Abstract: To solve the problem of pose distortion in the forward propagation of pose features in existing methods, this paper proposes a Dual-Side Feature Fusion Network for pose transfer (DSFFNet). Firstly, a fixed-length pose code is extracted from the source mesh by a pose encoder and combined with the target vertices to form a mixed feature. Then, a Feature Fusion Adaptive Instance Normalization module (FFAdaIN) is designed to process pose and identity features through two side channels, so that the pose features can be compensated in layer-by-layer forward propagation, thus solving the pose distortion problem. Finally, using the mesh decoder composed of this module, the pose are gradually transferred to the target mesh. Experimental results on SMPL, SMAL, FAUST, and MultiGarment datasets show that DSFFNet successfully solves the pose distortion problem while maintaining a smaller network structure with evaluation metrics PMD, CD, and EMD reaching 0.57×10^-4, 1.37×10^-4, and 13.40×10^-3, respectively, and can adapt to meshes with different numbers of vertices. Code is available at https://github.com/YikiDragon/DSFFNet.