Haihong Xiao

Palmprint and palm vein recognition are vital biometric technologies for secure authentication. The primary challenge lies in modeling the complex, unstructured textures of palmprints and the continuous vascular topology of palm veins, both of which require capturing long-range spatial dependencies. Traditional handcrafted and CNN-based methods partially address these challenges but are constrained by local receptive fields and manually designed features. In contrast, Transformers leverage global self-attention to model cross-scale correlations in unstructured palmprint patterns, while Mamba state space models (SSMs) offer linear computational complexity and hardware efficiency, making them well-suited for capturing continuous topological structures in palm veins. We present the first systematic evaluation of Transformer and Mamba architectures for palmprint and palm vein recognition, covering 13 public datasets (eight palmprint, five palm vein) and 17 deep models (nine Transformer variants, eight Mamba architectures), alongside traditional methods and CNN baselines. Key findings include: (i) XCiT achieves the best palmprint recognition (open-set ACC = 95.31%, EER = 1.75%) via cross-covariance attention; (ii) MambaVision achieves the best palm vein recognition (open-set ACC = 91.25%, TAR@FAR [ ] = 76.81%) via hybrid CNN–SSM design; (iii) synthetic data augmentation improves few-shot performance by up to 12.6% ACC on challenging datasets while exhibiting boundary effects on high-quality data. We further quantify the accuracy–efficiency trade-off, offering practical deployment insights and highlighting the complementary roles of Transformer and Mamba architectures.

Existing NeRF-based methods for reconstructing large-scale scenes face challenges in visual quality and rendering speed due to spectral biases and extensive sampling requirements. Recent 3DGS-based methods for real-time rendering of 3D objects and small scenes outperform NeRF, but several issues persist when extending these techniques to large-scale scenes. These include robust rendering in weak-texture areas, effective densification under memory constraints, finer detail rendering, and achieving natural lighting transitions. To address these, we introduce a geometry-aware 3DGS method for efficient real-time rendering of large scenes. First, we propose a geometry-guided anchor point initialization that reduces noise away from structural surfaces and generates new points in weak texture areas, particularly for large-scale datasets. We also present a structure-aware joint densification strategy combining surface- and curvature-based densification, ensuring Gaussian points are near structural surfaces and increasing density in low-curvature areas. Additionally, we propose a hash grid-assisted, viewpoint-sensitive feature enhancement scheme to improve detail rendering and natural lighting transitions. Our method achieves superior rendering quality compared to state-of-the-art methods while maintaining reasonable memory usage. Extensive experiments across 16 scenes, including 11 from five public datasets (MatrixCity-Aerial, Mill-19, Tanks & Temples, WHU, and UrbanScene3D) and five self-collected scenes from SCUT-CA and plateau regions, demonstrate its generalization capability. Codes are available at https://github.com/SCUT-BIP-Lab/Geo_gs.

Giving machines the ability to infer the complete 3D geometry and semantics of complex scenes is crucial for many downstream tasks, such as decision-making and planning. Vision-centric Semantic Scene Completion (SSC) has emerged as a trendy 3D perception paradigm due to its compatibility with task properties, low cost, and rich visual cues. Despite impressive results, current approaches inevitably suffer from problems such as depth errors or depth ambiguities during the 2D-to-3D transformation process. To overcome these limitations, in this paper, we first introduce an Optical Flow-Guided (OFG) Depth-Net that leverages the strengths of pretrained depth estimation models, while incorporating optical flow images to improve depth prediction accuracy in regions with significant depth changes. Then, we propose a depth ambiguity-mitigated feature lifting strategy that implements deformable cross-attention in 3D pixel space to avoid depth ambiguities caused by the projection process from 3D to 2D and further enhances the effectiveness of feature updating through the utilization of prior mask indices. Moreover, we customize two subnetworks: a residual voxel network and a sparse UNet, to enhance the network’s geometric prediction capabilities and ensure consistent semantic reasoning across varying scales. By doing so, our method achieves performance improvements over state-of-the-art methods on the SemanticKITTI, SSCBench-KITTI-360 and Occ3D-nuScene benchmarks.

