Multimodal fusion can make semantic segmentation more robust. However, fusing an arbitrary number of modalities remains underexplored. To delve into this problem, we create the DeLiVER arbitrary-modal segmentation benchmark, covering Depth, LiDAR, multiple Views, Events, and RGB. Aside from this, we provide this dataset in four severe weather conditions as well as five sensor failure cases to exploit modal complementarity and resolve partial outages. To make this possible, we present the arbitrary cross-modal segmentation model CMNeXt. It encompasses a Self-Query Hub (SQ-Hub) designed to extract effective information from any modality for subsequent fusion with the RGB representation and adds only negligible amounts of parameters (~0.01M) per additional modality. On top, to efficiently and flexibly harvest discriminative cues from the auxiliary modalities, we introduce the simple Parallel Pooling Mixer (PPX). With extensive experiments on a total of six benchmarks, our CMNeXt achieves state-of-the-art performance on the DeLiVER, KITTI-360, MFNet, NYU Depth V2, UrbanLF, and MCubeS datasets, allowing to scale from 1 to 81 modalities. On the freshly collected DeLiVER, the quad-modal CMNeXt reaches up to 66.30% in mIoU with a +9.10% gain as compared to the mono-modal baseline. The DeLiVER dataset and our code are at: https://jamycheung.github.io/DELIVER.html.

翻译：多模态融合可以提升语义分割的鲁棒性。然而，融合任意数量的模态仍是一个尚未充分探索的问题。为深入研究该问题，我们构建了DeLiVER任意模态分割基准数据集，涵盖深度、激光雷达、多视角、事件相机及RGB数据。此外，我们提供了四种恶劣天气条件及五种传感器故障场景下的数据，以挖掘模态互补性并解决部分模态失效问题。为实现这一目标，我们提出了任意跨模态分割模型CMNeXt。该模型包含一个自查询枢纽（SQ-Hub），旨在从任意模态中提取有效信息并与RGB表示进行后续融合，且每个新增模态仅增加可忽略的参数（约0.01M）。此外，为高效灵活地从辅助模态中提取判别性线索，我们引入了简单的并行池化混合器（PPX）。通过在六个基准数据集上的广泛实验，我们的CMNeXt在DeLiVER、KITTI-360、MFNet、NYU Depth V2、UrbanLF和MCubeS数据集上均取得了最先进性能，且支持从1到81种模态的扩展。在全新采集的DeLiVER数据集上，四模态CMNeXt的mIoU最高达66.30%，相比单模态基线提升了9.10%。DeLiVER数据集及代码已发布于：https://jamycheung.github.io/DELIVER.html。