{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T14:01:09Z","timestamp":1790949669856,"version":"4.1.0"},"reference-count":56,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T00:00:00Z","timestamp":1790899200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>We present MultiNet, a multi-branch pipeline that directly predicts the gaze vector or the point of gaze from multiple modalities derived from a single camera capture. In particular, we address the under-explored use of metric face-to-camera distance estimated from a conventional RGB web camera for appearance-based gaze estimation, in contrast to many distance-aware alternatives which require depth sensors, stereo rigs, or additional hardware. The proposed method employs a convolutional neural network (CNN) with attentional feature fusion and integrates cropped face images, left and right eye patches, head-pose information, and estimated camera-to-face distance. We also introduce NLGaze, a 141,000-image dataset collected for unconstrained and natural desktop settings, thereby emphasizing real-world applicability. In a person-specific real-time evaluation, MultiNet-Base reaches a root mean square error (RMSE) of 43.01 pixels at 15 frames per second (FPS) on a desktop with an off-the-shelf web-camera. We evaluate the proposed method against representative state-of-the-art solutions on benchmark datasets. MultiNet achieves angular errors of 2.94\u00b0, 7.47\u00b0, and 7.58\u00b0 at best on the MPIIFaceGaze, Gaze360, and NLGaze datasets, respectively, demonstrating competitive or superior performance in appearance-based gaze estimation. The results of the ablation study show that the attentional feature fusion mechanism and the addition of the estimated distance input to the set of input modalities result in significant angular error reduction.<\/jats:p>","DOI":"10.3390\/s26196265","type":"journal-article","created":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T13:39:34Z","timestamp":1790948374000},"page":"6265","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MultiNet: Improving Gaze Estimation via Face-to-Camera Distance and Multi-Branch Learning"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2998-9154","authenticated-orcid":false,"given":"Nikita","family":"Ligostaev","sequence":"first","affiliation":[{"name":"Center for Engineering Systems and Sciences, Moscow 121205, Russia"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"methodology","vocabulary":"credit"},{"role":"software","vocabulary":"credit"},{"role":"data-curation","vocabulary":"credit"},{"role":"validation","vocabulary":"credit"},{"role":"writing-original-draft","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"visualization","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7858-0928","authenticated-orcid":false,"given":"Nicola","family":"Conci","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6315-1023","authenticated-orcid":false,"given":"Roberto","family":"Passerone","sequence":"additional","affiliation":[{"name":"Department of Information Engineering and Computer Science, University of Trento, 38123 Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"methodology","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4615-3008","authenticated-orcid":false,"given":"Andrey","family":"Somov","sequence":"additional","affiliation":[{"name":"Center for Engineering Systems and Sciences, Moscow 121205, Russia"},{"name":"Central University, Moscow 123056, Russia"}],"role":[{"vocabulary":"crossref","role":"author"},{"role":"conceptualization","vocabulary":"credit"},{"role":"writing-review-editing","vocabulary":"credit"},{"role":"supervision","vocabulary":"credit"}]}],"member":"1968","published-online":{"date-parts":[[2026,10,2]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Li, C., Li, F., Zhang, K., Chen, N., and Pan, Z. (2025). Gaze estimation network based on multi-head attention, fusion, and interaction. Sensors, 25.","DOI":"10.3390\/s25061893"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bendimered, A., Iguernaissi, R., Nawaf, M.M., Cherif, R., Dubuisson, S., and Merad, D. (2025). Dual focus-3D: A hybrid deep learning approach for robust 3D gaze estimation. Sensors, 25.","DOI":"10.3390\/s25134086"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1109\/TBME.1974.324318","article-title":"Remote Measurement of Eye Direction Allowing Subject Motion Over One Cubic Foot of Space","volume":"BME-21","author":"Merchant","year":"1974","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"921","DOI":"10.1364\/JOSA.63.000921","article-title":"Accurate two-dimensional eye tracker using first and fourth Purkinje images","volume":"63","author":"Cornsweet","year":"1973","journal-title":"JOSA"},{"key":"ref_5","unstructured":"Park, S., Aksan, E., Zhang, X., and Hilliges, O. (2020). Towards end-to-end video-based eye-tracking. Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part XII 16, Springer."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Shen, J., Dong, P., Hu, B., and Wang, Y. (2026). Lightweight Geometric Framework for High-Precision 3D Gaze Tracking Based on Infrared Image Processing. Sensors, 26.","DOI":"10.3390\/s26123741"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"67","DOI":"10.3758\/s13428-013-0343-0","article-title":"Eye-tracking data quality as affected by ethnicity and experimental design","volume":"46","author":"Blignaut","year":"2014","journal-title":"Behav. Res. Methods"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"K\u00fcbler, T.C., Rittig, T., Kasneci, E., Ungewiss, J., and Krauss, C. (2016). Rendering refraction and reflection of eyeglasses for synthetic eye tracker images. Proceedings of the Ninth Biennial ACM Symposium on Eye Tracking Research & Applications, Association for Computing Machinery.","DOI":"10.1145\/2857491.2857494"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.16910\/jemr.8.5.1","article-title":"Eye tracking in the wild: The good, the bad and the ugly","volume":"8","author":"Lappi","year":"2015","journal-title":"J. Eye Mov. Res."},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Krafka, K., Khosla, A., Kellnhofer, P., Kannan, H., Bhandarkar, S., Matusik, W., and Torralba, A. (2016). Eye Tracking for Everyone. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE.","DOI":"10.1109\/CVPR.2016.239"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"5259","DOI":"10.1109\/TIP.2020.2982828","article-title":"Gaze estimation by exploring two-eye asymmetry","volume":"29","author":"Cheng","year":"2020","journal-title":"IEEE Trans. Image Process."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Balim, H., Park, S., Wang, X., Zhang, X., and Hilliges, O. (2023). Efe: End-to-end frame-to-gaze estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPRW59228.2023.00269"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"162","DOI":"10.1109\/TPAMI.2017.2778103","article-title":"Mpiigaze: Real-world dataset and deep appearance-based gaze estimation","volume":"41","author":"Zhang","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Zhang, X., Park, S., Beeler, T., Bradley, D., Tang, S., and Hilliges, O. (2020). Eth-xgaze: A large scale dataset for gaze estimation under extreme head pose and gaze variation. Proceedings of the Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, 23\u201328 August 2020, Proceedings, Part V 16, Springer.","DOI":"10.1007\/978-3-030-58558-7_22"},{"key":"ref_15","unstructured":"Yin, P., Wang, J., Zeng, G., Xie, D., and Zhu, J. Lg-gaze: Learning geometry-aware continuous prompts for language-guided gaze estimation. Proceedings of the European Conference on Computer Vision, Springer."},{"key":"ref_16","first-page":"9780","article-title":"Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation","volume":"39","author":"Zeng","year":"2025","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Yin, P., Zeng, G., Wang, J., and Xie, D. (2024). CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model. Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence and Thirty-Sixth Conference on Innovative Applications of Artificial Intelligence and Fourteenth Symposium on Educational Advances in Artificial Intelligence, AAAI Press.","DOI":"10.1609\/aaai.v38i7.28496"},{"key":"ref_18","first-page":"2488","article-title":"RGBD based gaze estimation via multi-task CNN","volume":"33","author":"Lian","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Liwan, L., Zongyu, W., Lu, Y., Chen, Z., and Weijie, G. (2025). Recent Progress on Eye-Tracking and Gaze Estimation for AR\/VR Applications: A Review. Electronics, 14.","DOI":"10.3390\/electronics14173352"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sugano, Y., Fritz, M., and Bulling, A. (2017). It\u2019s written all over your face: Full-face appearance-based gaze estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, IEEE.","DOI":"10.1109\/CVPRW.2017.284"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Ligostaev, N., Conci, N., Passerone, R., and Somov, A. (2025). Real-time Appearance-based Gaze Estimation via Web-Camera. Proceedings of the IEEE International Instrumentation and Measurement Technology Conference (I2MTC), IEEE.","DOI":"10.1109\/I2MTC62753.2025.11079227"},{"key":"ref_22","unstructured":"Deja, S. (2010). Real-Time System for Eye Detection and Tracking of Computer User Using Webcam. [Master\u2019s Thesis, AGH University of Science and Technology]."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Wood, E., and Bulling, A. (2014). Eyetab: Model-based gaze estimation on unmodified tablet computers. Proceedings of the Symposium on Eye Tracking Research and Applications, Association for Computing Machinery.","DOI":"10.1145\/2578153.2578185"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wood, E., Baltrusaitis, T., Zhang, X., Sugano, Y., Robinson, P., and Bulling, A. (2015). Rendering of eyes for eye-shape registration and gaze estimation. Proceedings of the IEEE International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2015.428"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Wang, K., and Ji, Q. (2017). Real time eye gaze tracking with 3d deformable eye-face model. Proceedings of the IEEE International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2017.114"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Park, S., Spurr, A., and Hilliges, O. (2018). Deep pictorial gaze estimation. Proceedings of the European Conference on Computer Vision (ECCV), Springer International Publishing.","DOI":"10.1007\/978-3-030-01261-8_44"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Funes Mora, K.A., Monay, F., and Odobez, J.M. (2014). Eyediap: A database for the development and evaluation of gaze estimation algorithms from rgb and rgb-d cameras. Proceedings of the Symposium on Eye Tracking Research and Applications, Association for Computing Machinery.","DOI":"10.1145\/2578153.2578190"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Kellnhofer, P., Recasens, A., Stent, S., Matusik, W., and Torralba, A. (2019). Gaze360: Physically unconstrained gaze estimation in the wild. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2019.00701"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"2033","DOI":"10.1109\/TPAMI.2014.2313123","article-title":"Adaptive Linear Regression for Appearance-Based Gaze Estimation","volume":"36","author":"Lu","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Sugano, Y., Matsushita, Y., and Sato, Y. (2014). Learning-by-synthesis for appearance-based 3d gaze estimation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2014.235"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Chen, Z., and Shi, B.E. (2018). Appearance-based gaze estimation using dilated-convolutions. Proceedings of the Asian Conference on Computer Vision, Springer.","DOI":"10.1007\/978-3-030-20876-9_20"},{"key":"ref_32","first-page":"10623","article-title":"A coarse-to-fine adaptive network for appearance-based gaze estimation","volume":"34","author":"Cheng","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Kim, J.H., and Jeong, J.W. (2020). Gaze estimation in the dark with generative adversarial networks. Proceedings of the ACM Symposium on Eye Tracking Research and Applications, Association for Computing Machinery.","DOI":"10.1145\/3379157.3391654"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"He, J., Pham, K., Valliappan, N., Xu, P., Roberts, C., Lagun, D., and Navalpakkam, V. (2019). On-device few-shot personalization for real-time gaze estimation. Proceedings of the IEEE\/CVF International Conference on Computer Vision Workshops, IEEE.","DOI":"10.1109\/ICCVW.2019.00146"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Park, S., Mello, S.D., Molchanov, P., Iqbal, U., Hilliges, O., and Kautz, J. (2019). Few-shot adaptive gaze estimation. Proceedings of the IEEE\/CVF International Conference on Computer Vision, IEEE.","DOI":"10.1109\/ICCV.2019.00946"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"8450","DOI":"10.1109\/JSEN.2024.3359085","article-title":"Gaze Estimation Based on the Improved Xception Network","volume":"24","author":"Luo","year":"2024","journal-title":"IEEE Sens. J."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Ansari, M.F., Kasprowski, P., and Peer, P. (2023). Person-specific gaze estimation from low-quality webcam images. Sensors, 23.","DOI":"10.3390\/s23084138"},{"key":"ref_38","first-page":"436","article-title":"Puregaze: Purifying gaze feature for generalizable gaze estimation","volume":"36","author":"Cheng","year":"2022","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Park, J., Park, S., and Cha, H. (2021). Gazel: Runtime gaze tracking for smartphones. Proceedings of the 2021 IEEE International Conference on Pervasive Computing and Communications (PerCom), IEEE.","DOI":"10.1109\/PERCOM50583.2021.9439113"},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Alberto Funes Mora, K., and Odobez, J.M. (2014). Geometric generative gaze estimation (g3e) for remote rgb-d cameras. