A new dataset called SOBA, named after Shadow-OBject Association, with 3,623 pairs of shadow and object instances in 1,000 photos, each with individual labeled masks.
8 PAPERS • 1 BENCHMARK
Collects shadow images for multiple scenarios and compiled a new dataset of 10,500 shadow images, each with labeled ground-truth mask, for supporting shadow detection in the complex world. The dataset covers a rich variety of scene categories, with diverse shadow sizes, locations, contrasts, and types.
1 PAPER • NO BENCHMARKS YET