Multi-View Stereo (MVS) reconstructs detailed 3D structures from multi-view images by establishing spatial correspondences. While learning-based methods have significantly advanced the MVS task, challenges such as ambiguous matching caused by textureless surfaces and lighting variations persist. To address these issues, we propose GAP-MVSNet, a framework that leverages surface normals from a monocular normal foundation model as priors to enhance the geometric awareness of reconstruction targets. In this work, surface normal priors are seamlessly integrated into the MVS pipeline to improve depth prediction robustness and accuracy. Specifically, we introduce a structure-aware feature pyramid network that incorporates surface normal information and utilizes uncertainty-aware feature resampling to extract robust image features. Additionally, we present the spatial geometry enhanced regularization that combines sampled depth hypotheses with surface normals to generate a spatial geometric prior, guiding the cost regularization process and enforcing strong spatial coherence, particularly in textureless regions. Furthermore, we design a local consistency depth refinement module that utilizes surface normals to establish depth relationships as a local geometric prior, thereby refining classification-based depth predictions and aligning them with ground truth depth. Extensive experiments on the DTU and Tanks & Temples datasets demonstrate that our method achieves state-of-the-art performance.

Reconstructing 3D indoor scenes presents significant challenges, requiring models capable of inferring both planar surfaces and intricate details. Although recent methods can generate complete surfaces, they often struggle to simultaneously reconstruct low-texture regions and high-frequency details due to non-local effects. In this paper, we introduce a novel triangle-based triplane representation, named (tri $^{2}$ plane), specifically designed to account for the diverse spatial feature distribution and information density of indoor environments. Our method begins by projecting point clouds onto three orthogonal planes, followed by 2D Delaunay triangulation. This representation enables adaptive encoding of low-texture and high-frequency regions by employing triangles of variable sizes. Moreover, we develop a dual tri$^{2}$ plane framework that incorporates both geometric and semantic information, significantly enhancing the reconstruction quality. We combine these key modules and evaluate our method on benchmark indoor scene datasets. The results unequivocally demonstrate the superiority of our proposed method over the state-of-the-art Occ-SDF. Specifically, our method achieves significant improvements over Occ-SDF, with margins of 1.3, 1.7, and 2.3in F-score on the ScanNet, Tanks & Temples, and Replica datasets, respectively. To facilitate further research, we will make our code publicly available.

Predicting per-voxel occupancy status and corresponding semantic labels in 3D scenes is pivotal to 3D intelligent perception in autonomous driving. In this paper, we propose a novel semantic scene completion framework that can generate complete 3D volumetric semantics from a single image at a low cost. To the best of our knowledge, this is the first endeavor specifically aimed at mitigating the negative impacts of incorrect voxel query proposals caused by erroneous depth estimates and enhancing interactions for positive ones in camera-based semantic scene completion tasks. Specifically, we present a straightforward yet effective Semantic-aware Guided (SAG) module, which seamlessly integrates with task-related semantic priors to facilitate effective interactions between image features and voxel query proposals in a plug-and-play manner. Furthermore, we introduce a set of learnable object queries to better perceive objects within the scene. Building on this, we propose an Interactive Refinement Transformer (IRT) block, which iteratively updates voxel query proposals to enhance the perception of semantics and objects within the scene by leveraging the interaction between object queries and voxel queries through query-to-query cross-attention. Extensive experiments demonstrate that our method outperforms existing state-of-the-art approaches, achieving overall improvements of 0.30 and 2.74 in mIoU metric on the SemanticKITTI and SSCBench-KITTI-360 validation datasets, respectively, while also showing superior performance in the aspect of small object generation.

Multi-view stereo (MVS) aims to reconstruct the dense 3D geometry of a scene by processing and relating images captured from different viewpoints. Despite impressive successes, most existing techniques simply supervise cost volumes or depth maps through conventional classification or regression methods, thereby inadequately exploring the depth representation’s full potential. Moreover, reconstructing areas with occlusions or weak textures continues to be a long-standing challenge within MVS. Another critical issue, frequently neglected, is the potential inaccuracy of ground truth depths, as evidenced in datasets like DTU. To address these problems, we introduce EA-MVSNet, an innovative error-aware MVS framework designed to enhance depth prediction. The key contributions of this work include three parts: (1) We present a novel error-aware depth representation that enhances depth prediction accuracy through error-aware learning, thereby improving reconstruction quality. (2) We develop a Deformable Feature Pyramid Network (DFPN), meticulously designed to augment reconstruction details in occluded and texture-deficient areas. (3) We introduce a cross-view consistency guidance module into the learning process, effectively mitigating the detrimental effects of ground truth depth inaccuracies and fostering faster convergence. Comprehensive experiments on the DTU dataset and Tanks and Temples dataset validate the superiority of our EA-MVSNet. Compared to the preceding UniMVSNet, EA-MVSNet achieves a notable 7.6% decrease in overall reconstruction error on the DTU dataset, and boosts the mean F-score by 3.0% and 4.1% in the intermediate and advanced groups of the Tanks and Temples dataset, respectively, surpassing most recent state-of-the-art methods.