{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T16:32:03Z","timestamp":1776357123434,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":44,"publisher":"ACM","funder":[{"name":"NSF (National Science Foundation)","award":["2236987"],"award-info":[{"award-number":["2236987"]}]},{"DOI":"10.13039\/100000001","name":"NSF (National Science Foundation)","doi-asserted-by":"publisher","award":["2346133"],"award-info":[{"award-number":["2346133"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,4]]},"DOI":"10.1145\/3793853.3795748","type":"proceedings-article","created":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T14:25:49Z","timestamp":1775485549000},"page":"72-83","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AR as an Evaluation Playground: Bridging Metric and Visual Perception of Computer Vision Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3490-0471","authenticated-orcid":false,"given":"Ashkan","family":"Ganj","sequence":"first","affiliation":[{"name":"Computer Science, Worcester Polytechnic Institute, Worcester, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1044-4732","authenticated-orcid":false,"given":"Yiqin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Rochester Institute of Technology, Rochester, New York, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0060-2266","authenticated-orcid":false,"given":"Tian","family":"Guo","sequence":"additional","affiliation":[{"name":"Computer Science, Worcester Polytechnic Institute, Worcester, Massachusetts, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,6]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2025. COCO Detection Evaluation. https:\/\/cocodataset.org\/#detection-eval. Accessed: 2025-06-16."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","unstructured":"2025. Multimodal Object Detection Using Depth and Image Data for Manufacturing Parts. arXiv:https:\/\/asmedigitalcollection.asme.org\/MSEC\/proceedings-pdf\/MSEC2025\/89022\/V002T16A001\/7543143\/v002t16a001-msec2025-155144.pdf doi:10.1115\/MSEC2025-155144","DOI":"10.1115\/MSEC2025-155144"},{"key":"e_1_3_2_1_3_1","unstructured":"Apple. 2017. https:\/\/developer.apple.com\/augmented-reality\/."},{"key":"e_1_3_2_1_4_1","unstructured":"Gilad Baruch Zhuoyuan Chen Afshin Dehghan Tal Dimry Yuri Feigin Peter Fu Thomas Gebauer Brandon Joffe Daniel Kurz Arik Schwartz and Elad Shulman. 2021. ARKitScenes - A Diverse Real-World Dataset For 3D Indoor Scene Understanding Using Mobile RGB-D Data. In NeurIPS. https:\/\/arxiv.org\/pdf\/2111.08897.pdf"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","unstructured":"Shariq Farooq Bhat Reiner Birkl Diana Wofk Peter Wonka and Matthias M\u00fcller. 2023. ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depth. doi:10.48550\/ARXIV.2302.12288","DOI":"10.48550\/ARXIV.2302.12288"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3327396"},{"key":"e_1_3_2_1_7_1","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/openreview.net\/forum?id=SSKZPJCt7B","author":"Croce Francesco","year":"2021","unstructured":"Francesco Croce, Maksym Andriushchenko, Vikash Sehwag, Edoardo Debenedetti, Nicolas Flammarion, Mung Chiang, Prateek Mittal, and Matthias Hein. 2021. RobustBench: a standardized adversarial robustness benchmark. In Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track. https:\/\/openreview.net\/forum?id=SSKZPJCt7B"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00104"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3615452.3617941"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3638550.3641122"},{"key":"e_1_3_2_1_12_1","volume-title":"Learning to Predict Indoor Illumination from a Single Image. ACM Transactions on Graphics","author":"Gardner Marc-Andr\u00e9","year":"2017","unstructured":"Marc-Andr\u00e9 Gardner, Kalyan Sunkavalli, Ersin Yumer, Xiaohui Shen, Emiliano Gambaretto, Christian Gagn\u00e9, and Jean-Fran\u00e7ois Lalonde. 2017. Learning to Predict Indoor Illumination from a Single Image. ACM Transactions on Graphics (2017)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00422"},{"key":"e_1_3_2_1_14_1","volume-title":"CoMIC: A Collaborative Mobile Immersive Computing Infrastructure for Conducting Multi-user XR Research","author":"Han Bo","year":"2022","unstructured":"Bo Han, Parth Pathak, Songqing Chen, and Lap-Fai Craig Yu. 2022. CoMIC: A Collaborative Mobile Immersive Computing Infrastructure for Conducting Multi-user XR Research. IEEE Netw. (2022), 1\u20139."},{"key":"e_1_3_2_1_15_1","volume-title":"ILLIXR: Enabling End-to-End Extended Reality Research. In 2021 IEEE International Symposium on Workload Characterization (IISWC). 24\u201338","author":"Huzaifa Muhammad","year":"2021","unstructured":"Muhammad Huzaifa, Rishi Desai, Samuel Grayson, Xutao Jiang, Ying Jing, Jae Lee, Fang Lu, Yihan Pang, Joseph Ravichandran, Finn Sinclair, Boyuan Tian, Hengzhi Yuan, Jeffrey Zhang, and Sarita V Adve. 2021. ILLIXR: Enabling End-to-End Extended Reality Research. In 2021 IEEE International Symposium on Workload Characterization (IISWC). 24\u201338."},{"key":"e_1_3_2_1_16_1","volume-title":"TOM: A Development Platform For Wearable Intelligent Assistants. In Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing. 837\u2013843","author":"Janaka Nuwan","year":"2024","unstructured":"Nuwan Janaka, Shengdong Zhao, David Hsu, Sherisse Tan Jing Wen, and Chun Keat Koh. 2024. TOM: A Development Platform For Wearable Intelligent Assistants. In Companion of the 2024 on ACM International Joint Conference on Pervasive and Ubiquitous Computing. 837\u2013843."},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of Machine Learning and Systems","volume":"5","author":"Kwon Hyoukjun","year":"2023","unstructured":"Hyoukjun Kwon, Krishnakumar Nair, Jamin Seo, Jason Yik, Debabrata Mohap-atra, Dongyuan Zhan, Jinook Song, Peter Capak, Peizhao Zhang, Peter Vajda, Colby Banbury, Mark Mazumder, Liangzhen Lai, Ashish Sirasao, Tushar Krishna, Harshit Khaitan, Vikas Chandra, and Vijay Janapa Reddi. 2023. XRBench: An extended reality (XR) machine learning benchmark suite for the metaverse. In Proceedings of Machine Learning and Systems, Vol. 5."},{"key":"e_1_3_2_1_18_1","volume-title":"Dong Wook Ko, and Il Hong Suh","author":"Lee Jin Han","year":"2019","unstructured":"Jin Han Lee, Myung-Kyu Han, Dong Wook Ko, and Il Hong Suh. 2019. From big to small: Multi-scale local planar guidance for monocular depth estimation. arXiv preprint arXiv:1907.10326 (2019)."},{"key":"e_1_3_2_1_19_1","volume-title":"BenchDepth: Are We on the Right Way to Evaluate Depth Foundation Models? arXiv preprint arXiv:2507.15321","author":"Li Zhenyu","year":"2025","unstructured":"Zhenyu Li, Haotong Lin, Jiashi Feng, Peter Wonka, and Bingyi Kang. 2025. BenchDepth: Are We on the Right Way to Evaluate Depth Foundation Models? arXiv preprint arXiv:2507.15321 (2025)."},{"key":"e_1_3_2_1_20_1","unstructured":"Jiahao Lu Tianyu Huang Peng Li Zhiyang Dou Cheng Lin Zhiming Cui Zhen Dong Sai-Kit Yeung Wenping Wang and Yuan Liu. 2025. Align3R: Aligned Monocular Depth Estimation for Dynamic Videos. In Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00115"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00471"},{"key":"e_1_3_2_1_23_1","volume-title":"Derek Hoiem and Rob Fergus","author":"Nathan Silberman Pushmeet Kohli","year":"2012","unstructured":"Pushmeet Kohli Nathan Silberman, Derek Hoiem and Rob Fergus. 2012. Indoor Segmentation and Support Inference from RGBD Images. In ECCV."},{"key":"e_1_3_2_1_24_1","volume-title":"Too Hot To Be True: Temperature Calibration for Higher Confidence in NN-assisted Side-channel Analysis. Cryptology ePrint Archive","author":"Nouraniboosjin Seyedmohammad","year":"2024","unstructured":"Seyedmohammad Nouraniboosjin and Fatemeh Ganji. 2024. Too Hot To Be True: Temperature Calibration for Higher Confidence in NN-assisted Side-channel Analysis. Cryptology ePrint Archive (2024)."},{"key":"e_1_3_2_1_25_1","unstructured":"Seyedmohammad Nouraniboosjin and Fatameh Ganji. 2025. Uncertainty estimation in neural network-enabled side-channel analysis and links to explainability. (2025)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Pakkapon Phongthawee Worameth Chinchuthakun Nontaphat Sinsunthithet Amit Raj Varun Jampani Pramook Khungurn and Supasorn Suwajanakorn. 2023. DiffusionLight: Light Probes for Free by Painting a Chrome Ball. In ArXiv.","DOI":"10.1109\/CVPR52733.2024.00018"},{"key":"e_1_3_2_1_27_1","volume-title":"UniDepth: Universal Monocular Metric Depth Estimation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Piccinelli Luigi","year":"2024","unstructured":"Luigi Piccinelli, Yung-Hsu Yang, Christos Sakaridis, Mattia Segu, Siyuan Li, Luc Van Gool, and Fisher Yu. 2024. UniDepth: Universal Monocular Metric Depth Estimation. