{"list":"other","total":54,"rows":[{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2006.11239","title":"Denoising Diffusion Probabilistic Models","created":"2020-06-19","cited_by_count":21076},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2302.13971","title":"LLaMA: Open and Efficient Foundation Language Models","created":"2023-02-27","cited_by_count":14132},{"id":"2104.14294","title":"Emerging Properties in Self-Supervised Vision Transformers","created":"2021-04-29","cited_by_count":6968},{"id":"2308.04079","title":"3D Gaussian Splatting for Real-Time Radiance Field Rendering","created":"2023-08-08","cited_by_count":6226},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"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":"2406.09414","title":"Depth Anything V2","created":"2024-06-13","cited_by_count":1422},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1910.02054","title":"ZeRO: Memory Optimizations Toward Training Trillion Parameter Models","created":"2019-10-04","cited_by_count":1301},{"id":"1406.2283","title":"Depth Map Prediction from a Single Image using a Multi-Scale Deep Network","created":"2014-06-09","cited_by_count":1274},{"id":"2011.12948","title":"Nerfies: Deformable Neural Radiance Fields","created":"2020-11-25","cited_by_count":1198},{"id":"1604.06174","title":"Training Deep Nets with Sublinear Memory Cost","created":"2016-04-21","cited_by_count":848},{"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":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2310.19512","title":"VideoCrafter1: Open Diffusion Models for High-Quality Video Generation","created":"2023-10-30","cited_by_count":535},{"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":"2211.11018","title":"MagicVideo: Efficient Video Generation With Latent Diffusion Models","created":"2022-11-20","cited_by_count":465},{"id":"2105.06468","title":"Dynamic View Synthesis from Dynamic Monocular Video","created":"2021-05-13","cited_by_count":420},{"id":"1907.10326","title":"From Big to Small: Multi-Scale Local Planar Guidance for Monocular Depth Estimation","created":"2019-07-24","cited_by_count":382},{"id":"2403.18913","title":"UniDepth: Universal Monocular Metric Depth Estimation","created":"2024-03-27","cited_by_count":382},{"id":"2307.10984","title":"Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image","created":"2023-07-20","cited_by_count":365},{"id":"2309.15103","title":"LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models","created":"2023-09-26","cited_by_count":349},{"id":"2304.01186","title":"Follow Your Pose: Pose-Guided Text-to-Video Generation using Pose-Free Videos","created":"2023-04-03","cited_by_count":314},{"id":"2211.11082","title":"DynIBaR: Neural Dynamic Image-Based Rendering","created":"2022-11-20","cited_by_count":224},{"id":"2409.02095","title":"DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos","created":"2024-09-03","cited_by_count":204},{"id":"2309.03897","title":"ProPainter: Improving Propagation and Transformer for Video Inpainting","created":"2023-09-07","cited_by_count":197},{"id":"2301.02239","title":"Robust Dynamic Radiance Fields","created":"2023-01-05","cited_by_count":194},{"id":"2012.05901","title":"Robust Consistent Video Depth Estimation","created":"2020-12-10","cited_by_count":188},{"id":"2306.00943","title":"Make-Your-Video: Customized Video Generation Using Textual and Structural Guidance","created":"2023-06-01","cited_by_count":129},{"id":"2103.12091","title":"Transformer-Based Attention Networks for Continuous Pixel-Wise Prediction","created":"2021-03-22","cited_by_count":125},{"id":"2203.14211","title":"DepthFormer: Exploiting Long-Range Correlation and Local Information for Accurate Monocular Depth Estimation","created":"2022-03-27","cited_by_count":118},{"id":"2204.02663","title":"Towards An End-to-End Framework for Flow-Guided Video Inpainting","created":"2022-04-06","cited_by_count":113},{"id":"2204.02091","title":"P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior","created":"2022-04-05","cited_by_count":107},{"id":"2109.02974","title":"FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting","created":"2021-09-07","cited_by_count":95},{"id":"2405.20222","title":"MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model","created":"2024-05-30","cited_by_count":89},{"id":"2112.02815","title":"Make It Move: Controllable Image-to-Video Generation with Text Descriptions","created":"2021-12-06","cited_by_count":88},{"id":"1604.03650","title":"Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks","created":"2016-04-13","cited_by_count":73},{"id":"2405.20279","title":"CV-VAE: A Compatible Video VAE for Latent Generative Video Models","created":"2024-05-30","cited_by_count":70},{"id":"2108.01166","title":"Consistent Depth of Moving Objects in Video","created":"2021-08-02","cited_by_count":56},{"id":"2009.00743","title":"Bidirectional Attention Network for Monocular Depth Estimation","created":"2020-09-01","cited_by_count":48},{"id":"2405.18426","title":"GFlow: Recovering 4D World from Monocular Video","created":"2024-05-28","cited_by_count":46},{"id":"2303.08524","title":"CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying","created":"2023-03-15","cited_by_count":34},{"id":"2403.10755","title":"Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching","created":"2024-03-16","cited_by_count":24},{"id":"2312.02135","title":"Fast View Synthesis of Casual Videos with Soup-of-Planes","created":"2023-12-04","cited_by_count":22},{"id":"2407.00367","title":"SVG: 3D Stereoscopic Video Generation via Denoising Frame Matrix","created":"2024-06-29","cited_by_count":20},{"id":"2406.00908","title":"ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation","created":"2024-06-03","cited_by_count":5},{"id":"2407.10285","title":"Noise Calibration: Plug-and-play Content-Preserving Video Enhancement using Pre-trained Video Diffusion Models","created":"2024-07-14","cited_by_count":5}],"next_cursor":null}