Image relighting is attracting increasing interest due to its various applications. From a research perspective, image relighting can be exploited to conduct both image normalization for domain adaptation, and also for data augmentation. It also has multiple direct uses for photo montage and aesthetic enhancement. In this paper, we review the NTIRE 2021 depth guided image relighting challenge.We rely on the VIDIT dataset for each of our two challenge tracks, including depth information. The first track is on one-to-one relighting where the goal is to transform the illumination setup of an input image (color temperature and light source position) to the target illumination setup. In the second track, the any-to-any relighting challenge, the objective is to transform the illumination settings of the input image to match those of another guide image, similar to style transfer. In both tracks, participants were given depth information about the captured scenes. We had nearly 250 registered participants, leading to 18 confirmed team submissions in the final competition stage. The competitions, methods, and final results are presented in this paper.

Recently, the application of satellite remote sensing images is becoming increasingly popular, but the observed images from satellite sensors are frequently in low-resolution (LR). Thus, they cannot fully meet the requirements of object identification and analysis. To utilize the multi-scale characteristics of objects fully in remote sensing images, this paper presents a multi-scale residual neural network (MRNN). MRNN adopts the multi-scale nature of satellite images to reconstruct high-frequency information accurately for super-resolution (SR) satellite imagery. Different sizes of patches from LR satellite images are initially extracted to fit different scale of objects. Large-, middle-, and small-scale deep residual neural networks are designed to simulate differently sized receptive fields for acquiring relative global, contextual, and local information for prior representation. Then, a fusion network is used to refine different scales of information. MRNN fuses the complementary high-frequency information from differently scaled networks to reconstruct the desired high-resolution satellite object image, which is in line with human visual experience (“look in multi-scale to see better”). Experimental results on the SpaceNet satellite image and NWPU-RESISC45 databases show that the proposed approach outperformed several state-of-the-art SR algorithms in terms of objective and subjective image qualities.

In this correspondence, a computationally efficient method that combines the subspace and projection separation approaches is developed for R-dimensional (R-D) frequency estimation of multiple sinusoids, where R ≥ 3, in the presence of white Gaussian noise. Through extracting a 2-D slice matrix set from the multidimensional data, we devise a covariance matrix associated with one dimension, from which the corresponding frequencies are estimated using the root-MUSIC method. With the use of the frequency estimates in this dimension, a set of projection separation matrices is then constructed to separate all frequencies in the remaining dimensions. Root-MUSIC method is again applied to estimate these singletone frequencies while multidimensional frequency pairing is automatically attained. Moreover, the mean square error of the frequency estimator is derived and confirmed by computer simulations. It is shown that the proposed approach is superior to two state-of-the-art frequency estimators in terms of accuracy and computational complexity. Index TermsMultidimensional frequency estimation, subspace method, projection separation.

No abstract

No abstract