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2014.229"},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Zhang, M., Liu, Y., and Lu, F. (2022). GazeOnce: Real-Time Multi-Person Gaze Estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), June 2022, IEEE.","DOI":"10.1109\/CVPR52688.2022.00416"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Wang, H., Zhang, Z., Yue, Y., Kim, B., Lu, F., and Chang, H.J. (2025). 3D Prior Is All You Need: Cross-Task Few-shot 2D Gaze Estimation. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, TN, USA, 11\u201315 June 2025, IEEE.","DOI":"10.1109\/CVPR52734.2025.02225"},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Kim, J., Stengel, M., Majercik, A., De Mello, S., Dunn, D., Laine, S., McGuire, M., and Luebke, D. (2019). Nvgaze: An anatomically-informed dataset for low-latency, near-eye gaze estimation. Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems, Association for Computing Machinery.","DOI":"10.1145\/3290605.3300780"},{"key":"ref_44","doi-asserted-by":"crossref","unstructured":"Fischer, T., Chang, H.J., and Demiris, Y. (2018). Rt-gene: Real-time eye gaze estimation in natural environments. Proceedings of the European Conference on Computer Vision (ECCV), Springer.","DOI":"10.1007\/978-3-030-01249-6_21"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"11","DOI":"10.2197\/ipsjtcva.8.11","article-title":"Mirror-based camera pose estimation using an orthogonality constraint","volume":"8","author":"Takahashi","year":"2016","journal-title":"IPSJ Trans. Comput. Vis. Appl."},{"key":"ref_46","unstructured":"Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.L., Yong, M.G., and Lee, J. (2019). Mediapipe: A framework for building perception pipelines. arXiv."},{"key":"ref_47","unstructured":"Wang, Y., Shi, X., De Mello, S., Chang, H.J., and Zhang, X. (2023). Investigation of Architectures and Receptive Fields for Appearance-based Gaze Estimation. arXiv."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Dai, Y., Gieseke, F., Oehmcke, S., Wu, Y., and Barnard, K. (2021). Attentional feature fusion. Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, IEEE.","DOI":"10.1109\/WACV48630.2021.00360"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Zhang, X., Sugano, Y., Fritz, M., and Bulling, A. (2015). Appearance-based gaze estimation in the wild. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, IEEE.","DOI":"10.1109\/CVPR.2015.7299081"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Cheng, Y., and Lu, F. (2022). Gaze estimation using transformer. Proceedings of the 2022 26th International Conference on Pattern Recognition (ICPR), IEEE.","DOI":"10.1109\/ICPR56361.2022.9956687"},{"key":"ref_51","doi-asserted-by":"crossref","unstructured":"Bao, Y., Cheng, Y., Liu, Y., and Lu, F. (2021). Adaptive feature fusion network for gaze tracking in mobile tablets. Proceedings of the 2020 25th International Conference on Pattern Recognition (ICPR), IEEE.","DOI":"10.1109\/ICPR48806.2021.9412205"},{"key":"ref_52","unstructured":"Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv."},{"key":"ref_53","unstructured":"Loshchilov, I., and Hutter, F. (2016). Sgdr: Stochastic gradient descent with warm restarts. arXiv."},{"key":"ref_54","first-page":"53","article-title":"Visualizing data using t-SNE","volume":"9","author":"Hinton","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"2623","DOI":"10.1109\/TCSVT.2016.2595322","article-title":"A regression-based user calibration framework for real-time gaze estimation","volume":"27","author":"Arar","year":"2016","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"1174","DOI":"10.1109\/TPAMI.2022.3148386","article-title":"Towards high performance low complexity calibration in appearance based gaze estimation","volume":"45","author":"Chen","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6265\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T13:39:59Z","timestamp":1790948399000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/19\/6265"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,2]]},"references-count":56,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2026,10]]}},"alternative-id":["s26196265"],"URL":"https:\/\/doi.org\/10.3390\/s26196265","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,2]]}}}