Publication Details

Vision UFormer: Long-Range Monocular Absolute Depth Estimation

POLÁŠEK Tomáš, ČADÍK Martin, KELLER Yosi and BENEŠ Bedřich. Vision UFormer: Long-Range Monocular Absolute Depth Estimation. Computers and Graphics, vol. 111, no. 4, 2023, pp. 180-189. ISSN 0097-8493. Available from:
Czech title
Vision UFormer: Absolutní Predikce Hloubek na Dlouhé Vzdálenosti
journal article
Polášek Tomáš, Ing. (DCGM FIT BUT)
Čadík Martin, doc. Ing., Ph.D. (DCGM FIT BUT)
Keller Yosi, prof. MSc., Ph.D. (BIU)
Beneš Bedřich, prof., Ph.D. (PU)

Absolute Depth Estimation, Monocular Depth Prediction, Long Range Distance, Transformer, UNet, Staged Training


We introduce Vision UFormer (ViUT), a novel deep neural long-range monocular depth estimator. The input is an RGB image, and the output is an image that stores the absolute distance of the object in the scene as its per-pixel values. ViUT consists of a Transformer encoder and a ResNet decoder combined with UNet style of skip connections. It is trained on 1M images across ten datasets in a staged regime that starts with easier-to-predict data such as indoor photographs and continues to more complex long-range outdoor scenes. We show that ViUT provides comparable results for normalized relative distances and short-range classical datasets such as NYUv2 and KITTI. We further show that it successfully estimates of absolute long-range depth in meters. We validate ViUT on a wide variety of long-range scenes showing its high estimation capabilities with a relative improvement of up to 23%. Absolute depth estimation finds application in many areas, and we show its usability in image composition, range annotation, defocus, and scene reconstruction.

Computers and Graphics, vol. 111, no. 4, ISSN 0097-8493
Elsevier Science
   author = "Tom\'{a}\v{s} Pol\'{a}\v{s}ek and Martin \v{C}ad\'{i}k and Yosi Keller and Bed\v{r}ich Bene\v{s}",
   title = "Vision UFormer: Long-Range Monocular Absolute Depth Estimation",
   pages = "180--189",
   journal = "Computers and Graphics",
   volume = 111,
   number = 4,
   year = 2023,
   ISSN = "0097-8493",
   doi = "10.1016/j.cag.2023.02.003",
   language = "english",
   url = ""
Back to top