English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Multi-modal 3D object detectors are dedicated to exploring secure andreliable perception systems for autonomous driving (AD). However, whileachieving state-of-the-art (SOTA) performance on clean benchmark datasets, theytend to overlook the complexity and harsh conditions of real-worldenvironments. Meanwhile, with the emergence of visual foundation models (VFMs),opportunities and challenges are presented for improving the robustness andgeneralization of multi-modal 3D object detection in autonomous driving.Therefore, we propose RoboFusion, a robust framework that leverages VFMs likeSAM to tackle out-of-distribution (OOD) noise scenarios. We first adapt theoriginal SAM for autonomous driving scenarios named SAM-AD. To align SAM orSAM-AD with multi-modal methods, we then introduce AD-FPN for upsampling theimage features extracted by SAM. We employ wavelet decomposition to denoise thedepth-guided images for further noise reduction and weather interference.Lastly, we employ self-attention mechanisms to adaptively reweight the fusedfeatures, enhancing informative features while suppressing excess noise. Insummary, our RoboFusion gradually reduces noise by leveraging thegeneralization and robustness of VFMs, thereby enhancing the resilience ofmulti-modal 3D object detection. Consequently, our RoboFusion achievesstate-of-the-art performance in noisy scenarios, as demonstrated by the KITTI-Cand nuScenes-C benchmarks.

RoboFusion: Towards Robust Multi-Modal 3D obiect Detection via SAM