I am looking for full-time (applied) research opportunities in industry, involving (trustworthy and robust) machine learning or (3D) computer vision, starting early 2022. Check out my CV and get in touch on LinkedIn!


S. Beigpour, M. Serra, J. van de Weijer, R. Benavente, M. Vanrell, O. Penacchio, D. Samaras. Intrinsic Image Evaluation on Synthetic Complex Scenes. International Conference on Image Processing, 2013.

Beigpour et al. introduce another synthetic dataset for intrinsic images similar to the MIT dataset [1]. In contrast to the MIT dataset, however, they have several more complex scenes, for examples see figure 1.

cic_bed1_dl cic_bed1_refl cic_bed1_dl_shad
cic_room2_dl cic_room2_refl cic_room2_dl_shad

Figure 1 (click to enlarge): Example images from the dataset introduced by Beigpour et al. From left to right: image, reflectance and shading.

What is your opinion on the summarized work? Or do you know related work that is of interest? Let me know your thoughts in the comments below: