{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cam-convs-camera-aware-multi-scale","title":"CAM-Convs: Camera-Aware Multi-Scale Convolutions for Single-View Depth","arxiv_id":"1904.02028","date":"2019-04-03","proceeding":"CVPR 2019 6","authors":["Jose M. Facil","Benjamin Ummenhofer","Huizhong Zhou","Luis Montesano","Thomas Brox","Javier Civera"],"abstract":"Single-view depth estimation suffers from the problem that a network trained\non images from one camera does not generalize to images taken with a different\ncamera model. Thus, changing the camera model requires collecting an entirely\nnew training dataset. In this work, we propose a new type of convolution that\ncan take the camera parameters into account, thus allowing neural networks to\nlearn calibration-aware patterns. Experiments confirm that this improves the\ngeneralization capabilities of depth prediction networks considerably, and\nclearly outperforms the state of the art when the train and test images are\nacquired with different cameras.","url_abs":"http://arxiv.org/abs/1904.02028v1","url_pdf":"http://arxiv.org/pdf/1904.02028v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cam-convs-camera-aware-multi-scale","repo_url":"https://github.com/jmfacil/camconvs","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"3d-depth-estimation","task_name":"3D Depth Estimation"},{"task_slug":"depth-estimation","task_name":"Depth Estimation"},{"task_slug":"depth-prediction","task_name":"Depth Prediction"},{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1904.02028","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}