$\mathcal{B}^{3}$-Net: Controlled Posterior Bridge Learning for Multi-Task Dense Prediction

ArXi:2605.05722v1 Announce Type: new Multi-task dense prediction solves complementary pixel-level tasks in a unified model, such as semantic segmentation, depth estimation, surface normal estimation, and edge detection. Existing decoder-side interactions use attention, prompts, routing, diffusion, Mamba, or bridge features to exchange task evidence, but most of them organize this evidence implicitly. They usually fuse task features by similarity or affinity, without explicitly modeling that evidence reliability varies across tasks and spatial locations.