DPMFormer: Dual-Path Mamba-Transformer for Efficient Image Super‑Resolution

ICLR 2026 Conference Submission20005 Authors

Keywords: Transformer, Mamba, Dual-Path Network, Lightweight Network

Abstract:

Vision Transformers have achieved outstanding performance in image super-resolution (SR), but existing lightweight models rely on window-based attention, limiting their ability to model global dependencies essential for high-quality reconstruction. To address these challenges, we present DPMFormer, a Dual-Path Mamba–Transformer architecture for lightweight image super-resolution. Rather than a simple combination of a state-space model and a Transformer, the design couples two streams throughout the network. On the Transformer side, an Enhanced Transformer Layer (ETL) replaces self-attention with Spatial–Channel Correlation (SCC) and a Depthwise-SwiGLU Feed-Forward (DW-SwiFFN). On the Mamba side, Lightweight Bi-directional Mamba Layers (LBi-ML) implement single-pass bidirectionality via channel split and sequence reversal with additive cross coupling. The streams interact at two levels: within each block, a Cross-Attention Layer (CAL) performs fixed, non-overlapping cross fusion,
and across blocks, Inter-branch Exchange Bridges (IEB) use resolution-preserving 1 × 1 adapters around tokenization to align channel spaces in both directions. Besides, we employ RMSNorm to reduce normalization overhead and, under our setup, observe modest, configuration-dependent gains. Extensive experiments show that DPMFormer reduces FLOPs by 47.3G (21\%) and parameters by 21K under 2 × upsampling compared to HiT-SR, while almost achieving state-of-the-art performance across five benchmarks. Measured on an RTX 4090, our method reaches 668 ms latency, yielding 1.59 × and 2.33 × speedups over MambaIR and CATANet, respectively. The code will be publicly released.

Primary Area: applications to computer vision, audio, language, and other modalities

Submission Number: 20005