RESUMEN
Deep learning methods have achieved impressive performance in compressed video quality enhancement tasks. However, these methods rely excessively on practical experience by manually designing the network structure and do not fully exploit the potential of the feature information contained in the video sequences, i.e., not taking full advantage of the multiscale similarity of the compressed artifact information and not seriously considering the impact of the partition boundaries in the compressed video on the overall video quality. In this article, we propose a novel Mixed Difference Equation inspired Transformer (MDEformer) for compressed video quality enhancement, which provides a relatively reliable principle to guide the network design and yields a new insight into the interpretable transformer. Specifically, drawing on the graphical concept of the mixed difference equation (MDE), we utilize multiple cross-layer cross-attention aggregation (CCA) modules to establish long-range dependencies between encoders and decoders of the transformer, where partition boundary smoothing (PBS) modules are inserted as feedforward networks. The CCA module can make full use of the multiscale similarity of compression artifacts to effectively remove compression artifacts, and recover the texture and detail information of the frame. The PBS module leverages the sensitivity of smoothing convolution to partition boundaries to eliminate the impact of partition boundaries on the quality of compressed video and improve its overall quality, while not having too much impacts on non-boundary pixels. Extensive experiments on the MFQE 2.0 dataset demonstrate that the proposed MDEformer can eliminate compression artifacts for improving the quality of the compressed video, and surpasses the state-of-the-arts (SOTAs) in terms of both objective metrics and visual quality.
RESUMEN
In birds, downy feather quantity mainly affected by the follicles. Wnt6, a secreted cysteine-rich protein, plays a key role in follicular development as an intercellular signaling molecule. The present study was to investigate the follicle development and Wnt6 polymorphism in Wanxi-white geese, a Chinese indigenous breed. In total, 300 fertilized eggs were hatched. At embryonic stage and on early birth goslings, the diameter and density of follicles from different sites were examined after sectioning and staining. The results showed that the diameter of primary feather follicles in thorax, venter, dorsum and flank had no difference at embryonic stage. In contrast, after birth, thorax and ventral feather follicles had greater diameter than those on dorsum and flank. Similarly, the primary feather follicle density was higher in thorax and venter than in dorsum and flank at embryonic stage. The secondary feather follicle diameter in flank was greater than that in other sites examined. The secondary follicle showed lush growth in E27 with thickest in ventral and thorax. Overall, follicle formed consistently in dorsal and flank, and follicle in thorax and ventral formed in another consistent way. The polymorphism study showed 2 single nucleotide polymorphisms of Wnt6 and 3 genotypes identified. Sequencing revealed two nucleotide transitions, T451C and A466G, which were synonymous mutations causing codons for aspartate and lysine to change from GAU to GAC and from AAA to AAG, respectively. This information about follicle development and Wnt6 polymorphisms would provide potential utilization in marker-assisted selection program for down feather selection.