{"list":"other","total":58,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"2105.05233","title":"Diffusion Models Beat GANs on Image Synthesis","created":"2021-05-11","cited_by_count":8255},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2210.08402","title":"LAION-5B: An open large-scale dataset for training next generation image-text models","created":"2022-10-16","cited_by_count":4152},{"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":"2209.14988","title":"DreamFusion: Text-to-3D using 2D Diffusion","created":"2022-09-29","cited_by_count":3025},{"id":"2103.13415","title":"Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields","created":"2021-03-24","cited_by_count":1964},{"id":"2212.08051","title":"Objaverse: A Universe of Annotated 3D Objects","created":"2022-12-15","cited_by_count":1540},{"id":"2303.11328","title":"Zero-1-to-3: Zero-shot One Image to 3D Object","created":"2023-03-20","cited_by_count":1489},{"id":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"id":"2211.10440","title":"Magic3D: High-Resolution Text-to-3D Content Creation","created":"2022-11-18","cited_by_count":1290},{"id":"2008.02268","title":"NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Collections","created":"2020-08-05","cited_by_count":1232},{"id":"2010.07492","title":"NeRF++: Analyzing and Improving Neural Radiance Fields","created":"2020-10-15","cited_by_count":861},{"id":"2003.00196","title":"First Order Motion Model for Image Animation","created":"2020-02-29","cited_by_count":704},{"id":"2212.08751","title":"Point-E: A System for Generating 3D Point Clouds from Complex Prompts","created":"2022-12-16","cited_by_count":699},{"id":"2303.13873","title":"Fantasia3D: Disentangling Geometry and Appearance for High-quality Text-to-3D Content Creation","created":"2023-03-24","cited_by_count":687},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2109.00512","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","created":"2021-09-01","cited_by_count":652},{"id":"2204.11918","title":"Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Items","created":"2022-04-25","cited_by_count":612},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"2305.02463","title":"Shap-E: Generating Conditional 3D Implicit Functions","created":"2023-05-03","cited_by_count":385},{"id":"1912.08804","title":"SynSin: End-to-end View Synthesis from a Single Image","created":"2019-12-18","cited_by_count":364},{"id":"2303.14184","title":"Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion Prior","created":"2023-03-24","cited_by_count":343},{"id":"2210.04628","title":"Novel View Synthesis with Diffusion Models","created":"2022-10-06","cited_by_count":300},{"id":"2003.05534","title":"Softmax Splatting for Video Frame Interpolation","created":"2020-03-11","cited_by_count":279},{"id":"2304.02602","title":"Generative Novel View Synthesis with 3D-Aware Diffusion Models","created":"2023-04-05","cited_by_count":274},{"id":"2004.11364","title":"Single-View View Synthesis with Multiplane Images","created":"2020-04-23","cited_by_count":263},{"id":"1605.07157","title":"Unsupervised Learning for Physical Interaction through Video Prediction","created":"2016-05-23","cited_by_count":260},{"id":"2110.13903","title":"NeRV: Neural Representations for Videos","created":"2021-10-26","cited_by_count":256},{"id":"1802.07687","title":"Stochastic Video Generation with a Learned Prior","created":"2018-02-21","cited_by_count":245},{"id":"1908.06903","title":"Multi-Garment Net: Learning to Dress 3D People from Images","created":"2019-08-19","cited_by_count":245},{"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":"2303.11396","title":"Text2Tex: Text-driven Texture Synthesis via Diffusion Models","created":"2023-03-20","cited_by_count":235},{"id":"2111.13152","title":"Scene Representation Transformer: Geometry-Free Novel View Synthesis Through Set-Latent Scene Representations","created":"2021-11-25","cited_by_count":227},{"id":"2212.00792","title":"SparseFusion: Distilling View-conditioned Diffusion for 3D Reconstruction","created":"2022-12-01","cited_by_count":216},{"id":"1812.08861","title":"Animating Arbitrary Objects via Deep Motion Transfer","created":"2018-12-20","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":"2212.07422","title":"ECON: Explicit Clothed humans Optimized via Normal integration","created":"2022-12-14","cited_by_count":199},{"id":"2302.10109","title":"NerfDiff: Single-image View Synthesis with NeRF-guided Distillation from 3D-aware Diffusion","created":"2023-02-20","cited_by_count":180},{"id":"1706.08033","title":"Decomposing Motion and Content for Natural Video Sequence Prediction","created":"2017-06-25","cited_by_count":169},{"id":"1806.04166","title":"Learning to Decompose and Disentangle Representations for Video Prediction","created":"2018-06-11","cited_by_count":121},{"id":"2105.08756","title":"Pathdreamer: A World Model for Indoor Navigation","created":"2021-05-18","cited_by_count":118},{"id":"1812.04777","title":"Extreme View Synthesis","created":"2018-12-12","cited_by_count":94},{"id":"2304.10261","title":"Anything-3D: Towards Single-view Anything Reconstruction in the Wild","created":"2023-04-19","cited_by_count":92},{"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":"2305.10853","title":"LDM3D: Latent Diffusion Model for 3D","created":"2023-05-18","cited_by_count":53},{"id":"2112.03051","title":"Controllable Animation of Fluid Elements in Still Images","created":"2021-12-06","cited_by_count":45},{"id":"2303.13515","title":"Persistent Nature: A Generative Model of Unbounded 3D Worlds","created":"2023-03-23","cited_by_count":44},{"id":"1908.08522","title":"Compositional Video Prediction","created":"2019-08-22","cited_by_count":43},{"id":"2201.02533","title":"NeROIC: Neural Rendering of Objects from Online Image Collections","created":"2022-01-07","cited_by_count":36},{"id":"2205.07058","title":"RTMV: A Ray-Traced Multi-View Synthetic Dataset for Novel View Synthesis","created":"2022-05-14","cited_by_count":33},{"id":"1702.05619","title":"3D Face Reconstruction with Geometry Details from a Single Image","created":"2017-02-18","cited_by_count":27},{"id":"2104.06697","title":"Revisiting Hierarchical Approach for Persistent Long-Term Video Prediction","created":"2021-04-14","cited_by_count":23}],"next_cursor":null}