{"list":"other","total":52,"rows":[{"id":"1706.03762","title":"Attention Is All You Need","created":"2017-06-12","cited_by_count":60361},{"id":"2103.00020","title":"Learning Transferable Visual Models From Natural Language Supervision","created":"2021-02-26","cited_by_count":33744},{"id":"2010.11929","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","created":"2020-10-22","cited_by_count":30186},{"id":"2112.10752","title":"High-Resolution Image Synthesis with Latent Diffusion Models","created":"2021-12-20","cited_by_count":18863},{"id":"2304.07193","title":"DINOv2: Learning Robust Visual Features without Supervision","created":"2023-04-14","cited_by_count":7974},{"id":"2111.06377","title":"Masked Autoencoders Are Scalable Vision Learners","created":"2021-11-11","cited_by_count":7403},{"id":"2212.09748","title":"Scalable Diffusion Models with Transformers","created":"2022-12-19","cited_by_count":6054},{"id":"2403.03206","title":"Scaling Rectified Flow Transformers for High-Resolution Image Synthesis","created":"2024-03-05","cited_by_count":4181},{"id":"2111.09881","title":"Restormer: Efficient Transformer for High-Resolution Image Restoration","created":"2021-11-18","cited_by_count":1627},{"id":"2312.14132","title":"DUSt3R: Geometric 3D Vision Made Easy","created":"2023-12-21","cited_by_count":1567},{"id":"2503.11651","title":"VGGT: Visual Geometry Grounded Transformer","created":"2025-03-14","cited_by_count":1539},{"id":"1712.07629","title":"SuperPoint: Self-Supervised Interest Point Detection and Description","created":"2017-12-20","cited_by_count":1320},{"id":"2502.14786","title":"SigLIP 2: Multilingual Vision-Language Encoders with Improved Semantic Understanding, Localization, and Dense Features","created":"2025-02-20","cited_by_count":1188},{"id":"2104.00680","title":"LoFTR: Detector-Free Local Feature Matching with Transformers","created":"2021-04-01","cited_by_count":984},{"id":"2406.09756","title":"Grounding Image Matching in 3D with MASt3R","created":"2024-06-14","cited_by_count":983},{"id":"2308.11417","title":"ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenes","created":"2023-08-22","cited_by_count":764},{"id":"1612.02177","title":"Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring","created":"2016-12-07","cited_by_count":727},{"id":"2511.10647","title":"Depth Anything 3: Recovering the Visual Space from Any Views","created":"2025-11-13","cited_by_count":692},{"id":"2011.02523","title":"Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding","created":"2020-11-04","cited_by_count":604},{"id":"1710.04026","title":"FFDNet: Toward a Fast and Flexible Solution for CNN based Image Denoising","created":"2017-10-11","cited_by_count":510},{"id":"2003.14338","title":"TartanAir: A Dataset to Push the Limits of Visual SLAM","created":"2020-03-31","cited_by_count":506},{"id":"2501.01423","title":"Reconstruction vs. Generation: Taming Optimization Dilemma in Latent Diffusion Models","created":"2025-01-02","cited_by_count":393},{"id":"2507.13347","title":"$\\pi^3$: Permutation-Equivariant Visual Geometry Learning","created":"2025-07-17","cited_by_count":319},{"id":"2510.11690","title":"Diffusion Transformers with Representation Autoencoders","created":"2025-10-13","cited_by_count":295},{"id":"2308.15070","title":"DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior","created":"2023-08-29","cited_by_count":257},{"id":"2201.12288","title":"VRT: A Video Restoration Transformer","created":"2022-01-28","cited_by_count":220},{"id":"1910.02490","title":"Kimera: an Open-Source Library for Real-Time Metric-Semantic Localization and Mapping","created":"2019-10-06","cited_by_count":184},{"id":"2401.16468","title":"InstructIR: