Aug 2026· International Conference on Digital Image Processing· Vol 14351, pp. 143511L - 143511L-11· 0 citations
Engineering
TL;DR
A 3D Local- Global Linear Attention Mechanism (LG-LAM) is devised that efficiently captures long-range contextual information with linear complexity, enabling a comprehensive understanding of the 3D scene without heavy computational burdens.
Abstract
3D Semantic Scene Completion (SSC), a cornerstone task in computer vision, aims to simultaneously predict the geometric structure and semantic content of 3D scenes from sparse inputs. This capability is crucial for advancing applications in robotics, autonomous driving, and virtual reality. However, SSC faces significant challenges, including the high computational cost of capturing long-range contextual information and the scarcity of 3D semantic labels leading to overfitting. To address these limitations, we propose an enhanced network for semantic scene completion. Firstly, we devise a 3D Local- Global Linear Attention Mechanism (LG-LAM) that efficiently captures long-range contextual information with linear complexity, enabling a comprehensive understanding of the 3D scene without heavy computational burdens. Secondly, a 3D Feature Augmentation Module (FAM) is integrated to enrich feature diversity through rotation-invariant learning, mitigating overfitting and enhancing the model’s robustness given limited annotations. Extensive experiments on the NYUCAD dataset demonstrate that our method achieves state-of-the-art performance among non-iterative methods while introducing negligible computational overhead.
Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supervised methods. However, deploying these models in real-world scenarios is severely hindered by their inability to efficiently handle streaming RGB-D inputs and their inherent vulnerability to noise 2D segmentation masks. To address these critical limitations, we propose Stream3Dv2, a novel training-free framework designed for robust streaming 3D perception. Stream3Dv2 processes sequential data through an original nested local-to-historical architecture, capturing multi-view consistency while circumventing the high computational overhead so as to support timely responses. At its core, we introduce a comprehensive geometric-semantic fusion mechanism that resolves geometric noise and semantic ambiguity by explicitly utilizing semantic guidance and formulating 3D segmentation as solving point-and-set merging and partitioning problems. Furthermore, we present an innovative manifold-distance-based point cloud refinement strategy. This approach leverages local manifold graphs for point-to-manifold optimization that mitigates the boundary delineation failures caused by Euclidean-distance metrics, and employs geometric bounding boxes to dynamically activate and update historical instances for achieving rapid manifold-to-manifold refinement. Extensive experiments on public datasets demonstrate that Stream3Dv2 consistently outperforms existing baselines in foundational open-vocabulary streaming 3D segmentation and detection. Finally, we show that integrating our framework with an LLM-based agent enables advanced language-driven 3D scene understanding, underscoring its potential for open-world embodied intelligence. Code will be updated at https://github.com/SubmissionsIn/Stream3D.
Semantically-guided progressive network (SGP-Net) is proposed, a semantically guided progressive refinement framework for MDE based on multi-task learning that improves key relative-error and accuracy metrics over the DCDepth baseline and remains competitive with recent methods.
Henan Hu, Xu Cheng, Rong-Hua Li et al.· Measurement science and tech...· 0 citations
This study presents an enhanced YOLOv11 framework specifically designed for global geometric perception and high-fidelity single-stage 6D pose regression, which validate that the integration of global geometric awareness consistently outperforms the vanilla YOLOv11 and other classical baselines in complex scenarios.
Pin Tao, Wen Zhu· International Conference on...· 0 citations
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.
Waseem Iqbal, J. Paffenholz· The International Archives o...· 0 citations
The integration of novel view synthesis (NVS) and open-vocabulary segmentation (OVS) has recently yielded powerful feed-forward 3D foundation models. However, their inherent reliance on static-scene assumptions leads to severe misalignment of spatial features in unconstrained dynamic environments. To bridge this critical gap, we propose SPAR, a novel joint semantic-geometric encoding architecture that explicitly isolates transient dynamic noise prior to latent space aggregation. Furthermore, we introduce a dynamic-region-aware end-to-end training paradigm that structurally couples motion estimation with multi-view visual and semantic learning. This unified approach enables the network to inherently resolve motion conflicts and distill multi-view consistent, temporally stable scene representations from dynamic inputs. Extensive experiments on the challenging D-RE10K benchmark demonstrate that SPAR achieves state-of-the-art performance. Our end-to-end approach achieves exceptional novel view synthesis quality, yielding a PSNR of 22.15 dB and 23.33 dB given only 3 and 4 input views respectively. Despite being trained in a self-supervised manner, our model achieves an mIoU of 88.5% for motion mask prediction. Furthermore, our analysis reveals a strong inter-task synergy between photometric scene reconstruction and semantic understanding, where semantic synthesis learning consistently enhances photometric fidelity in novel view rendering. Code will be available at https://github.com/dmucby/SPAR.
3D object detection stands as a pivotal task in scene understanding. However, two primary bottlenecks constrain current methodologies: semantic ambiguity arising from spatial misalignment during cross-modal fusion, and the inadequate contextual representation of individual candidate points within complex scenes. To address these challenges, this paper presents a Graph-driven Contextual Synergy Network (GCS3D), which is designed to systematically enhance point representations across both semantic and geometric dimensions. Specifically, the proposed method incorporates a Semantic Representation Rectification (G-SRR) module for cross-modal representation enhancement. By performing region-level semantic aggregation based on 3D neighborhoods to mitigate projection bias, this module achieves robust cross-modal fusion through a Spatial-aware Gating Mechanism (SGM) that adaptively regulates visual feature injection. Regarding contextual correlation modeling, the framework introduces a Graph-guided Geometric Consistency Interaction (G-GCI) module. By constructing a local topology graph among anchors and executing position-aware feature interaction, this module facilitates the aggregation of complementary neighborhood information, thereby bolstering the feature consistency and discriminability of anchor representations. Furthermore, a Spatial-Scale Aware Assigner (SSA-Assigner) is utilized to dynamically allocate supervision signals based on prediction quality, fully exploiting the performance potential inherent in the enhanced anchor representations. Extensive experiments on the SUN RGB-D and ScanNet V2 datasets demonstrate that GCS3D achieves superior results with mAP@0.25 scores of 70.39 and 73.86 respectively, validating the effectiveness and robustness of the proposed strategy in complex indoor scenes.
