recurrent All-Pairs Field Transforms for Optical Flow","created":"2020-03-26","cited_by_count":2415},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"1711.07971","title":"Non-local Neural Networks","created":"2017-11-21","cited_by_count":2293},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"id":"2209.14792","title":"Make-A-Video: Text-to-Video Generation without Text-Video Data","created":"2022-09-29","cited_by_count":1742},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"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":"1709.06158","title":"Matterport3D: Learning from RGB-D Data in Indoor Environments","created":"2017-09-18","cited_by_count":1376},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"1904.01201","title":"Habitat: A Platform for Embodied AI Research","created":"2019-04-02","cited_by_count":1191},{"id":"2106.15282","title":"Cascaded Diffusion Models for High Fidelity Image Generation","created":"2021-05-30","cited_by_count":1163},{"id":"2107.10833","title":"Real-ESRGAN: Training Real-World Blind Super-Resolution with Pure Synthetic Data","created":"2021-07-22","cited_by_count":970},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2010.07492","title":"NeRF++: Analyzing and Improving Neural Radiance Fields","created":"2020-10-15","cited_by_count":861},{"id":"1805.08318","title":"Self-Attention Generative Adversarial Networks","created":"2018-05-21","cited_by_count":809},{"id":"2202.05263","title":"Block-NeRF: Scalable Large Scene Neural View Synthesis","created":"2022-02-10","cited_by_count":724},{"id":"1905.00889","title":"Local Light Field Fusion: Practical View Synthesis with Prescriptive Sampling Guidelines","created":"2019-05-02","cited_by_count":672},{"id":"2104.03670","title":"3D Shape Generation and Completion through Point-Voxel Diffusion","created":"2021-04-08","cited_by_count":516},{"id":"2104.14951","title":"SRDiff: Single Image Super-Resolution with Diffusion Probabilistic Models","created":"2021-04-30","cited_by_count":415},{"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":"2205.09853","title":"MCVD: Masked Conditional Video Diffusion for Prediction, Generation, and Interpolation","created":"2022-05-19","cited_by_count":309},{"id":"2205.02833","title":"Cross-view Transformers for real-time Map-view Semantic Segmentation","created":"2022-05-05","cited_by_count":264},{"id":"2004.11364","title":"Single-View View Synthesis with Multiplane Images","created":"2020-04-23","cited_by_count":263},{"id":"1808.00449","title":"Learning Blind Video Temporal Consistency","created":"2018-08-01","cited_by_count":253},{"id":"1906.07316","title":"DeepView: View Synthesis with Learned Gradient Descent","created":"2019-06-18","cited_by_count":253},{"id":"2112.02475","title":"Deblurring via Stochastic Refinement","created":"2021-12-05","cited_by_count":249},{"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":"1805.09817","title":"Stereo Magnification: Learning View Synthesis using Multiplane Images","created":"2018-05-24","cited_by_count":211},{"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":"1506.06825","title":"DeepStereo: Learning to Predict New Views from the World's Imagery","created":"2015-06-22","cited_by_count":185},{"id":"1605.03557","title":"View Synthesis by Appearance Flow","created":"2016-05-11","cited_by_count":172},{"id":"2202.04901","title":"FILM: Frame Interpolation for Large Motion","created":"2022-02-10","cited_by_count":153},{"id":"2207.13751","title":"GAUDI: A Neural Architect for Immersive 3D Scene Generation","created":"2022-07-27","cited_by_count":136},{"id":"2111.12704","title":"Investigating Tradeoffs in Real-World Video Super-Resolution","created":"2021-11-24","cited_by_count":134},{"id":"1909.05483","title":"3D Ken Burns Effect from a Single Image","created":"2019-09-12","cited_by_count":128},{"id":"1904.04290","title":"Neural Rerendering in the Wild","created":"2019-04-08","cited_by_count":121},{"id":"2303.13791","title":"Progressively Optimized Local Radiance Fields for Robust View Synthesis","created":"2023-03-24","cited_by_count":103},{"id":"2104.07652","title":"Geometry-Free View Synthesis: Transformers and no 3D Priors","created":"2021-04-15","cited_by_count":100},{"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":"1708.03292","title":"Learning to Synthesize a 4D RGBD Light Field from a Single Image","created":"2017-08-10","cited_by_count":60},{"id":"1703.02921","title":"Transformation-Grounded Image Generation Network for Novel 3D View Synthesis","created":"2017-03-08","cited_by_count":59},{"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":"2008.12298","title":"One Shot 3D Photography","created":"2020-08-27","cited_by_count":45},{"id":"2110.02951","title":"Video Autoencoder: self-supervised disentanglement of static 3D structure and motion","created":"2021-10-06","cited_by_count":34},{"id":"2207.11192","title":"Progressive Deblurring of Diffusion Models for Coarse-to-Fine Image Synthesis","created":"2022-07-16","cited_by_count":34},{"id":"2204.02960","title":"Simple and Effective Synthesis of Indoor 3D Scenes","created":"2022-04-06","cited_by_count":33},{"id":"2008.10598","title":"Semantic View Synthesis","created":"2020-08-24","cited_by_count":18},{"id":"2111.04639","title":"S3RP: Self-Supervised Super-Resolution and Prediction for Advection-Diffusion Process","created":"2021-11-08","cited_by_count":9}],"next_cursor":null}