High-Quality Image Restoration Following Human Instructions","created":"2024-01-29","cited_by_count":140},{"id":"2504.05741","title":"DDT: Decoupled Diffusion Transformer","created":"2025-04-08","cited_by_count":109},{"id":"2305.12966","title":"Hierarchical Integration Diffusion Model for Realistic Image Deblurring","created":"2023-05-22","cited_by_count":88},{"id":"2411.18466","title":"Complexity Experts are Task-Discriminative Learners for Any Image Restoration","created":"2024-11-27","cited_by_count":77},{"id":"2410.15067","title":"A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends","created":"2024-10-19","cited_by_count":60},{"id":"2503.23580","title":"DiT4SR: Taming Diffusion Transformer for Real-World Image Super-Resolution","created":"2025-03-30","cited_by_count":53},{"id":"2601.16208","title":"Scaling Text-to-Image Diffusion Transformers with Representation Autoencoders","created":"2026-01-22","cited_by_count":53},{"id":"2107.07596","title":"Depth Estimation from Monocular Images and Sparse radar using Deep Ordinal Regression Network","created":"2021-07-15","cited_by_count":33},{"id":"2506.17220","title":"Emergent Temporal Correspondences from Video Diffusion Transformers","created":"2025-06-20","cited_by_count":31},{"id":"2412.09072","title":"Cross-View Completion Models are Zero-shot Correspondence Estimators","created":"2024-12-12","cited_by_count":30},{"id":"2401.03707","title":"FMA-Net: Flow-Guided Dynamic Filtering and Iterative Feature Refinement with Multi-Attention for Joint Video Super-Resolution and Deblurring","created":"2024-01-08","cited_by_count":28},{"id":"2601.17895","title":"Masked Depth Modeling for Spatial Perception","created":"2026-01-25","cited_by_count":28},{"id":"2512.04012","title":"Emergent Outlier View Rejection in Visual Geometry Grounded Transformers","created":"2025-12-03","cited_by_count":22},{"id":"2603.22275","title":"Repurposing Geometric Foundation Models for Multi-view Diffusion","created":"2026-03-23","cited_by_count":15},{"id":"2212.00654","title":"maplab 2.0 -- A Modular and Multi-Modal Mapping Framework","created":"2022-12-01","cited_by_count":14},{"id":"2405.13218","title":"Computational Tradeoffs in Image Synthesis: Diffusion, Masked-Token, and Next-Token Prediction","created":"2024-05-21","cited_by_count":13},{"id":"2602.10099","title":"Learning on the Manifold: Unlocking Standard Diffusion Transformers with Representation Encoders","created":"2026-02-10","cited_by_count":13},{"id":"2008.05938","title":"RGB cameras failures and their effects in autonomous driving applications","created":"2020-08-13","cited_by_count":12},{"id":"2310.11031","title":"Domain Generalization Using Large Pretrained Models with Mixture-of-Adapters","created":"2023-10-17","cited_by_count":11},{"id":"2512.03045","title":"CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models","created":"2025-12-02","cited_by_count":10},{"id":"2506.09993","title":"Text-Aware Image Restoration with Diffusion Models","created":"2025-06-11","cited_by_count":6},{"id":"2404.01703","title":"Boosting Visual Recognition in Real-world Degradations via Unsupervised Feature Enhancement Module with Deep Channel Prior","created":"2024-04-02","cited_by_count":5},{"id":"2503.14463","title":"SIR-DIFF: Sparse Image Sets Restoration with Multi-View Diffusion Model","created":"2025-03-18","cited_by_count":5},{"id":"2512.08922","title":"Unified Diffusion Transformer for High-fidelity Text-Aware Image Restoration","created":"2025-12-09","cited_by_count":3},{"id":"2507.08375","title":"Unsupervised Methods for Video Quality Improvement: A Survey of Restoration and Enhancement Techniques","created":"2025-07-11","cited_by_count":1}],"next_cursor":null}