Co-Occ: Coupling Explicit Feature Fusion with Volume Rendering Regularization for Multi-Modal 3D Semantic Occupancy Prediction

no code implementations • 6 Apr 2024 • Jingyi Pan, Zipeng Wang, Lin Wang

However, multi-modal semantic occupancy prediction approaches have encountered difficulties in dealing with the modality heterogeneity, modality misalignment, and insufficient modality interactions that arise during the fusion of different modalities data, which may result in the loss of important geometric and semantic information.

3D Semantic Occupancy Prediction Autonomous Driving

Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentation

no code implementations • 7 Oct 2023 • Jingyi Pan, Sihang Li, Yucheng Chen, Jinjing Zhu, Lin Wang

Moreover, semantic segmentation models trained on daytime datasets often face difficulties in generalizing effectively to nighttime conditions.

Autonomous Driving Contrastive Learning +4