Soft Split and Soft Composition
2000년 도입 · 논문 1편에서 사용
Soft Split and Soft Composition are video frame based operations used in the FuseFormer architecture, specifically the FuseFormer blocks. We softly split each frame into overlapped patches and then softly composite them back, by using an unfold and fold operator with patch size $k$ being greater than patch stride $s$. When compositing patches back to its original spatial shape, we add up feature values at each overlapping spatial location of neighboring patches.
출처: FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
소개 논문: FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
Video Model Blocks · Computer Vision