How to objectively evaluate the effect of different vectorization models in measuring similarity between patents is a fundamental issue, which can help to select high-performance vectorization models to support advanced patent services. Based on the rank consistency index and hypothesis testing approach, a framework for evaluating the effect of different vectorization models on patents’ similarity is proposed based on whether the model can accurately predict the similarity ranking of patents. Integrating the factors of time and technical field, an empirical study is conducted under the proposed framework to objectively evaluate the effect of six mainstream text vectorization models for assessing the semantic similarity of patents, which is evaluated based on Chinese patents (English Translation) from 2010 to 2024. The results show that the performance of Llama 2 is the best among six compared models in all years and in all technical fields. The proposed framework can objectively evaluate the similarity measurement effect of different vectorization models and provides a basis for the selection of the vectorization model for patent semantic similarity measurement for advanced patent services.

Accurate indoor 3D reconstruction requires both the preservation of informative visual evidence and an efficient scene representation. Existing 3D Gaussian Splatting (3DGS) methods often struggle with uneven visual information distribution in low-light regions, geometric ambiguity in textureless regions, and redundant Gaussian primitives. These issues lead to insufficient preservation of weak visual details and the accumulation of redundant scene primitives. To address them, we propose a darkness-aware and sparsity-constrained 3DGS framework for lightweight indoor scene modeling. Spherical Gaussians and normal-guided SDF optimization provide complementary geometric priors for sharp edges and textureless planar regions. More importantly, the proposed Darkness-Aware Weighted Loss (DAWL) adaptively reweights pixels according to luminance, compensating for the unequal contribution of visual information across illumination regions and preserving details in shadowed and underexposed areas. The Sparsity Constraint Loss (SCL) promotes opacity decay and pruning of low-contribution Gaussian primitives, thereby reducing redundancy in the explicit 3D scene representation. Experiments on the ScanNet and ScanNet++ datasets demonstrate competitive SSIM, PSNR, and LPIPS performance. Compared with the SENPE-GS baseline, our method reduces the number of Gaussian primitives by approximately 34\% while maintaining reconstruction quality. These results demonstrate the effectiveness of illumination-aware supervision and redundancy-constrained representation for efficient and high-fidelity indoor scene modeling.

3D visual grounding is a fundamental task for human–machine interaction, aiming to localize specific objects in complex 3D point clouds based on natural language descriptions. Despite recent advancements, existing Transformer-based architectures often rely on absolute position embeddings and heuristic query initialization, which lack the capacity to capture fine-grained relative spatial dependencies and fail to effectively filter out scene clutter. In this paper, we propose SESQ, a novel framework that synergizes Spatially Aware Encoding and Semantically Guided Querying for 3D grounding. Our approach introduces two key innovations. First, we propose the Rotary Spatially Aware Encoder (RSAE), which incorporates Rotary Position Embeddings (RoPE) into the self-attention layers. By transforming 3D coordinates into a rotary representation, RSAE enables the model to inherently capture relative spatial distances and maintains geometric consistency throughout the encoding stage. Second, a Semantic Query Initialization (SQI) module is designed to initialize object queries by explicitly computing the cross-modal similarity between textual embeddings and visual point cloud features. By replacing traditional heuristic-based selection with semantic-aware alignment, SQI ensures that the decoding process originates from contextually relevant object candidates, significantly reducing the impact of task-irrelevant distractors. Extensive experiments on ScanRefer and ReferIt3D (Nr3D/Sr3D) benchmarks demonstrate the effectiveness of our framework. Compared to the baseline EDA, our method achieves a significant performance gain of 2.68% in overall Acc@0.5 on ScanRefer, a 4.9% improvement on the challenging Nr3D “Hard” subset, and a 1.1% increase in overall Acc@0.25 on Sr3D.

