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.

Background: Thermophilic filamentous fungus Myceliophthora thermophila has great capacity for biomass degradation and is an attractive system for direct production of enzymes and chemicals from plant biomass. Its industrial importance inspired us to develop genome editing tools to speed up the genetic engineering of this fungus. First-generation CRISPR-Cas9 technology was developed in 2017 and, since then, some progress has been made in thermophilic fungi genetic engineering, but a number of limitations remain. They include the need for complex independent expression cassettes for targeting multiplex genomic loci and the limited number of available selectable marker genes. Results:In this study, we developed an Acidaminococcus sp. Cas12a-based CRISPR system for efficient multiplex genome editing, using a single-array approach in M. thermophila. These CRISPR-Cas12a cassettes worked well for simultaneous multiple gene deletions/insertions. We also developed a new simple approach for marker recycling that relied on the novel cleavage activity of the CRISPR-Cas12a system to make DNA breaks in selected markers. We demonstrated its performance by targeting nine genes involved in the cellulase production pathway in M. thermophila via three transformation rounds, using two selectable markers neo and bar. We obtained the nonuple mutant M9 in which protein productivity and lignocellulase activity were 9.0-and 18.5-fold higher than in the wild type. We conducted a parallel investigation using our transient CRISPR-Cas9 system and found the two technologies were complementary. Together we called them CRISPR-Cas-assisted marker recycling technology (Camr technology). Conclusions:Our study described new approaches (Camr technology) that allow easy and efficient marker recycling and iterative stacking of traits in the same thermophilic fungus strain either, using the newly established CRISPR-Cas12a system or the established CRISPR-Cas9 system. This Camr technology will be a versatile and efficient tool for engineering, theoretically, an unlimited number of genes in fungi. We expect this advance to accelerate biotechnology-oriented engineering processes in fungi.

No abstract