Uni MS-PS: a Multi-Scale Encoder Decoder Transformer for Universal Photometric Stereo

Clément Hardy1, Yvain Quéau1, David Tschumperlé1,
1Normandie Université, UNICAEN, CNRS, ENSICAEN, GREYC laboratory, Caen, France
Images credits: Skoltech3D [1] DiLiGenT-Pi [2]

Visual DiLiGent [3] Results

Ours
Ground Truth

Visual on a very high resolution image

Images credits: Marsoulas cave [4]

References

[1] Voynov, O., Bobrovskikh, G., Karpyshev, P., Galochkin, S., Ardelean, A.T., Bozhenko, A., Karmanova, E., Kopanev, P., Labutin-Rymsho, Y., Rakhimov, R., Safin, A., Serpiva, V., Artemov, A., Burnaev, E., Tsetserukou, D., Zorin, D., 2023. Multi-sensor large-scale dataset for multi-view 3d reconstruction, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 21392–21403
[2] Wang, F., Ren, J., Guo, H., Ren, M., Shi, B., 2023. Diligent-pi: Photometric stereo for planar surfaces with rich details benchmark dataset and beyond, in: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pp. 12571–12580
[3] Shi, B., Wu, Z., Mo, Z., Duan, D., Yeung, S., Tan, P., 2016. A benchmark dataset and evaluation for non-lambertian and uncalibrated photometric stereo, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3707–3716
[4] A. Laurent 2023 (INPT, UMR 5505 IRIT), C. Fritz and G. Tosello team (CREAP-E.Cartailhac), MSHS-T (UAR 3414)