Aug 2026· Journal of Visualized Experiments· Vol 234· 0 citations
Medicine
TL;DR
This paper proposes a semantic parsing method that leverages building-structure priors that uses a shifted-window hierarchical transformer encoder to extract multi-scale visual features and combines a gradient-direction-consistency line segment detection algorithm to construct a Manhattan 3D bounding box.
This work proposes a segmentation framework guided by Contrastive Language–Image Pre-training (CLIP) that enriches sparse 3D tokens with vision–language semantic priors and introduces a decoupled CLIP-induced semantic residual that forms semantic-geometric attention biases for local window attention.
GFE-Net is rigorously benchmarked on two widely adopted large-scale datasets—S3DIS and SensatUrban—yielding OA/mIoU of 89.6%/73.1% and 93.3%/61.1%, respectively.
GaussianDS, a depth-supervised semantic 3DGS framework that treats semantic lifting as a supervision-alignment problem and jointly optimizes RGB appearance, rendered depth, and compact semantics from scratch, is proposed.
Recent advances in 3D reconstruction have progressed from per-scene optimization to feed-forward inference, and semantic scene understanding has followed suit -- yet existing methods remain confined to object-centric perception, neglecting spatial relations between objects. We formulate 3D spatial relation segmentation...
Minsu Kim, Jaesung Choe, J. Lee et al.· 0 citations
3D Gaussian Splatting (3DGS) enables real-time photorealistic scene reconstruction, yet its segmentation tasks suffer from two critical flaws: poor 3D consistency (e.g., blurred instance boundaries and unstable cross-view semantic association) and insufficient structural awareness near ambiguous object boundaries. To a...
Ying-Han Zhou, Fan Zhou· Italian National Conference...· 0 citations
Automated road extraction from high-resolution satellite imagery is critical for geospatial applications. However, accurate segmentation requires balancing global topological continuity with local boundary precision. Existing methods often struggle with this tradeoff, while directly adapting large-scale foundation mode...
Li-Lun Deng, Jiang-She Zhang, Hao-Wen Bai et al.· IEEE Journal of Selected Top...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