Vision-based 3D sensing provides an effective approach for constructing human-centric digital twins in applications such as ergonomic assessment and human–robot collaboration. However, reconstructing reliable dynamic human digital twins from visual sensor observations remains challenging due to large articulated deformation, which often causes surface discontinuities in existing 3D Gaussian Splatting (3DGS)-based human avatars. Although current methods achieve high image-level rendering quality, their Gaussian primitives are not explicitly adapted to pose-induced surface deformation, resulting in cracks and holes during motion. In this work, we propose ElasticGS, a geometry-consistent human digital twin reconstruction framework for vision-based 3D sensing. ElasticGS introduces a training-free Pose-Aware Dynamic Covariance Adaptation strategy, which dynamically adjusts the rotation and anisotropic scale of Gaussian primitives according to local human surface deformation. Specifically, localized Principal Component Analysis (PCA) is performed on deformed SMPL-X mesh neighborhoods to estimate surface stretching directions and magnitudes, enabling Gaussian representations to maintain continuous surface coverage under complex poses. Furthermore, we propose the Avatar Surface Integrity Score (ASIS), a reference-free metric that evaluates structural completeness and surface compactness of reconstructed human avatars without requiring pixel-aligned ground truth. Experiments on the X-Humans and AvatarReX datasets demonstrate that ElasticGS significantly improves surface integrity while maintaining competitive image-level sensing consistency. Compared with ExAvatar, ElasticGS improves ASIS from 0.642 to 0.846 on X-Humans and from 0.603 to 0.688 on AvatarReX. These results demonstrate the effectiveness of pose-aware covariance adaptation for robust human digital twin reconstruction in vision-based 3D sensing systems.

Vision-based 3D sensing provides an effective approach for constructing human-centric digital twins in applications such as ergonomic assessment and human–robot collaboration. However, reconstructing reliable dynamic human digital twins from visual sensor observations remains challenging due to large articulated deformation, which often causes surface discontinuities in existing 3D Gaussian Splatting (3DGS)-based human avatars. Although current methods achieve high image-level rendering quality, their Gaussian primitives are not explicitly adapted to pose-induced surface deformation, resulting in cracks and holes during motion. In this work, we propose ElasticGS, a geometry-consistent human digital twin reconstruction framework for vision-based 3D sensing. ElasticGS introduces a training-free Pose-Aware Dynamic Covariance Adaptation strategy, which dynamically adjusts the rotation and anisotropic scale of Gaussian primitives according to local human surface deformation. Specifically, localized Principal Component Analysis (PCA) is performed on deformed SMPL-X mesh neighborhoods to estimate surface stretching directions and magnitudes, enabling Gaussian representations to maintain continuous surface coverage under complex poses. Furthermore, we propose the Avatar Surface Integrity Score (ASIS), a reference-free metric that evaluates structural completeness and surface compactness of reconstructed human avatars without requiring pixel-aligned ground truth. Experiments on the X-Humans, AvatarReX, and People-Snapshot datasets demonstrate that ElasticGS significantly improves surface integrity while maintaining competitive image-level sensing consistency. Compared with ExAvatar, ElasticGS maintains satisfactory rendering quality while improving ASIS from 0.741 to 0.961 on X-Humans, from 0.871 to 0.949 on AvatarReX, and from 0.874 to 0.952 on People-Snapshot. These results demonstrate the effectiveness of pose-aware covariance adaptation for robust human digital twin reconstruction in vision-based 3D sensing systems.

3D referring expression instance segmentation aims to identify and segment target objects in complex scenes according to natural language descriptions. This task is particularly challenging due to spatial ambiguity and unstable query-instance associations caused by weak linguistic supervision. Previous methods relying on implicit spatial modeling often struggle with confused localization and ambiguous instance aggregation. To address these limitations, we propose SpaDis, a new end-to-end framework that jointly achieves Spatial Semantic Enhancement (SSE) and Discriminative Query Refinement (DQR). Specifically, the SSE module explicitly encodes spatial relationships via geometric cues to strengthen query-level semantic representations, while the DQR module performs a discriminative refinement on queries to establish robust associations, enforcing intra-instance consistency and inter-instance separation before decoding. Extensive experiments on multiple benchmarks demonstrate that SpaDis achieves consistent performance gains, validating the effectiveness of explicit spatial modeling and discriminative feature optimization in complex 3D scenes.