The paper introduces a novel imputation-free deep incomplete multi-view clustering method called Deep Variational Incomplete Multi-View Clustering (DVIMC). DVIMC aims to reveal shared clustering structures within multi-view data where only partial views of the samples are available. The method leverages variational autoencoders (VAEs) and the Product-of-Experts (PoE) approach to efficiently aggregate information from multiple views, obtaining a common representation. To enhance the shared information in this representation, a coherence objective is introduced to mitigate the influence of information imbalance. By incorporating a Mixture-of-Gaussians (MoG) prior, DVIMC learns a common representation with clustering-friendly structures. Extensive experiments on four datasets show that DVIMC achieves competitive clustering performance compared to state-of-the-art methods, demonstrating its effectiveness in handling incomplete multi-view data. The paper also includes an ablation study and parameter analysis to validate the contributions of each component of the method.The paper introduces a novel imputation-free deep incomplete multi-view clustering method called Deep Variational Incomplete Multi-View Clustering (DVIMC). DVIMC aims to reveal shared clustering structures within multi-view data where only partial views of the samples are available. The method leverages variational autoencoders (VAEs) and the Product-of-Experts (PoE) approach to efficiently aggregate information from multiple views, obtaining a common representation. To enhance the shared information in this representation, a coherence objective is introduced to mitigate the influence of information imbalance. By incorporating a Mixture-of-Gaussians (MoG) prior, DVIMC learns a common representation with clustering-friendly structures. Extensive experiments on four datasets show that DVIMC achieves competitive clustering performance compared to state-of-the-art methods, demonstrating its effectiveness in handling incomplete multi-view data. The paper also includes an ablation study and parameter analysis to validate the contributions of each component of the method.