Aug 2026· Journal of Real-Time Image Processing· Vol 23· 0 citations· 51 references
Computer Science
TL;DR
This paper replaces the Stem layer in FRNet with the proposed FD-Stem, which improves feature representation while reducing computational complexity, and introduces long-range modeling capability with limited additional parameters, enabling effective learning of both spatial and channel-wise representations.
A spatial-channel collaborative modeling framework named SPMixNet is introduced to improve fine-grained 3D scene understanding and effectively mitigates the structural and representational limitations of existing projection-based methods, providing a promising solution for accurate segmentation of small and structurall...
Hong-Dou He, Chenggong Sun, Yi-Fang Huang et al.· The Visual Computer· 1 citation
This paper proposes a new, to the authors' knowledge, efficient and accurate semantic segmentation network for LiDAR, called Range-FDSeg, and introduces a lightweight and dynamic upsampler, called Dysample-S+.
Hong Tan, Fen Chen, Tingna Liu et al.· Applied Optics· 0 citations
The proposed PDES-Net enhances segmentation performance while maintaining advantages in model parameters and inference speed, and achieves a well-balanced trade-off between accuracy and computational efficiency.
Si-Si Zhang, Zong-Ju Peng, Hong Tan et al.· Measurement science and tech...· 0 citations
The proposed Dilated Context Attention Network (DCA-Net), which consists of a dilated local geometric encoding module, a channel attention pooling module, and a category-boundary sampling strategy, alleviates boundary confusion in point cloud segmentation with long-tail categories.
Bingchen Du, Bo-Zhao Li, Zhenkun Zhang et al.· Remote Sensing· 0 citations
A contextual cue framework of "LiDAR semantics-large language model-retrieval-enhanced generation" is proposed, providing a new technical path for high-precision, fine-grained semantic segmentation of urban LiDAR point clouds and also offers a theoretical reference for promoting the in-depth application of large langua...
Jinlong Wang, Tao Shen, Liang Huo et al.· The International Archives o...· 0 citations
The core of the proposed method is a bidirectional long short-term memory (BiLSTM)-based sequencer module, which models long-range contextual dependencies among points with linear computational complexity, enabling effective global feature learning at a low cost.
Dongzhen Liu, Yuzhong Deng, Jian-Xiao Zou et al.· PLoS ONE· 1 citation
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
