{"list":"other","total":74,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"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":"1801.03924","title":"The Unreasonable Effectiveness of Deep Features as a Perceptual Metric","created":"2018-01-11","cited_by_count":11177},{"id":"1503.03585","title":"Deep Unsupervised Learning using Nonequilibrium Thermodynamics","created":"2015-03-12","cited_by_count":7058},{"id":"2104.09864","title":"RoFormer: Enhanced Transformer with Rotary Position Embedding","created":"2021-04-20","cited_by_count":4703},{"id":"2307.01952","title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis","created":"2023-07-04","cited_by_count":4356},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2209.03003","title":"Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow","created":"2022-09-07","cited_by_count":3700},{"id":"1709.07871","title":"FiLM: Visual Reasoning with a General Conditioning Layer","created":"2017-09-22","cited_by_count":2333},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"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":"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":"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":"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":"2506.15742","title":"FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space","created":"2025-06-17","cited_by_count":1006},{"id":"2310.00426","title":"PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis","created":"2023-09-30","cited_by_count":864},{"id":"2004.07728","title":"Image Quality Assessment: Unifying Structure and Texture Similarity","created":"2020-04-16","cited_by_count":811},{"id":"1804.00607","title":"MegaDepth: Learning Single-View Depth Prediction from Internet Photos","created":"2018-04-02","cited_by_count":737},{"id":"1806.02446","title":"Deep Ordinal Regression Network for Monocular Depth Estimation","created":"2018-06-06","cited_by_count":723},{"id":"2405.14867","title":"Improved Distribution Matching Distillation for Fast Image Synthesis","created":"2024-05-23","cited_by_count":684},{"id":"2302.12288","title":"ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth","created":"2023-02-23","cited_by_count":657},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2011.14141","title":"AdaBins: Depth Estimation using Adaptive Bins","created":"2020-11-28","cited_by_count":601},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"2404.15506","title":"Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation","created":"2024-03-22","cited_by_count":395},{"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":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2403.04692","title":"PixArt-\\Sigma: Weak-to-Strong Training of Diffusion Transformer for 4K Text-to-Image Generation","created":"2024-03-07","cited_by_count":329},{"id":"2312.02145","title":"Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation","created":"2023-12-04","cited_by_count":327},{"id":"2507.02546","title":"MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Details","created":"2025-07-03","cited_by_count":261},{"id":"2012.07810","title":"Real-Time High-Resolution Background Matting","created":"2020-12-14","cited_by_count":173},{"id":"2502.20110","title":"UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler","created":"2025-02-27","cited_by_count":173},{"id":"2005.00305","title":"Defocus Deblurring Using Dual-Pixel Data","created":"2020-05-01","cited_by_count":139},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"2403.03431","title":"Towards Understanding Cross and Self-Attention in Stable Diffusion for Text-Guided Image Editing","created":"2024-03-06","cited_by_count":135},{"id":"2401.03407","title":"Bilateral Reference for High-Resolution Dichotomous Image Segmentation","created":"2024-01-07","cited_by_count":112},{"id":"2108.13610","title":"Iterative Filter Adaptive Network for Single Image Defocus Deblurring","created":"2021-08-31","cited_by_count":86},{"id":"2303.05021","title":"DiffusionDepth: Diffusion Denoising Approach for Monocular Depth Estimation","created":"2023-03-09","cited_by_count":82},{"id":"1904.02028","title":"CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth","created":"2019-04-03","cited_by_count":75},{"id":"2304.06334","title":"iDisc: Internal Discretization for Monocular Depth