{"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":"2005.14165","title":"Language Models are Few-Shot Learners","created":"2020-05-28","cited_by_count":32419},{"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":"2303.08774","title":"GPT-4 Technical Report","created":"2023-03-15","cited_by_count":18396},{"id":"2010.02502","title":"Denoising Diffusion Implicit Models","created":"2020-10-06","cited_by_count":9781},{"id":"2304.08485","title":"Visual Instruction Tuning","created":"2023-04-17","cited_by_count":7869},{"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":"2301.12597","title":"BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models","created":"2023-01-30","cited_by_count":6137},{"id":"2207.12598","title":"Classifier-Free Diffusion Guidance","created":"2022-07-26","cited_by_count":5847},{"id":"2302.05543","title":"Adding Conditional Control to Text-to-Image Diffusion Models","created":"2023-02-10","cited_by_count":5503},{"id":"2204.14198","title":"Flamingo: a Visual Language Model for Few-Shot Learning","created":"2022-04-29","cited_by_count":4386},{"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":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2208.01618","title":"An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion","created":"2022-08-02","cited_by_count":2245},{"id":"2104.07636","title":"Image Super-Resolution via Iterative Refinement","created":"2021-04-15","cited_by_count":1511},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"2111.05826","title":"Palette: Image-to-Image Diffusion Models","created":"2021-11-10","cited_by_count":1300},{"id":"1801.01401","title":"Demystifying MMD GANs","created":"2018-01-04","cited_by_count":1293},{"id":"2211.01324","title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","created":"2022-11-02","cited_by_count":931},{"id":"2111.14818","title":"Blended Diffusion for Text-driven Editing of Natural Images","created":"2021-11-29","cited_by_count":927},{"id":"2302.00923","title":"Multimodal Chain-of-Thought Reasoning in Language Models","created":"2023-02-02","cited_by_count":752},{"id":"2103.01458","title":"Diffusion Probabilistic Models for 3D Point Cloud Generation","created":"2021-03-02","cited_by_count":735},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"2210.11427","title":"DiffEdit: Diffusion-based semantic image editing with mask guidance","created":"2022-10-20","cited_by_count":647},{"id":"2210.06978","title":"LION: Latent Point Diffusion Models for 3D Shape Generation","created":"2022-10-12","cited_by_count":553},{"id":"2305.07015","title":"Exploiting Diffusion Prior for Real-World Image Super-Resolution","created":"2023-05-11","cited_by_count":489},{"id":"2305.16322","title":"Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models","created":"2023-05-25","cited_by_count":359},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2302.09778","title":"Composer: Creative and Controllable Image Synthesis with Composable Conditions","created":"2023-02-20","cited_by_count":304},{"id":"2307.06350","title":"T2I-CompBench++: An Enhanced and Comprehensive Benchmark for Compositional Text-to-image Generation","created":"2023-07-12","cited_by_count":260},{"id":"2112.02475","title":"Deblurring via Stochastic Refinement","created":"2021-12-05","cited_by_count":249},{"id":"2205.07680","title":"BBDM: Image-to-image Translation with Brownian Bridge Diffusion Models","created":"2022-05-16","cited_by_count":225},{"id":"2303.16491","title":"Implicit Diffusion Models for Continuous Super-Resolution","created":"2023-03-29","cited_by_count":218},{"id":"2307.01097","title":"MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion","created":"2023-07-03","cited_by_count":212},{"id":"2304.05684","title":"InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions","created":"2023-04-12","cited_by_count":206},{"id":"2312.14867","title":"VIEScore: Towards Explainable Metrics for Conditional Image Synthesis Evaluation","created":"2023-12-22","cited_by_count":201},{"id":"1903.12351","title":"Lending Orientation to Neural Networks for Cross-view Geo-localization","created":"2019-03-29","cited_by_count":180},{"id":"2310.18235","title":"Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation","created":"2023-10-27","cited_by_count":171},{"id":"2401.04092","title":"GPT-4V(ision) is a Human-Aligned Evaluator for Text-to-3D Generation","created":"2024-01-08","cited_by_count":153},{"id":"2406.16855","title":"DreamBench++: A Human-Aligned Benchmark for Personalized Image Generation","created":"2024-06-24","cited_by_count":131},{"id":"2311.01361","title":"GPT-4V(ision) as a Generalist Evaluator for Vision-Language Tasks","created":"2023-11-02","cited_by_count":119},{"id":"2303.17598","title":"Consistent View Synthesis with Pose-Guided Diffusion Models","created":"2023-03-30","cited_by_count":117},{"id":"2103.06818","title":"Coming Down to Earth: Satellite-to-Street View Synthesis for Geo-Localization","created":"2021-03-11","cited_by_count":113},{"id":"1904.06807","title":"Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image Translation","created":"2019-04-15","cited_by_count":97},{"id":"1612.02709","title":"Predicting Ground-Level Scene Layout from Aerial Imagery","created":"2016-12-08","cited_by_count":90},{"id":"1803.03396","title":"Cross-View Image Synthesis using Conditional GANs","created":"2018-03-09","cited_by_count":69},{"id":"1907.06023","title":"Structure-Aware Residual Pyramid Network for Monocular Depth Estimation","created":"2019-07-13","cited_by_count":49},{"id":"2311.08403","title":"Instant3D: Instant Text-to-3D Generation","created":"2023-11-14","cited_by_count":45},{"id":"2103.01623","title":"Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery","created":"2021-03-02","cited_by_count":41},{"id":"2408.05475","title":"Cross-view image geo-localization with Panorama-BEV Co-Retrieval Network","created":"2024-08-10","cited_by_count":40},{"id":"2403.14198","title":"Unleashing Unlabeled Data: A Paradigm for Cross-View Geo-Localization","created":"2024-03-21","cited_by_count":31},{"id":"2303.14672","title":"Sat2Density: Faithful Density Learning from Satellite-Ground Image Pairs","created":"2023-03-26","cited_by_count":29},{"id":"2401.10786","title":"Sat2Scene: 3D Urban Scene Generation from Satellite Images with Diffusion","created":"2024-01-19","cited_by_count":27},{"id":"2203.11832","title":"Cross-View Panorama Image Synthesis","created":"2022-03-22","cited_by_count":26},{"id":"2208.00928","title":"OmniCity: Omnipotent City Understanding with Multi-level and Multi-view Images","created":"2022-08-01","cited_by_count":21},{"id":"2404.02638","title":"SG-BEV: Satellite-Guided BEV Fusion for Cross-View Semantic Segmentation","created":"2024-04-03","cited_by_count":18}],"next_cursor":null}