Abstract
We address the task of point cloud denoising by leveraging a diffusion-based generative framework augmented with adversarial training. While recent diffusion models have demonstrated strong capabilities in learning complex data distributions, their effectiveness in recovering fine geometric details remains limited, especially under severe noise conditions. To mitigate this, we propose the Adversarial Diffusion Bridge Model (ADBM), a novel approach for denoising 3D point cloud data by integrating a diffusion bridge model with adversarial learning. ADBM incorporates a lightweight discriminator that guides the denoising process through adversarial supervision, encouraging sharper and more faithful reconstructions. The denoiser is trained using a denoising diffusion objective based on a Schrödinger Bridge, while the discriminator distinguishes between real, clean point clouds and generated outputs, promoting perceptual realism. Experiments are conducted on the PU-Net and PC-Net datasets, with performance evaluation employing the Chamfer distance and Point-to-Mesh metrics. The qualitative and quantitative results both highlight the effectiveness of adversarial supervision in enhancing local detail reconstruction, making our approach a promising direction for robust point cloud restoration.