Biqi Wu

Recent advances in no-reference point cloud quality assessment (NR-PCQA) have been largely driven by deep learning techniques. To further enhance prediction accuracy, existing methods often rely on multi-modal feature fusion. However, the introduction of multimodality ignores the consideration of the model’s generalization ability. Moreover, it often introduces additional computational overhead inference. To address these challenges, we propose a novel NR-PCQA method based on domain-invariant learning framework (DI-PCQA). Specifically, the input point cloud is first projected to obtain a spatial-domain visual representation. To construct different representations with the same origin and semantics, this spatial information is further transformed into a frequency domain representation. Both spatial and frequency features are then fed into a weight-shared encoder to extract feature. Subsequently, an adversarial domain classification task is introduced. We attach the gradient reversal layer to the weight-shared encoder, enabling the encoder to generate features that can confuse the domain classifier. This adversarial training encourages the weight-shared encoder to learn domain-invariant semantic features rather than overfitting to a single data distribution. And the spatial features are simultaneously regressed to quality scores. Finally, DI-PCQA employs a decoupled training-testing strategy. It leverages both spatial and frequency domain inputs to learn domain-invariant representations during training, but performs efficient quality prediction using only spatial information at test time. We conduct extensive tests on public databases and achieve superior performance. Further evaluations confirm its generalization ability and fast inference speed.

Point cloud quality assessment (PCQA) aims to establish an objective and unified standard for point cloud evaluation. With the rapid advancement of large language models (LLMs), their application in PCQA has recently gained attention. Existing LLM-based PCQA methods typically adopt static quality description and perceptual information alignment to judge the relevance of each quality level. This overlooks the dynamic nature of human perception, which is progressively refined through multi-level visual stimuli. And the strategy of single-level alignment constrains the variability of the quality description process, thereby resulting in bias. To address this, we propose a dynamic alignment learning framework that simulates progressive quality perception via hierarchical perceptual stimuli. Specifically, to provide a more comprehensive visual information, we capture visual information from two perspectives: from 2D to 3D and from static to dynamic. In addition, a multi-perception learner is utilized to enhance the understanding of these visual information. Subsequently, we employ learnable weights to simulate perceptual stimuli at different levels and embed them into the quality description. During this process, we apply masking to certain perceptual stimuli to illustrate the impact of partial perceptual loss on quality description. Finally, the contrastive learning is introduced to further refine the aligned information under different perceptual stimuli, thereby improving the accuracy of quality assessment. We conduct comprehensive experiments on the public databases, and the results demonstrate that our method achieves state-of-the-art (SOTA) performance. Further analysis confirms the robustness of our approach across various scenarios.

Point cloud quality assessment (PCQA) aims to provide an objective and unified evaluation of the quality of the point cloud. Existing research in this field lacks a comprehensive exploration of cross-modal perceptual feature fusion, overlooking the intrinsic correlations and complementarities across different modalities. To establish explicit relationships between modal features and capture the importance differences across modalities, we propose a novel method based on the cross-modal deep-coupling framework (CMDC-PCQA) for evaluating objective indicators of point clouds. First, we divide the point cloud into patches of equal size and propose a point cloud feature extraction (SGSA) module based on point space and graph structure, which employs self-attention mechanism for fusion learning. Second, we capture the projected images of point clouds from multiple viewpoints. To improve the perception of 2-D texture and semantic features, we embed attention to spatial and channel information in the local acceptance domain of convolutional neural networks. Third, we propose a method called dual-stage feature attention interaction module (DFAM). It is designed to update the local and global weights of the semantic and geometric features that fully characterize deep coupling. The proposed method is validated on the SJTU-PCQA, WPC, and WPC2.0 databases. Experimental results demonstrate that our method has surpassed the state-of-the-art PCQA methods, which validate its effectiveness in the PCQA task.