{"list":"other","total":51,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"1409.1556","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","created":"2014-09-04","cited_by_count":15364},{"id":"2106.09685","title":"LoRA: Low-Rank Adaptation of Large Language Models","created":"2021-06-17","cited_by_count":14380},{"id":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2208.12242","title":"DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation","created":"2022-08-25","cited_by_count":3300},{"id":"2104.08718","title":"CLIPScore: A Reference-free Evaluation Metric for Image Captioning","created":"2021-04-18","cited_by_count":2424},{"id":"2111.12077","title":"Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields","created":"2021-11-23","cited_by_count":2032},{"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":"2304.08818","title":"Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models","created":"2023-04-18","cited_by_count":1476},{"id":"2011.13961","title":"D-NeRF: Neural Radiance Fields for Dynamic Scenes","created":"2020-11-27","cited_by_count":1465},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"2212.11565","title":"Tune-A-Video: One-Shot Tuning of Image Diffusion Models for Text-to-Video Generation","created":"2022-12-22","cited_by_count":961},{"id":"2307.05663","title":"Objaverse-XL: A Universe of 10M+ 3D Objects","created":"2023-07-11","cited_by_count":774},{"id":"2011.13084","title":"Neural Scene Flow Fields for Space-Time View Synthesis of Dynamic Scenes","created":"2020-11-26","cited_by_count":751},{"id":"2301.10241","title":"K-Planes: Explicit Radiance Fields in Space, Time, and Appearance","created":"2023-01-24","cited_by_count":746},{"id":"2303.13439","title":"Text2Video-Zero: Text-to-Image Diffusion Models are Zero-Shot Video Generators","created":"2023-03-23","cited_by_count":670},{"id":"2012.15838","title":"Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans","created":"2020-12-31","cited_by_count":634},{"id":"2301.09632","title":"HexPlane: A Fast Representation for Dynamic Scenes","created":"2023-01-23","cited_by_count":587},{"id":"2112.01455","title":"Zero-Shot Text-Guided Object Generation with Dream Fields","created":"2021-12-02","cited_by_count":513},{"id":"2201.04127","title":"HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video","created":"2022-01-11","cited_by_count":483},{"id":"2012.12247","title":"Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video","created":"2020-12-22","cited_by_count":471},{"id":"2303.09535","title":"FateZero: Fusing Attentions for Zero-shot Text-based Video Editing","created":"2023-03-16","cited_by_count":466},{"id":"2307.10373","title":"TokenFlow: Consistent Diffusion Features for Consistent Video Editing","created":"2023-07-19","cited_by_count":442},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2011.12950","title":"Space-time Neural Irradiance Fields for Free-Viewpoint Video","created":"2020-11-25","cited_by_count":414},{"id":"2205.15285","title":"Fast Dynamic Radiance Fields with Time-Aware Neural Voxels","created":"2022-05-30","cited_by_count":346},{"id":"2303.04761","title":"Video-P2P: Video Editing with Cross-attention Control","created":"2023-03-08","cited_by_count":314},{"id":"2204.02491","title":"Text2LIVE: Text-Driven Layered Image and Video Editing","created":"2022-04-05","cited_by_count":312},{"id":"2309.15818","title":"Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation","created":"2023-09-27","cited_by_count":302},{"id":"2306.07954","title":"Rerender A Video: Zero-Shot Text-Guided Video-to-Video Translation","created":"2023-06-13","cited_by_count":253},{"id":"2203.12575","title":"NeuMan: Neural Human Radiance Field from a Single Video","created":"2022-03-23","cited_by_count":244},{"id":"2308.09592","title":"StableVideo: Text-driven Consistency-aware Diffusion Video Editing","created":"2023-08-18","cited_by_count":183},{"id":"2306.13455","title":"DreamEditor: Text-Driven 3D Scene Editing with Neural Fields","created":"2023-06-23","cited_by_count":155},{"id":"2210.15947","title":"NeRFPlayer: A Streamable Dynamic Scene Representation with Decomposed Neural Radiance Fields","created":"2022-10-28","cited_by_count":152},{"id":"2104.14786","title":"Editable Free-viewpoint Video Using a Layered Neural Representation","created":"2021-04-30","cited_by_count":148},{"id":"2206.06360","title":"ARF: Artistic Radiance Fields","created":"2022-06-13","cited_by_count":147},{"id":"2109.11418","title":"Layered Neural Atlases for Consistent Video Editing","created":"2021-09-23","cited_by_count":137},{"id":"2212.08070","title":"NeRF-Art: Text-Driven Neural Radiance Fields Stylization","created":"2022-12-15","cited_by_count":126},{"id":"2308.07926","title":"CoDeF: Content Deformation Fields for Temporally Consistent Video Processing","created":"2023-08-15","cited_by_count":108},{"id":"2205.15723","title":"DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes","created":"2022-05-31","cited_by_count":103},{"id":"2306.09329","title":"DreamHuman: Animatable 3D Avatars from Text","created":"2023-06-15","cited_by_count":102},{"id":"2303.13277","title":"SINE: Semantic-driven Image-based NeRF Editing with Prior-guided Editing Field","created":"2023-03-23","cited_by_count":94},{"id":"2308.10608","title":"FocalDreamer: Text-driven 3D Editing via Focal-fusion Assembly","created":"2023-08-21","cited_by_count":76},{"id":"2301.13173","title":"Shape-aware Text-driven Layered Video Editing","created":"2023-01-30","cited_by_count":54},{"id":"2306.08707","title":"VidEdit: Zero-Shot and Spatially Aware Text-Driven Video Editing","created":"2023-06-14","cited_by_count":36},{"id":"2304.12281","title":"HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video","created":"2023-04-24","cited_by_count":33},{"id":"2307.07663","title":"INVE: Interactive Neural Video Editing","created":"2023-07-15","cited_by_count":10},{"id":"2307.12909","title":"Dyn-E: Local Appearance Editing of Dynamic Neural Radiance Fields","created":"2023-07-24","cited_by_count":5}],"next_cursor":null}