{"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":"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2006.10739","title":"Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domains","created":"2020-06-18","cited_by_count":2200},{"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":"2201.09865","title":"RePaint: Inpainting using Denoising Diffusion Probabilistic Models","created":"2022-01-24","cited_by_count":1430},{"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":"2308.16512","title":"MVDream: Multi-view Diffusion for 3D Generation","created":"2023-08-31","cited_by_count":938},{"id":"2311.17117","title":"Animate Anyone: Consistent and Controllable Image-to-Video Synthesis for Character Animation","created":"2023-11-28","cited_by_count":688},{"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":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"1803.08669","title":"Pyramid Stereo Matching Network","created":"2018-03-23","cited_by_count":489},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2109.07547","title":"RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching","created":"2021-09-15","cited_by_count":353},{"id":"2311.16498","title":"MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model","created":"2023-11-27","cited_by_count":330},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"2004.04727","title":"3D Photography using Context-aware Layered Depth Inpainting","created":"2020-04-09","cited_by_count":206},{"id":"2203.11483","title":"Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation","created":"2022-03-22","cited_by_count":197},{"id":"1604.03901","title":"Single-Image Depth Perception in the Wild","created":"2016-04-13","cited_by_count":180},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172},{"id":"2305.02296","title":"DynamicStereo: Consistent Dynamic Depth from Stereo Videos","created":"2023-05-03","cited_by_count":148},{"id":"2104.03866","title":"SMD-Nets: Stereo Mixture Density Networks","created":"2021-04-08","cited_by_count":120},{"id":"2303.17598","title":"Consistent View Synthesis with Pose-Guided Diffusion Models","created":"2023-03-30","cited_by_count":117},{"id":"1804.06534","title":"Falling Things: A Synthetic Dataset for 3D Object Detection and Pose Estimation","created":"2018-04-18","cited_by_count":92},{"id":"1810.05424","title":"Real-time self-adaptive deep stereo","created":"2018-10-12","cited_by_count":80},{"id":"2405.17251","title":"GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping","created":"2024-05-27","cited_by_count":73},{"id":"2409.00638","title":"IGEV++: Iterative Multi-range Geometry Encoding Volumes for Stereo Matching","created":"2024-09-01","cited_by_count":59},{"id":"2303.17603","title":"NeRF-Supervised Deep Stereo","created":"2023-03-30","cited_by_count":46},{"id":"2008.01484","title":"Learning Stereo from Single Images","created":"2020-08-04","cited_by_count":45},{"id":"1904.02957","title":"Learning to Adapt for Stereo","created":"2019-04-05","cited_by_count":42},{"id":"2008.07130","title":"Reversing the cycle: self-supervised deep stereo through enhanced monocular distillation","created":"2020-08-17","cited_by_count":34},{"id":"2301.08245","title":"Booster: a Benchmark for Depth from Images of Specular and Transparent Surfaces","created":"2023-01-19","cited_by_count":33},{"id":"1709.00930","title":"Self-Supervised Learning for Stereo Matching with Self-Improving Ability","created":"2017-09-04","cited_by_count":32},{"id":"2004.04627","title":"AdaStereo: A Simple and Efficient Approach for Adaptive Stereo Matching","created":"2020-04-09","cited_by_count":31},{"id":"1909.03943","title":"Unsupervised Domain Adaptation for Depth Prediction from Images","created":"2019-09-09","cited_by_count":29},{"id":"2403.04965","title":"StereoDiffusion: Training-Free Stereo Image Generation Using Latent Diffusion Models","created":"2024-03-08","cited_by_count":25},{"id":"2403.10755","title":"Match-Stereo-Videos: Bidirectional Alignment for Consistent Dynamic Stereo Matching","created":"2024-03-16","cited_by_count":24},{"id":"1905.09265","title":"Bridging Stereo Matching and Optical Flow via Spatiotemporal Correspondence","created":"2019-05-22","cited_by_count":23},{"id":"2007.05233","title":"Continual Adaptation for Deep Stereo","created":"2020-07-10","cited_by_count":23},{"id":"2407.07816","title":"A Survey on Deep Stereo Matching in the Twenties","created":"2024-07-10","cited_by_count":23},{"id":"1904.10230","title":"A Large RGB-D Dataset for Semi-supervised Monocular Depth Estimation","created":"2019-04-23","cited_by_count":21},{"id":"2005.01927","title":"StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching","created":"2020-05-05","cited_by_count":21},{"id":"2203.16521","title":"CoordGAN: Self-Supervised Dense Correspondences Emerge from GANs","created":"2022-03-30","cited_by_count":17},{"id":"2411.09151","title":"Mono2Stereo: Monocular Knowledge Transfer for Enhanced Stereo Matching","created":"2024-11-14","cited_by_count":5},{"id":"2309.01842","title":"StereoFlowGAN: Co-training for Stereo and Flow with Unsupervised Domain Adaptation","created":"2023-09-04","cited_by_count":4},{"id":"2406.07667","title":"PLT-D3: A High-fidelity Dynamic Driving Simulation Dataset for Stereo Depth and Scene Flow","created":"2024-06-11","cited_by_count":3}],"next_cursor":null}