no code implementations • IEEE Transactions on Multimedia 2023 • Zhixuan Li, Weining Ye, Tingting Jiang, Tiejun Huang
In human amodal perception, shape-prior knowledge is helpful for AIS.
no code implementations • ICCV 2023 • Zhixuan Li, Weining Ye, Juan Terven, Zachary Bennett, Ying Zheng, Tingting Jiang, Tiejun Huang
To bridge this gap, we propose a new task called Multi-view Amodal Instance Segmentation (MAIS) and introduce the MUVA dataset, the first MUlti-View AIS dataset that takes the shopping scenario as instantiation.
no code implementations • European Conference on Computer Vision (ECCV) 2022 • Zhixuan Li, Weining Ye, Tingting Jiang, Tiejun Huang
However, masks in 2D space are only some observations and samples from the 3D model in different viewpoints and thus can not represent the real complete physical shape of the instances.