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3561160"},{"key":"e_1_3_2_1_29_1","volume-title":"Vision Transformers for Dense Prediction. ArXiv preprint","author":"Ranftl Ren\u00e9","year":"2021","unstructured":"Ren\u00e9 Ranftl, Alexey Bochkovskiy, and Vladlen Koltun. 2021. Vision Transformers for Dense Prediction. ArXiv preprint (2021)."},{"key":"e_1_3_2_1_30_1","volume-title":"Learning Multi-Arm Manipulation Through Collaborative Teleoperation. In 2021 IEEE International Conference on Robotics and Automation (ICRA). 9212\u20139219","author":"Tung Albert","year":"2021","unstructured":"Albert Tung, Josiah Wong, Ajay Mandlekar, Roberto Mart\u00edn-Mart\u00edn, Yuke Zhu, Li Fei-Fei, and Silvio Savarese. 2021. Learning Multi-Arm Manipulation Through Collaborative Teleoperation. In 2021 IEEE International Conference on Robotics and Automation (ICRA). 9212\u20139219."},{"key":"e_1_3_2_1_31_1","volume-title":"StyleLight: HDR Panorama Generation for Lighting Estimation and Editing. In European Conference on Computer Vision (ECCV).","author":"Wang Guangcong","year":"2022","unstructured":"Guangcong Wang, Yinuo Yang, Chen Change Loy, and Ziwei Liu. 2022. StyleLight: HDR Panorama Generation for Lighting Estimation and Editing. In European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00874"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISMAR62088.2024.00063"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581500"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 21880\u201321890","author":"Yan Weilong","unstructured":"Weilong Yan, Ming Li, Haipeng Li, Shuwei Shao, and Robby T. Tan. 2025. Synthetic-to-Real Self-supervised Robust Depth Estimation via Learning with Motion and Structure Priors. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 21880\u201321890."},{"key":"e_1_3_2_1_36_1","volume-title":"Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. In CVPR.","author":"Yang Lihe","year":"2024","unstructured":"Lihe Yang, Bingyi Kang, Zilong Huang, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. 2024. Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. In CVPR."},{"key":"e_1_3_2_1_37_1","volume-title":"Depth Anything V2. arXiv:2406.09414","author":"Yang Lihe","year":"2024","unstructured":"Lihe Yang, Bingyi Kang, Zilong Huang, Zhen Zhao, Xiaogang Xu, Jiashi Feng, and Hengshuang Zhao. 2024. Depth Anything V2. arXiv:2406.09414 (2024)."},{"key":"e_1_3_2_1_38_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). In press.","author":"Sun Zitang","year":"2025","unstructured":"Yung-hao Yang, Zitang Sun, Taiki Fukiage, and Shin'ya Nishida. 2025. HuPer-Flow: A Comprehensive Benchmark for Human vs. Machine Motion Estimation Comparison. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). In press."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419192"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139486"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"crossref","unstructured":"Richard Zhang Phillip Isola Alexei A. Efros Eli Shechtman and Oliver Wang. 2018. The Unreasonable Effectiveness of Deep Features as a Perceptual Metric. arXiv:1801.03924 [cs.CV] https:\/\/arxiv.org\/abs\/1801.03924","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458864.3467886"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3638550.3643617"},{"key":"e_1_3_2_1_44_1","volume-title":"Li Fei-Fei, and Michael S Bernstein.","author":"Zhou Sharon","year":"2019","unstructured":"Sharon Zhou, Mitchell L Gordon, Ranjay Krishna, Austin Narcomey, Li Fei-Fei, and Michael S Bernstein. 2019. HYPE: A benchmark for Human eYe Perceptual Evaluation of generative models. arXiv [cs.CV] (April 2019)."}],"event":{"name":"MMSys '26: ACM Multimedia Systems Conference 2026","location":"Hong Kong Hong Kong","acronym":"MMSys '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the ACM Multimedia Systems Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3793853.3795748","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T15:24:48Z","timestamp":1776353088000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3793853.3795748"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,4]]},"references-count":44,"alternative-id":["10.1145\/3793853.3795748","10.1145\/3793853"],"URL":"https:\/\/doi.org\/10.1145\/3793853.3795748","relation":{},"subject":[],"published":{"date-parts":[[2026,4,4]]},"assertion":[{"value":"2026-04-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}