发表机构
University of Technology Sydney; Nanjing University of Science and Technology; Honor Device Co., Ltd.; Shanghai Institute of Microsystem and Information Technology, CAS（悉尼科技大学; 南京理工大学; 荣耀终端有限公司; 中国科学院上海微系统与信息技术研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有RGB-D语义分割方法的不足，提出URNet，通过单编码器实现多模态特征提取与跨模态融合，采用RepBlock、LGA和PMD，在多基准上达到最优性能且高效。
AI 中文摘要
现有的RGB-D语义分割方法通常采用双编码器分别处理RGB和深度输入，再使用专用模块进行跨模态特征融合。但这类设计往往无法充分捕获深度表征，从而限制了有效的跨模态交互，额外的编码器分支还会引入冗余计算，阻碍轻量级执行。为应对这些挑战，我们提出URNet，即统一重参数化RGB-D网络，其在单个编码器内同时执行多模态特征提取与跨模态融合。具体而言，我们采用重参数化策略以压缩网络架构并实现快速推理；在每个重参数化块（RepBlock）内，引入线性门控注意力（LGA）模块，以充分利用不同特征尺度上互补的RGB和深度线索。此外，考虑到现有RGB-D分割模型中解码器设计的研究相对不足，我们开发了一种简洁且有效的通用解码器，即金字塔融合解码器（PMD）。在多个RGB-D分割基准上开展的大量实验表明，URNet在保持高计算效率的同时达到了最优性能。代码将在此URL处提供。
英文摘要
Previous RGB-D semantic segmentation methods commonly employ dual encoders to separately process RGB and depth inputs, followed by dedicated modules for cross-modal feature fusion. However, such designs often inadequately capture depth representations and consequently limit effective cross-modal interaction, while the additional encoder branch introduces redundant computation that hinders lightweight execution. To tackle these challenges, we propose URNet, a Unified Reparameterized RGB-D Network that performs simultaneous multi-modal feature extraction and cross-modal fusion within a single encoder. Specifically, we adopt a reparameterization strategy to compact the network architecture and facilitate fast inference. Within each Reparameterized Block (RepBlock), a Linear Gated Attention (LGA) module is introduced to fully exploit complementary RGB and depth cues across different feature scales. Furthermore, considering that decoder design has been relatively underexplored in existing RGB-D segmentation models, we develop a concise yet effective universal decoder, termed the Pyramid Merging Decoder (PMD). Extensive experiments on multiple RGB-D segmentation benchmarks demonstrate that URNet achieves state-of-the-art performance while maintaining high efficiency. Code will be available at https://github.com/Wild-Stephen/URNet.
CommentsACM MM 2026
