Figure 1. Comparisons among the main RGBD segmentation
pipelines and our approach. (a) Use dual encoders to encode
RGB and depth respectively and design fusion modules to fusion
them [28, 61]; (b) Adopt an unified RGBD encoder to extract and
fuseRGBDfeatures[1,59]; (c)OurDFormerv2usedepthtoform
ageometrypriorofthesceneandthenenhancethevisualfeatures.