{"list":"other","total":77,"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":"1405.0312","title":"Microsoft COCO: Common Objects in Context","created":"2014-05-01","cited_by_count":17608},{"id":"2011.13456","title":"Score-Based Generative Modeling through Stochastic Differential Equations","created":"2020-11-26","cited_by_count":9122},{"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":"1604.01685","title":"The Cityscapes Dataset for Semantic Urban Scene Understanding","created":"2016-04-06","cited_by_count":4444},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"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":"1702.04405","title":"ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenes","created":"2017-02-14","cited_by_count":3117},{"id":"2408.00714","title":"SAM 2: Segment Anything in Images and Videos","created":"2024-08-01","cited_by_count":2863},{"id":"2211.09800","title":"InstructPix2Pix: Learning to Follow Image Editing Instructions","created":"2022-11-17","cited_by_count":2611},{"id":"2311.15127","title":"Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets","created":"2023-11-25","cited_by_count":2581},{"id":"2112.01527","title":"Masked-attention Mask Transformer for Universal Image Segmentation","created":"2021-12-02","cited_by_count":2351},{"id":"2204.03458","title":"Video Diffusion Models","created":"2022-04-07","cited_by_count":2305},{"id":"2103.13413","title":"Vision Transformers for Dense Prediction","created":"2021-03-24","cited_by_count":1803},{"id":"2210.02303","title":"Imagen Video: High Definition Video Generation with Diffusion Models","created":"2022-10-05","cited_by_count":1778},{"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":"2508.10104","title":"DINOv3","created":"2025-08-13","cited_by_count":1414},{"id":"2302.08453","title":"T2I-Adapter: Learning Adapters to Dig out More Controllable Ability for Text-to-Image Diffusion Models","created":"2023-02-16","cited_by_count":1351},{"id":"2210.09276","title":"Imagic: Text-Based Real Image Editing with Diffusion Models","created":"2022-10-17","cited_by_count":1178},{"id":"1804.08328","title":"Taskonomy: Disentangling Task Transfer Learning","created":"2018-04-23","cited_by_count":634},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"1802.00434","title":"DensePose: Dense Human Pose Estimation In The Wild","created":"2018-02-01","cited_by_count":575},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"2312.14125","title":"VideoPoet: A Large Language Model for Zero-Shot Video Generation","created":"2023-12-21","cited_by_count":492},{"id":"2306.03881","title":"Emergent Correspondence from Image Diffusion","created":"2023-06-06","cited_by_count":446},{"id":"2410.02073","title":"Depth Pro: Sharp Monocular Metric Depth in Less Than a Second","created":"2024-10-02","cited_by_count":404},{"id":"1905.04804","title":"Video Instance Segmentation","created":"2019-05-12","cited_by_count":393},{"id":"2001.10773","title":"Virtual KITTI 2","created":"2020-01-29","cited_by_count":353},{"id":"2204.01678","title":"MultiMAE: Multi-modal Multi-task Masked Autoencoders","created":"2022-04-04","cited_by_count":291},{"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":"2307.15055","title":"PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking","created":"2023-07-27","cited_by_count":276},{"id":"1908.00463","title":"DIODE: A Dense Indoor and Outdoor DEpth Dataset","created":"2019-08-01","cited_by_count":240},{"id":"1406.2031","title":"Detect What You Can: Detecting and Representing Objects using Holistic Models and Body Parts","created":"2014-06-08","cited_by_count":232},{"id":"2501.12375","title":"Video Depth Anything: Consistent Depth Estimation for Super-Long Videos","created":"2025-01-21","cited_by_count":207},{"id":"2303.01943","title":"Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo","created":"2023-03-03","cited_by_count":172},{"id":"2409.18124","title":"Lotus: Diffusion-based Visual Foundation Model for High-quality Dense Prediction","created":"2024-09-26","cited_by_count":166},{"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":"2403.00712","title":"Rethinking Inductive Biases for Surface Normal Estimation","created":"2024-03-01","cited_by_count":124},{"id":"2112.13762","title":"MSeg: A Composite Dataset for Multi-domain Semantic Segmentation","created":"2021-12-27","cited_by_count":122},{"id":"2203.01441","title":"3D Common Corruptions and Data Augmentation","created":"2022-03-02","cited_by_count":119},{"id":"2406.01493","title":"Learning Temporally Consistent Video