aiqbench analysis
This paper presents CLFTv2, an efficient framework for fusing camera and LiDAR data in autonomous driving by replacing global attention mechanisms with hierarchical local-attention architectures. The approach significantly reduces computational overhead while improving the detection of vulnerable road users across standard datasets like ZOD and Waymo. These findings offer a scalable path toward real-time perception systems without relying on heavy query-matching decoders.
CLFTv2: Efficient Camera-LiDAR Fusion for Semantic Segmentation via Hierarchical Feature Pyramids
arXiv:2609.09881v1 Announce Type: cross Abstract: Semantic segmentation for autonomous driving requires reliable detection of vulnerable road users (VRUs) despite heavy class imbalance. We introduce CLFTv2, a hierarchical camera-LiDAR fusion framework replacing global ViT attention with a Swin-based multi-scale encoder and a lightweight FPN-style residual decoder. Operating in the 2D perspective domain, CLFTv2 integrates multi-scale geometric cues through shifted-window attention and per-scale residual fusion, avoiding the computational overhead of query-matching decoders. Across three driving datasets, CLFTv2 consistently improves VRU recall. On ZOD, CLFTv2-Large achieves 53.5\% mIoU, improving pedestrian IoU from 35.5\% to 44.9\% over the prior CLFT model. On Waymo, CLFTv2 reaches 61.7\% mIoU. Additionally, a modality-isolation study suggests ViT's global receptive field yields stronger fusion gains only under dense LiDAR returns. Compared to a Swin-based Mask2Former adaptation, CLFTv2 requires 1.4$\times$ fewer GFLOPs and delivers 2.2$\times$ higher throughput, while achieving comparable overall accuracy. These results demonstrate that hierarchical local-attention fusion offers an efficient, scalable alternative to global-attention and query-based decoders for real-time on-vehicle perception in intelligent transportation systems. Source code is publicly available.
Abstract:Semantic segmentation for autonomous driving requires reliable detection of vulnerable road users (VRUs) despite heavy class imbalance. We introduce CLFTv2, a hierarchical camera-LiDAR fusion framework replacing global ViT attention with a Swin-based multi-scale encoder and a lightweight FPN-style residual decoder. Operating in the 2D perspective domain, CLFTv2 integrates multi-scale geometric cues through shifted-window attention and per-scale residual fusion, avoiding the computational overhead of query-matching decoders. Across three driving datasets, CLFTv2 consistently improves VRU recall. On ZOD, CLFTv2-Large achieves 53.5\% mIoU, improving pedestrian IoU from 35.5\% to 44.9\% over the prior CLFT model. On Waymo, CLFTv2 reaches 61.7\% mIoU. Additionally, a modality-isolation study suggests ViT's global receptive field yields stronger fusion gains only under dense LiDAR returns. Compared to a Swin-based Mask2Former adaptation, CLFTv2 requires 1.4$\times$ fewer GFLOPs and delivers 2.2$\times$ higher throughput, while achieving comparable overall accuracy. These results demonstrate that hierarchical local-attention fusion offers an efficient, scalable alternative to global-attention and query-based decoders for real-time on-vehicle perception in intelligent transportation systems. Source code is publicly available.
Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
arXiv:2609.09881 [cs.CV]
(or arXiv:2609.09881v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.09881 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 266 words
Related coverage
PolygMap: A Perceptive Locomotion Framework for Humanoid Robot Stair Climbing
arXiv · Jul 30, 2026
MatchFusion: Explicit-Implicit Instance Matching for Spatio-Temporal Multimodal Autonomous Driving
arXiv · Sep 24, 2026
UP-Fuse: Uncertainty-guided LiDAR-Camera Fusion for 3D Panoptic Segmentation
arXiv · Jul 28, 2026
DAGLFNet: Deep Feature Attention Guided Global and Local Feature Fusion for Pseudo-Image Point Cloud Segmentation
arXiv · Sep 9, 2026