{"list":"other","total":53,"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":"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":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2204.06125","title":"Hierarchical Text-Conditional Image Generation with CLIP Latents","created":"2022-04-13","cited_by_count":6585},{"id":"2205.11487","title":"Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding","created":"2022-05-23","cited_by_count":6355},{"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":"2201.12086","title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","created":"2022-01-28","cited_by_count":4322},{"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":"1809.11096","title":"Large Scale GAN Training for High Fidelity Natural Image Synthesis","created":"2018-09-28","cited_by_count":2626},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"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":"1906.00446","title":"Generating Diverse High-Fidelity Images with VQ-VAE-2","created":"2019-06-02","cited_by_count":1387},{"id":"1502.02791","title":"Learning Transferable Features with Deep Adaptation Networks","created":"2015-02-10","cited_by_count":1329},{"id":"2206.10789","title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","created":"2022-06-22","cited_by_count":1295},{"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":"1801.04406","title":"Which Training Methods for GANs do actually Converge?","created":"2018-01-13","cited_by_count":679},{"id":"2007.03898","title":"NVAE: A Deep Hierarchical Variational Autoencoder","created":"2020-07-08","cited_by_count":637},{"id":"1606.00373","title":"Deeper Depth Prediction with Fully Convolutional Residual Networks","created":"2016-06-01","cited_by_count":403},{"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":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"1605.06457","title":"Virtual Worlds as Proxy for Multi-Object Tracking Analysis","created":"2016-05-20","cited_by_count":341},{"id":"2211.00680","title":"On the detection of synthetic images generated by diffusion models","created":"2022-11-01","cited_by_count":283},{"id":"2211.12446","title":"EDICT: Exact Diffusion Inversion via Coupled Transformations","created":"2022-11-22","cited_by_count":258},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"1803.10081","title":"DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation","created":"2018-03-27","cited_by_count":214},{"id":"2111.13606","title":"Conditional Image Generation with Score-Based Diffusion Models","created":"2021-11-26","cited_by_count":197},{"id":"1704.01705","title":"Generate To Adapt: Aligning Domains using Generative Adversarial Networks","created":"2017-04-06","cited_by_count":183},{"id":"1502.07411","title":"Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields","created":"2015-02-26","cited_by_count":169},{"id":"2303.13703","title":"End-to-End Diffusion Latent Optimization Improves Classifier Guidance","created":"2023-03-23","cited_by_count":108},{"id":"2103.10951","title":"Paint by Word","created":"2021-03-19","cited_by_count":107},{"id":"2209.05442","title":"Soft Diffusion: Score Matching for General Corruptions","created":"2022-09-12","cited_by_count":102},{"id":"2210.09071","title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention","created":"2022-10-17","cited_by_count":93},{"id":"1603.06432","title":"Beyond Sharing Weights for Deep Domain Adaptation","created":"2016-03-21","cited_by_count":80},{"id":"1803.11029","title":"Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation","created":"2018-03-29","cited_by_count":78},{"id":"2207.13038","title":"Text-Guided Synthesis of Artistic Images with Retrieval-Augmented Diffusion Models","created":"2022-07-26","cited_by_count":64},{"id":"2108.10531","title":"Unsupervised Depth Completion with Calibrated Backprojection Layers","created":"2021-08-24","cited_by_count":61},{"id":"1903.07309","title":"Bilateral Cyclic Constraint and Adaptive Regularization for Unsupervised Monocular Depth Prediction","created":"2019-03-18","cited_by_count":44},{"id":"2106.02994","title":"Learning Topology from Synthetic Data for Unsupervised Depth Completion","created":"2021-06-06","cited_by_count":38},{"id":"2207.13744","title":"Lighting (In)consistency of Paint by Text","created":"2022-07-27","cited_by_count":35},{"id":"2206.14617","title":"Perspective (In)consistency of Paint by Text","created":"2022-06-27","cited_by_count":34},{"id":"1807.11130","title":"Geo-Supervised Visual Depth Prediction","created":"2018-07-30","cited_by_count":33},{"id":"2008.03286","title":"HoliCity: A City-Scale Data Platform for Learning Holistic 3D Structures","created":"2020-08-07","cited_by_count":29},{"id":"1908.11757","title":"Temporal Coherence for Active Learning in Videos","created":"2019-08-30","cited_by_count":24},{"id":"2112.13515","title":"UV-SLAM: Unconstrained Line-based SLAM Using Vanishing Points for Structural Mapping","created":"2021-12-27","cited_by_count":23},{"id":"2204.13635","title":"SemAttNet: Towards Attention-based Semantic Aware Guided Depth Completion","created":"2022-04-28","cited_by_count":23},{"id":"2203.08586","title":"Deep vanishing point detection: Geometric priors make dataset variations vanish","created":"2022-03-16","cited_by_count":18},{"id":"1805.08019","title":"DiDA: Disentangled Synthesis for Domain Adaptation","created":"2018-05-21","cited_by_count":10},{"id":"2210.12756","title":"VP-SLAM: A Monocular Real-time Visual SLAM with Points, Lines and Vanishing Points","created":"2022-10-23","cited_by_count":2}],"next_cursor":null}