4 papers
When Muon Optimizer Meets Adversarial Training: A Theoretical and Empirical Study
Jun Yan, Weiquan Huang, Jiankai Zuo +4
Adversarial training (AT) remains one of the most reliable empirical defenses against adversarial attacks. Its robustness critically depends on how the underlying min-max objective…
MU-GeNeRF: Multi-view Uncertainty-guided Generalizable Neural Radiance Fields for Distractor-aware Scene
Wenjie Mu, Zhan Li, Chuanzhou Su +8
Generalizable Neural Radiance Fields (GeNeRFs) enable high-quality scene reconstruction from sparse views and can generalize to unseen scenes. However, in real-world settings, tran…
LDRFusion: A LiDAR-Dominant multimodal refinement framework for 3D object detection
Jijun Wang, Yan Wu, Yujian Mo +3
Existing LiDAR-Camera fusion methods have achieved strong results in 3D object detection. To address the sparsity of point clouds, previous approaches typically construct spatial p…
Enhancing LiDAR Point Features with Foundation Model Priors for 3D Object Detection
Yujian Mo, Yan Wu, Junqiao Zhao +3
Recent advances in foundation models have opened up new possibilities for enhancing 3D perception. In particular, DepthAnything offers dense and reliable geometric priors from mono…