S3OD is a large-scale fully synthetic dataset for salient object detection and background removal, with 140K high-quality images generated using diffusion models. Our model, trained on large-scale ...
Synthesizing large-scale, explorable, and geometrically accurate 3D urban scenes is a challenging yet valuable task in providing immersive and embodied applications. The challenges lie in the lack of ...
Abstract: Extended depth-of-field of white light illumination imaging is theoretically and experimentally demonstrated. Pupil phase mask tailoring focal chromatic dispersion is hybridized with ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback