{"list":"other","total":53,"rows":[{"id":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2304.02643","title":"Segment Anything","created":"2023-04-05","cited_by_count":8234},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2408.06072","title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","created":"2024-08-12","cited_by_count":2261},{"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":"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":"2508.02324","title":"Qwen-Image Technical Report","created":"2025-08-04","cited_by_count":1044},{"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":"2401.14159","title":"Grounded SAM: Assembling Open-World Models for Diverse Visual Tasks","created":"2024-01-25","cited_by_count":929},{"id":"2211.12572","title":"Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation","created":"2022-11-22","cited_by_count":906},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"2112.10003","title":"Image Segmentation Using Text and Image Prompts","created":"2021-12-18","cited_by_count":512},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2206.08916","title":"Unified-IO: A Unified Model for Vision, Language, and Multi-Modal Tasks","created":"2022-06-17","cited_by_count":421},{"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":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2110.04994","title":"Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scans","created":"2021-10-11","cited_by_count":336},{"id":"2312.04461","title":"PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding","created":"2023-12-07","cited_by_count":328},{"id":"2403.12013","title":"GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image","created":"2024-03-18","cited_by_count":286},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"2305.11147","title":"UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild","created":"2023-05-18","cited_by_count":200},{"id":"2206.13397","title":"Generative Modelling With Inverse Heat Dissipation","created":"2022-06-21","cited_by_count":167},{"id":"2405.00666","title":"RGB$\\leftrightarrow$X: Image decomposition and synthesis using material- and lighting-aware diffusion models","created":"2024-05-01","cited_by_count":161},{"id":"2406.16864","title":"StableNormal: Reducing Diffusion Variance for Stable and Sharp Normal","created":"2024-06-24","cited_by_count":154},{"id":"1805.01328","title":"Evaluation of CNN-based Single-Image Depth Estimation Methods","created":"2018-05-03","cited_by_count":138},{"id":"2011.11961","title":"MODNet: Real-Time Trimap-Free Portrait Matting via Objective Decomposition","created":"2020-11-24","cited_by_count":127},{"id":"2403.00712","title":"Rethinking Inductive Biases for Surface Normal Estimation","created":"2024-03-01","cited_by_count":124},{"id":"2312.06647","title":"4M: Massively Multimodal Masked Modeling","created":"2023-12-11","cited_by_count":120},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"2203.03041","title":"Highly Accurate Dichotomous Image Segmentation","created":"2022-03-06","cited_by_count":110},{"id":"2407.16655","title":"MovieDreamer: Hierarchical Generation for Coherent Long Visual Sequence","created":"2024-07-23","cited_by_count":89},{"id":"2409.11355","title":"Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think","created":"2024-09-17","cited_by_count":83},{"id":"2403.06090","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","created":"2024-03-10","cited_by_count":74},{"id":"1809.01354","title":"Semantic Human Matting","created":"2018-09-05","cited_by_count":67},{"id":"2305.01643","title":"Neural LiDAR Fields for Novel View Synthesis","created":"2023-05-02","cited_by_count":67},{"id":"2404.11593","title":"IntrinsicAnything: Learning Diffusion Priors for Inverse Rendering Under Unknown Illumination","created":"2024-04-17","cited_by_count":67},{"id":"2007.13215","title":"OASIS: A Large-Scale Dataset for Single Image 3D in the Wild","created":"2020-07-26","cited_by_count":62},{"id":"2002.00569","title":"DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data","created":"2020-02-03","cited_by_count":61},{"id":"2104.14222","title":"Privacy-Preserving Portrait Matting","created":"2021-04-29","cited_by_count":60},{"id":"1411.4958","title":"Designing Deep Networks for Surface Normal Estimation","created":"2014-11-18","cited_by_count":59},{"id":"2210.09670","title":"Hierarchical Normalization for Robust Monocular Depth Estimation","created":"2022-10-18","cited_by_count":52},{"id":"2502.17157","title":"DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks","created":"2025-02-24","cited_by_count":39},{"id":"1908.00894","title":"Pothole Detection Based on Disparity Transformation and Road Surface Modeling","created":"2019-08-02","cited_by_count":38},{"id":"2203.16828","title":"Rethinking Portrait Matting with Privacy Preserving","created":"2022-03-31","cited_by_count":25},{"id":"2410.18978","title":"Framer: Interactive Frame Interpolation","created":"2024-10-24","cited_by_count":24},{"id":"1506.03495","title":"BoWFire: Detection of Fire in Still Images by Integrating Pixel Color and Texture Analysis","created":"2015-06-10","cited_by_count":16},{"id":"2503.18363","title":"MonoInstance: Enhancing Monocular Priors via Multi-view Instance Alignment for Neural Rendering and Reconstruction","created":"2025-03-24","cited_by_count":15},{"id":"2405.00340","title":"NC-SDF: Enhancing Indoor Scene Reconstruction Using Neural SDFs with View-Dependent Normal Compensation","created":"2024-05-01","cited_by_count":5}],"next_cursor":null}