arXiv Computer Vision research summaries for March 30, 2024.

Today's Research Themes (AI-Generated):

• Panoramic video quality assessment enhanced by learned scanpaths modeling user viewing patterns.

• Open-world object detection improved by the YOLO-based YOLOOC method, capable of discovering novel classes.

• Self-Supervised Constraints in image super-resolution improve performance on benchmark datasets.

• Image-to-image matching via foundation models outperforms state-of-the-art in open-vocabulary semantic segmentation.

• Implicit Field Learning combined with point diffusion leads to advancements in 3D object reconstruction from single RGB-D images.