Depth from Video Diffusion Priors","created":"2024-06-03","cited_by_count":100},{"id":"2203.07997","title":"InvPT: Inverted Pyramid Multi-task Transformer for Dense Scene Understanding","created":"2022-03-15","cited_by_count":89},{"id":"1809.00716","title":"InteriorNet: Mega-scale Multi-sensor Photo-realistic Indoor Scenes Dataset","created":"2018-09-03","cited_by_count":87},{"id":"1807.06667","title":"Accel: A Corrective Fusion Network for Efficient Semantic Segmentation on Video","created":"2018-07-17","cited_by_count":78},{"id":"2403.06090","title":"What Matters When Repurposing Diffusion Models for General Dense Perception Tasks?","created":"2024-03-10","cited_by_count":74},{"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":"2403.17749","title":"Multi-Task Dense Prediction via Mixture of Low-Rank Experts","created":"2024-03-26","cited_by_count":58},{"id":"2410.10815","title":"Depth Any Video with Scalable Synthetic Data","created":"2024-10-14","cited_by_count":57},{"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":"2307.15324","title":"TaskExpert: Dynamically Assembling Multi-Task Representations with Memorial Mixture-of-Experts","created":"2023-07-28","cited_by_count":45},{"id":"2409.13690","title":"Colorful Diffuse Intrinsic Image Decomposition in the Wild","created":"2024-09-20","cited_by_count":44},{"id":"2111.14893","title":"Learning Multiple Dense Prediction Tasks from Partially Annotated Data","created":"2021-11-29","cited_by_count":42},{"id":"2502.17157","title":"DICEPTION: A Generalist Diffusion Model for Visual Perceptual Tasks","created":"2025-02-24","cited_by_count":39},{"id":"2405.15757","title":"Looking Backward: Streaming Video-to-Video Translation with Feature Banks","created":"2024-05-24","cited_by_count":38},{"id":"2205.14354","title":"Multi-Task Learning with Multi-Query Transformer for Dense Prediction","created":"2022-05-28","cited_by_count":34},{"id":"1512.02311","title":"Direct Intrinsics: Learning Albedo-Shading Decomposition by Convolutional Regression","created":"2015-12-08","cited_by_count":33},{"id":"2303.14969","title":"Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching","created":"2023-03-27","cited_by_count":29},{"id":"2301.03461","title":"DeMT: Deformable Mixer Transformer for Multi-Task Learning of Dense Prediction","created":"2023-01-09","cited_by_count":27},{"id":"2504.11427","title":"NormalCrafter: Learning Temporally Consistent Normals from Video Diffusion Priors","created":"2025-04-15","cited_by_count":25},{"id":"2304.04694","title":"Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation","created":"2023-04-10","cited_by_count":24},{"id":"2207.10614","title":"A Dense Material Segmentation Dataset for Indoor and Outdoor Scene Parsing","created":"2022-07-21","cited_by_count":23},{"id":"2306.04842","title":"InvPT++: Inverted Pyramid Multi-Task Transformer for Visual Scene Understanding","created":"2023-06-08","cited_by_count":22},{"id":"2407.02228","title":"MTMamba: Enhancing Multi-Task Dense Scene Understanding by Mamba-Based Decoders","created":"2024-07-02","cited_by_count":22},{"id":"1705.01156","title":"Shading Annotations in the Wild","created":"2017-05-02","cited_by_count":19},{"id":"2403.15389","title":"DiffusionMTL: Learning Multi-Task Denoising Diffusion Model from Partially Annotated Data","created":"2024-03-22","cited_by_count":18},{"id":"2307.15362","title":"Prompt Guided Transformer for Multi-Task Dense Prediction","created":"2023-07-28","cited_by_count":13},{"id":"2503.09344","title":"Unified Dense Prediction of Video Diffusion","created":"2025-03-12","cited_by_count":13},{"id":"2502.13078","title":"L4P: Towards Unified Low-Level 4D Vision Perception","created":"2025-02-18","cited_by_count":12},{"id":"2408.15101","title":"MTMamba++: Enhancing Multi-Task Dense Scene Understanding via Mamba-Based Decoders","created":"2024-08-27","cited_by_count":10},{"id":"2309.04422","title":"Video Task Decathlon: Unifying Image and Video Tasks in Autonomous Driving","created":"2023-09-08","cited_by_count":8},{"id":"2404.18459","title":"Chameleon: A Data-Efficient Generalist for Dense Visual Prediction in the Wild","created":"2024-04-29","cited_by_count":6},{"id":"2506.20279","title":"From Ideal to Real: Unified and Data-Efficient Dense Prediction for Real-World Scenarios","created":"2025-06-25","cited_by_count":3},{"id":"2506.08013","title":"StableMTL: Repurposing Latent Diffusion Models for Multi-Task Learning from Partially Annotated Synthetic Datasets","created":"2025-06-09","cited_by_count":2}],"next_cursor":null}