Fig. 1
The negative impact of lens flare on different downstream tasks. The left panel shows semantic segmentation results generated by Segment Anything5, and the right panel shows monocular depth estimation results from Vision Transformers for Dense Prediction4. In both tasks, the flare-corrupted input (top-left of each set) leads to an erroneous output (bottom-left), while the output from the flare-free ground truth (bottom-right) is accurate.
