{"list":"other","total":67,"rows":[{"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":"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":"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":"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":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2102.12092","title":"Zero-Shot Text-to-Image Generation","created":"2021-02-24","cited_by_count":4288},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2102.09672","title":"Improved Denoising Diffusion Probabilistic Models","created":"2021-02-18","cited_by_count":3761},{"id":"2112.10741","title":"GLIDE: Towards Photorealistic Image Generation and Editing with Text-Guided Diffusion Models","created":"2021-12-20","cited_by_count":3614},{"id":"2012.09841","title":"Taming Transformers for High-Resolution Image Synthesis","created":"2020-12-17","cited_by_count":3253},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2108.01073","title":"SDEdit: Guided Image Synthesis and Editing with Stochastic Differential Equations","created":"2021-08-02","cited_by_count":1937},{"id":"2006.04768","title":"Linformer: Self-Attention with Linear Complexity","created":"2020-06-08","cited_by_count":1474},{"id":"2308.06721","title":"IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models","created":"2023-08-13","cited_by_count":1464},{"id":"2401.10891","title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data","created":"2024-01-19","cited_by_count":1360},{"id":"1809.00219","title":"ESRGAN: Enhanced Super-Resolution Generative Adversarial Networks","created":"2018-09-01","cited_by_count":1254},{"id":"1501.00092","title":"Image Super-Resolution Using Deep Convolutional Networks","created":"2014-12-31","cited_by_count":1224},{"id":"2108.05997","title":"MUSIQ: Multi-scale Image Quality Transformer","created":"2021-08-12","cited_by_count":1081},{"id":"2207.12396","title":"Exploring CLIP for Assessing the Look and Feel of Images","created":"2022-07-25","cited_by_count":991},{"id":"2301.07093","title":"GLIGEN: Open-Set Grounded Text-to-Image Generation","created":"2023-01-17","cited_by_count":781},{"id":"2401.12168","title":"SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities","created":"2024-01-22","cited_by_count":706},{"id":"1711.06077","title":"The Perception-Distortion Tradeoff","created":"2017-11-16","cited_by_count":587},{"id":"2103.14006","title":"Designing a Practical Degradation Model for Deep Blind Image Super-Resolution","created":"2021-03-25","cited_by_count":529},{"id":"2204.08958","title":"MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment","created":"2022-04-19","cited_by_count":522},{"id":"2305.07015","title":"Exploiting Diffusion Prior for Real-World Image Super-Resolution","created":"2023-05-11","cited_by_count":489},{"id":"2307.12348","title":"ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting","created":"2023-07-23","cited_by_count":365},{"id":"2311.16518","title":"SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution","created":"2023-11-27","cited_by_count":315},{"id":"2205.00363","title":"Visual Spatial Reasoning","created":"2022-04-30","cited_by_count":293},{"id":"2401.13627","title":"Scaling Up to Excellence: Practicing Model Scaling for Photo-Realistic Image Restoration In the Wild","created":"2024-01-24","cited_by_count":286},{"id":"2308.15070","title":"DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior","created":"2023-08-29","cited_by_count":257},{"id":"2308.14469","title":"Pixel-Aware Stable Diffusion for Realistic Image Super-resolution and Personalized Stylization","created":"2023-08-28","cited_by_count":254},{"id":"2310.19785","title":"What's \"up\" with vision-language models? Investigating their struggle with spatial reasoning","created":"2023-10-30","cited_by_count":254},{"id":"2311.14760","title":"SinSR: Diffusion-Based Image Super-Resolution in a Single Step","created":"2023-11-23","cited_by_count":238},{"id":"2312.00785","title":"Sequential Modeling Enables Scalable Learning for Large Vision Models","created":"2023-12-01","cited_by_count":212},{"id":"2303.11435","title":"Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration","created":"2023-03-20","cited_by_count":165},{"id":"2410.10812","title":"HART: Efficient Visual Generation with Hybrid Autoregressive Transformer","created":"2024-10-14","cited_by_count":132},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120},{"id":"2409.10695","title":"Playground v3: Improving Text-to-Image Alignment with Deep-Fusion Large Language Models","created":"2024-09-16","cited_by_count":116},{"id":"2203.09195","title":"Details or Artifacts: A Locally Discriminative Learning Approach to Realistic Image Super-Resolution","created":"2022-03-17","cited_by_count":114},{"id":"2202.13142","title":"Real-World Blind Super-Resolution via Feature Matching with Implicit High-Resolution Priors","created":"2022-02-26","cited_by_count":100},{"id":"2305.02677","title":"Caption Anything: Interactive Image Description with Diverse Multimodal Controls","created":"2023-05-04","cited_by_count":99},{"id":"2203.14216","title":"Efficient and Degradation-Adaptive Network for Real-World Image Super-Resolution","created":"2022-03-27","cited_by_count":96},{"id":"2310.01110","title":"Prompt-tuning latent diffusion models for inverse problems","created":"2023-10-02","cited_by_count":70},{"id":"2410.17385","title":"Do Vision-Language Models Represent Space and How? Evaluating Spatial Frame of Reference Under Ambiguities","created":"2024-10-22","cited_by_count":59},{"id":"2406.09406","title":"4M-21: An Any-to-Any Vision Model for Tens of Tasks and Modalities","created":"2024-06-13","cited_by_count":52},{"id":"2407.05878","title":"HiT-SR: Hierarchical Transformer for Efficient Image Super-Resolution","created":"2024-07-08","cited_by_count":42},{"id":"2403.05049","title":"XPSR: Cross-modal Priors for Diffusion-based Image Super-Resolution","created":"2024-03-08","cited_by_count":41},{"id":"2110.08521","title":"Locally Adaptive Structure and Texture Similarity for Image Quality Assessment","created":"2021-10-16","cited_by_count":32},{"id":"2410.08159","title":"DART: Denoising Autoregressive Transformer for Scalable Text-to-Image Generation","created":"2024-10-10","cited_by_count":32},{"id":"2312.02156","title":"Latent Feature-Guided Diffusion Models for Shadow Removal","created":"2023-12-04","cited_by_count":29},{"id":"2310.01407","title":"CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation","created":"2023-10-02","cited_by_count":26},{"id":"2312.11595","title":"SPIRE: Semantic Prompt-Driven Image Restoration","created":"2023-12-18","cited_by_count":24},{"id":"2401.17258","title":"You Only Need One Step: Fast Super-Resolution with Stable Diffusion via Scale Distillation","created":"2024-01-30","cited_by_count":24},{"id":"2404.01367","title":"Bigger is not Always Better: Scaling Properties of Latent Diffusion Models","created":"2024-04-01","cited_by_count":21},{"id":"2403.02601","title":"Low-Res Leads the Way: Improving Generalization for Super-Resolution by Self-Supervised Learning","created":"2024-03-05","cited_by_count":19},{"id":"2404.15620","title":"A Dynamic Kernel Prior Model for Unsupervised Blind Image Super-Resolution","created":"2024-04-24","cited_by_count":15},{"id":"2405.21048","title":"Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling","created":"2024-05-31","cited_by_count":13},{"id":"2403.01124","title":"Text-guided Explorable Image Super-resolution","created":"2024-03-02","cited_by_count":9},{"id":"2403.10988","title":"Boosting Flow-based Generative Super-Resolution Models via Learned Prior","created":"2024-03-16","cited_by_count":7},{"id":"2207.09302","title":"Deep Semantic Statistics Matching (D2SM) Denoising Network","created":"2022-07-19","cited_by_count":2}],"next_cursor":null}