Aug 2026· The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences· 0 citations· 12 references
TL;DR
A lightweight boundary-aware learning framework that explicitly models boundary regions during training is proposed, showing that incorporating boundary-aware supervision provides an effective and efficient approach to improving segmentation quality in challenging regions.
Abstract
Abstract. Accurate semantic segmentation of 3D point clouds is essential for applications in photogrammetry, robotics, and large-scale scene understanding. While recent point-based architectures such as PointNeXt achieve strong performance through hierarchical feature learning, they still struggle near semantic boundaries, where points from different classes share local neighborhoods and feature aggregation leads to oversmoothing and ambiguous predictions. To address this limitation, we propose a lightweight boundary-aware learning framework that explicitly models boundary regions during training. The method introduces an auxiliary boundary prediction head that learns boundary cues from local semantic disagreement and integrates them into the segmentation process through a simple late-stage feature fusion mechanism. This design enhances feature discrimination near class transitions without modifying the backbone architecture or increasing inference complexity. Experiments on the S3DIS benchmark with the standard 6-fold cross-validation protocol show consistent improvements over the PointNeXt baseline, achieving gains of 3.22% in mean Intersection over Union (mIoU) and 2.85% in mean class accuracy (mACC) (relative), with notably improved predictions along object boundaries. These results show that incorporating boundary-aware supervision provides an effective and efficient approach to improving segmentation quality in challenging regions.
3D semantic segmentation has achieved remarkable advances with powerful architectures and large-scale datasets. However, most existing approaches perform under closed-set assumptions, limiting their applicability in dynamic real-world environments where novel categories frequently emerge. This motivates the task of open-world semantic segmentation (OWSS), in which a model must not only identify unknown objects at inference time but also incorporate them with previously learned classes once annotated. To address this challenge, we propose PointPDF V2, a unified framework that integrates open-set recognition (OSS) and incremental learning (IL) into a cohesive pipeline. Our design consists of three components: a multistage pseudo-labeling (MPL) module that generates pseudo-labels for unknown classes by leveraging confidence and geometric information; a distribution-aware confidence estimation (DCE) module that models class-wise semantic distributions to separate known and unknown categories; and a weighted knowledge distillation (WKD) module that balances old-class retention with novel-class adaptation in IL. In addition to the standard OWSS setting, we introduce a more challenging continual OWSS (COWSS) protocol in 3D, where models must simultaneously preserve the known-class performance, acquire new knowledge, and still identify the remaining unknowns across sequential updates. Extensive experiments on both indoor and outdoor benchmarks show that PointPDF V2 consistently outperforms state-of-the-art baselines in OSS, IL, and C-OWSS. We shall release our code and models upon publication of this work.
Jinfeng Xu, Xianzhi Li, Yixue Hao et al.· IEEE Transactions on Pattern...· 0 citations
COSMOS-NeRF, a volumetric model that extends the Mip-NeRF 360 architecture by incorporating a supervised semantic channel and a multi-view consensus mechanism, represents a significant advancement in integrating semantic and structural information within three-dimensional environments.
Abstract. OpenStreetMap (OSM) is a representative open geospatial platform that provides free access to major spatial objects, including buildings worldwide, constructed through crowdsourcing-based manual digitization. However, subjective differences among contributors and the absence of unified quality control standards have led to the accumulation of positional offsets and boundary shape errors in building polygons. To address this issue, studies using deep learning-based semantic segmentation for OSM quality improvement have been conducted. Nevertheless, Transformer-based segmentation models exhibit an under-segmentation tendency that merges adjacent buildings into a single object, along with limitations in precise boundary delineation. To overcome these challenges, this study proposes a two-stage framework that integrates SegFormer, which excels in global context recognition, with SAM 2, which is capable of precise boundary segmentation. In the first stage, SegFormer semantically segments building regions from a true orthoimage, and in the second stage, SAM 2 infers object-level precise boundaries using the bounding boxes of OSM polygons as box prompts. The two results are combined into a prior probability map, enabling uncertain boundary regions to be re-evaluated in an unsupervised manner. In experiments conducted over the Suseo-dong area in Gangnam-gu, Seoul, the proposed method achieved a BIoU of 70.40%, an improvement of 23.85 percentage points over OSM building data, with consistent performance gains across all evaluation metrics. This framework offers scalability applicable to any region worldwide without additional label construction, provided that high-resolution true orthoimagery and OSM data are available.
Inhyeok Lee, Chong Lee, J. Cheon et al.· The International Archives o...· 0 citations
A SAM-guided framework for point cloud oversegmentation that significantly improves boundary recall and maintains high oracle accuracy while maintaining high oracle accuracy, and generalizes well to unseen datasets without retraining, showing strong cross-dataset inference capability.
Dening Lu, Michael A. Chapman, Jonathan Li· The International Archives o...· 0 citations
Abstract. Point cloud semantic segmentation of indoor environments is a fundamental task in 3D scene understanding. However, existing methods mainly rely on geometric structures and color information, which are prone to error results in scenarios involving occlusion, sparse sampling, and geometrically similar structures. To address this issue, this paper proposes a text-knowledge-guided method for the point cloud semantic segmentation of indoor 3D scene. Built upon RandLA-Net as the baseline, the proposed method first constructs the textual semantic prototypes using multi-template prompts, and further enhances the stability of semantic anchors through periodic prototype refreshing. Then, a cross-modal semantic feature alignment mechanism is introduced at both the shallow and the high-level feature stages. Through feature alignment, bidirectional semantic interaction, and gated fusion, textual priors are progressively injected into the point cloud feature learning process. Finally, the model is jointly trained with a point-wise classification loss, a text-prototype alignment constraint, and a boundary optimization constraint to improve the semantic feature discrimination and segmentation boundary quality. Experimental results on the S3DIS dataset demonstrate that the proposed method achieves 86.8% OA, 81.6% mAcc, and 67.2% mIoU, exhibiting more stable segmentation performance in complex indoor scenes. As a consequence, these results indicate that incorporating textual semantic priors can effectively enhance high-level semantic representations of point clouds, providing a feasible solution for indoor 3D scene understand.
Jinyu Tan, Juntao Yang, Yutao Zhang et al.· The International Archives o...· 0 citations
This work investigates whether a frozen, self-supervised point transformer already contains the structural information required to isolate object instances without any handcrafted geometric prior, and develops a training-free segmenter that groups points via connected components on a key-similarity graph, using neither density-based clustering nor proximity priors.
Ted Lentsch, Santiago Montiel-Mar'in, Holger Caesar et al.· 0 citations