{"list":"other","total":59,"rows":[{"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":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"1812.04948","title":"A Style-Based Generator Architecture for Generative Adversarial Networks","created":"2018-12-12","cited_by_count":6013},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2203.00667","title":"Generative Adversarial Networks","created":"2022-03-01","cited_by_count":5627},{"id":"1912.04958","title":"Analyzing and Improving the Image Quality of StyleGAN","created":"2019-12-03","cited_by_count":3588},{"id":"1901.05103","title":"DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation","created":"2019-01-16","cited_by_count":2689},{"id":"2006.09661","title":"Implicit Neural Representations with Periodic Activation Functions","created":"2020-06-17","cited_by_count":2238},{"id":"1705.06950","title":"The Kinetics Human Action Video Dataset","created":"2017-05-19","cited_by_count":1909},{"id":"1812.01717","title":"Towards Accurate Generative Models of Video: A New Metric & Challenges","created":"2018-12-03","cited_by_count":1234},{"id":"2205.15868","title":"CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers","created":"2022-05-29","cited_by_count":985},{"id":"1506.03099","title":"Scheduled Sampling for Sequence Prediction with Recurrent Neural Networks","created":"2015-06-09","cited_by_count":803},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2304.06706","title":"Zip-NeRF: Anti-Aliased Grid-Based Neural Radiance Fields","created":"2023-04-13","cited_by_count":671},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2012.09161","title":"Learning Continuous Image Representation with Local Implicit Image Function","created":"2020-12-16","cited_by_count":552},{"id":"2212.05199","title":"MAGVIT: Masked Generative Video Transformer","created":"2022-12-10","cited_by_count":346},{"id":"2406.07550","title":"An Image is Worth 32 Tokens for Reconstruction and Generation","created":"2024-06-11","cited_by_count":302},{"id":"2211.16677","title":"3D Neural Field Generation using Triplane Diffusion","created":"2022-11-30","cited_by_count":274},{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256},{"id":"2303.09556","title":"Efficient Diffusion Training via Min-SNR Weighting Strategy","created":"2023-03-16","cited_by_count":246},{"id":"2204.03638","title":"Long Video Generation with Time-Agnostic VQGAN and Time-Sensitive Transformer","created":"2022-04-07","cited_by_count":244},{"id":"2103.03123","title":"COIN: COmpression with Implicit Neural representations","created":"2021-03-03","cited_by_count":233},{"id":"2205.04978","title":"NeRF-Editing: Geometry Editing of Neural Radiance Fields","created":"2022-05-10","cited_by_count":217},{"id":"2212.01206","title":"DiffRF: Rendering-Guided 3D Radiance Field Diffusion","created":"2022-12-02","cited_by_count":204},{"id":"2202.10571","title":"Generating Videos with Dynamics-aware Implicit Generative Adversarial Networks","created":"2022-02-21","cited_by_count":186},{"id":"2304.06714","title":"Single-Stage Diffusion NeRF: A Unified Approach to 3D Generation and Reconstruction","created":"2023-04-13","cited_by_count":180},{"id":"2112.04267","title":"Implicit Neural Representations for Image Compression","created":"2021-12-08","cited_by_count":162},{"id":"2303.17015","title":"HyperDiffusion: Generating Implicit Neural Fields with Weight-Space Diffusion","created":"2023-03-29","cited_by_count":152},{"id":"2011.12026","title":"Adversarial Generation of Continuous Images","created":"2020-11-24","cited_by_count":135},{"id":"2406.09399","title":"OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation","created":"2024-06-13","cited_by_count":118},{"id":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108},{"id":"2206.04647","title":"VideoINR: Learning Video Implicit Neural Representation for Continuous Space-Time Super-Resolution","created":"2022-06-09","cited_by_count":101},{"id":"2308.15321","title":"Elucidating the Exposure Bias in Diffusion Models","created":"2023-08-29","cited_by_count":101},{"id":"2303.11722","title":"Implicit Neural Representation for Cooperative Low-light Image Enhancement","created":"2023-03-21","cited_by_count":92},{"id":"2209.12892","title":"Learning to Learn with Generative Models of Neural Network Checkpoints","created":"2022-09-26","cited_by_count":86},{"id":"2201.12904","title":"COIN++: Neural Compression Across Modalities","created":"2022-01-30","cited_by_count":82},{"id":"2507.23268","title":"PixNerd: Pixel Neural Field Diffusion","created":"2025-07-31","cited_by_count":82},{"id":"2208.02801","title":"Transformers as Meta-Learners for Implicit Neural Representations","created":"2022-08-04","cited_by_count":79},{"id":"2207.08132","title":"E-NeRV: Expedite Neural Video Representation with Disentangled Spatial-Temporal Context","created":"2022-07-17","cited_by_count":76},{"id":"2306.09818","title":"HiNeRV: Video Compression with Hierarchical Encoding-based Neural Representation","created":"2023-06-16","cited_by_count":71},{"id":"2204.01943","title":"Unified Implicit Neural Stylization","created":"2022-04-05","cited_by_count":67},{"id":"2103.03243","title":"Anycost GANs for Interactive Image Synthesis and Editing","created":"2021-03-04","cited_by_count":54},{"id":"2112.11312","title":"Implicit Neural Video Compression","created":"2021-12-21","cited_by_count":52},{"id":"2411.06449","title":"Improved Video VAE for Latent Video Diffusion Model","created":"2024-11-10","cited_by_count":48},{"id":"2212.12294","title":"FFNeRV: Flow-Guided Frame-Wise Neural Representations for Videos","created":"2022-12-23","cited_by_count":46},{"id":"2410.21264","title":"LARP: Tokenizing Videos with a Learned Autoregressive Generative Prior","created":"2024-10-28","cited_by_count":46},{"id":"2304.06544","title":"DNeRV: Modeling Inherent Dynamics via Difference Neural Representation for Videos","created":"2023-04-13","cited_by_count":42},{"id":"2211.13223","title":"Generalizable Implicit Neural Representations via Instance Pattern Composers","created":"2022-11-23","cited_by_count":39},{"id":"2212.02802","title":"Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding","created":"2022-12-06","cited_by_count":39},{"id":"2412.05796","title":"Language-Guided Image Tokenization for Generation","created":"2024-12-08","cited_by_count":36},{"id":"2406.07480","title":"Image Neural Field Diffusion Models","created":"2024-06-11","cited_by_count":13},{"id":"2404.02788","title":"GenN2N: Generative NeRF2NeRF Translation","created":"2024-04-03","cited_by_count":11},{"id":"2409.19429","title":"Fast Encoding and Decoding for Implicit Video Representation","created":"2024-09-28","cited_by_count":11},{"id":"2412.03791","title":"INRFlow: Flow Matching for INRs in Ambient Space","created":"2024-12-05","cited_by_count":2},{"id":"2507.22404","title":"MINR: Implicit Neural Representations with Masked Image Modelling","created":"2025-07-30","cited_by_count":1}],"next_cursor":null}