5 papers
Robust 3DGS-based SLAM via Adaptive Kernel Smoothing
Shouhe Zhang, Dayong Ren, Wen Jie Li +4
In this paper, we challenge the conventional notion in 3DGS-SLAM that rendering quality is the primary determinant of tracking accuracy. We argue that, compared to solely pursuing…
Keep the Core: Adversarial Priors for Significance-Preserving Brain MRI Segmentation
Feifei Zhang, Zhenhong Jia, Sensen Song +3
Medical image segmentation is constrained by sparse pathological annotations. Existing augmentation strategies, from conventional transforms to random masking for self-supervision,…
Taming the Light: Illumination-Invariant Semantic 3DGS-SLAM
Shouhe Zhang, Dayong Ren, Sensen Song +2
Extreme exposure degrades both the 3D map reconstruction and semantic segmentation accuracy, which is particularly detrimental to tightly-coupled systems. To achieve illumination i…
ZigzagPointMamba: Spatial-Semantic Mamba for Point Cloud Understanding
Linshuang Diao, Sensen Song, Yurong Qian +1
State Space models (SSMs) such as PointMamba enable efficient feature extraction for point cloud self-supervised learning with linear complexity, outperforming Transformers in comp…
Rethinking Convergence in Deep Learning: The Predictive-Corrective Paradigm for Anatomy-Informed Brain MRI Segmentation
Feifei Zhang, Zhenhong Jia, Sensen Song +2
Despite the remarkable success of the end-to-end paradigm in deep learning, it often suffers from slow convergence and heavy reliance on large-scale datasets, which fundamentally l…