3DEnhancer: Consistent Multi-View Diffusion for 3D Enhancement
This work addresses the challenge of generating high-quality, consistent 3D models from limited data for applications in computer vision and graphics, representing a novel method for a known bottleneck.
The paper tackles the problem of low-resolution and inconsistent multi-view 3D generation by proposing 3DEnhancer, a pipeline that enhances coarse 3D inputs using a multi-view latent diffusion model, resulting in significant performance improvements over existing methods in multi-view enhancement and 3D optimization tasks.
Despite advances in neural rendering, due to the scarcity of high-quality 3D datasets and the inherent limitations of multi-view diffusion models, view synthesis and 3D model generation are restricted to low resolutions with suboptimal multi-view consistency. In this study, we present a novel 3D enhancement pipeline, dubbed 3DEnhancer, which employs a multi-view latent diffusion model to enhance coarse 3D inputs while preserving multi-view consistency. Our method includes a pose-aware encoder and a diffusion-based denoiser to refine low-quality multi-view images, along with data augmentation and a multi-view attention module with epipolar aggregation to maintain consistent, high-quality 3D outputs across views. Unlike existing video-based approaches, our model supports seamless multi-view enhancement with improved coherence across diverse viewing angles. Extensive evaluations show that 3DEnhancer significantly outperforms existing methods, boosting both multi-view enhancement and per-instance 3D optimization tasks.