Estimation","created":"2023-04-13","cited_by_count":73},{"id":"1806.04171","title":"Synthetic Depth-of-Field with a Single-Camera Mobile Phone","created":"2018-06-11","cited_by_count":71},{"id":"1904.08601","title":"Deep Optics for Monocular Depth Estimation and 3D Object Detection","created":"2019-04-18","cited_by_count":65},{"id":"2308.09711","title":"Robust Monocular Depth Estimation under Challenging Conditions","created":"2023-08-18","cited_by_count":58},{"id":"2006.05698","title":"Rendering Natural Camera Bokeh Effect with Deep Learning","created":"2020-06-10","cited_by_count":57},{"id":"2510.07316","title":"Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers","created":"2025-10-08","cited_by_count":51},{"id":"2206.12614","title":"BokehMe: When Neural Rendering Meets Classical Rendering","created":"2022-06-25","cited_by_count":48},{"id":"2312.02284","title":"PatchFusion: An End-to-End Tile-Based Framework for High-Resolution Monocular Metric Depth Estimation","created":"2023-12-04","cited_by_count":41},{"id":"2501.02464","title":"Depth Any Camera: Zero-Shot Metric Depth Estimation from Any Camera","created":"2025-01-05","cited_by_count":40},{"id":"2005.09623","title":"Focus on defocus: bridging the synthetic to real domain gap for depth estimation","created":"2020-05-19","cited_by_count":37},{"id":"1704.01085","title":"Deep Depth From Focus","created":"2017-04-04","cited_by_count":28},{"id":"2412.02168","title":"Generative Photography: Scene-Consistent Camera Control for Realistic Text-to-Image Synthesis","created":"2024-12-03","cited_by_count":26},{"id":"2411.18229","title":"SharpDepth: Sharpening Metric Depth Predictions Using Diffusion Distillation","created":"2024-11-27","cited_by_count":21},{"id":"2112.01712","title":"Deep Depth from Focus with Differential Focus Volume","created":"2021-12-03","cited_by_count":20},{"id":"2011.02242","title":"BGGAN: Bokeh-Glass Generative Adversarial Network for Rendering Realistic Bokeh","created":"2020-11-04","cited_by_count":19},{"id":"2205.04565","title":"Is my Depth Ground-Truth Good Enough? HAMMER -- Highly Accurate Multi-Modal Dataset for DEnse 3D Scene Regression","created":"2022-05-09","cited_by_count":19},{"id":"2308.08843","title":"Dr.Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering","created":"2023-08-17","cited_by_count":19},{"id":"2207.08403","title":"MPIB: An MPI-Based Bokeh Rendering Framework for Realistic Partial Occlusion Effects","created":"2022-07-18","cited_by_count":17},{"id":"2303.10752","title":"Fully Self-Supervised Depth Estimation from Defocus Clue","created":"2023-03-19","cited_by_count":17},{"id":"2503.16067","title":"Bokehlicious: Photorealistic Bokeh Rendering with Controllable Apertures","created":"2025-03-20","cited_by_count":11},{"id":"2503.08434","title":"Bokeh Diffusion: Defocus Blur Control in Text-to-Image Diffusion Models","created":"2025-03-11","cited_by_count":10},{"id":"2306.04506","title":"Defocus to focus: Photo-realistic bokeh rendering by fusing defocus and radiance priors","created":"2023-06-07","cited_by_count":8},{"id":"2504.17787","title":"The Fourth Monocular Depth Estimation Challenge","created":"2025-04-24","cited_by_count":8},{"id":"2507.18060","title":"BokehDiff: Neural Lens Blur with One-Step Diffusion","created":"2025-07-24","cited_by_count":8},{"id":"1808.04446","title":"Visual Reasoning with Multi-hop Feature Modulation","created":"2018-08-03","cited_by_count":7},{"id":"2202.13055","title":"Deep Depth from Focal Stack with Defocus Model for Camera-Setting Invariance","created":"2022-02-26","cited_by_count":7},{"id":"2302.10730","title":"Depth Estimation and Image Restoration by Deep Learning from Defocused Images","created":"2023-02-21","cited_by_count":7},{"id":"2311.13045","title":"Camera-Independent Single Image Depth Estimation from Defocus Blur","created":"2023-11-21","cited_by_count":5},{"id":"2509.26599","title":"DiffCamera: Arbitrary Refocusing on Images","created":"2025-09-30","cited_by_count":5},{"id":"2503.23606","title":"Blurry-Edges: Photon-Limited Depth Estimation from Defocused Boundaries","created":"2025-03-30","cited_by_count":4},{"id":"2504.03738","title":"Attention in Diffusion Model: A Survey","created":"2025-04-01","cited_by_count":4},{"id":"2409.12323","title":"Depth Estimation Based on 3D Gaussian Splatting Siamese Defocus","created":"2024-09-18","cited_by_count":3}],"next_cursor":null}