You Only Need One Stage: Novel-View Synthesis From A Single Blind Face Image

TL;DR

This paper introduces NVB-Face, a one-stage method that directly generates consistent novel-view face images from a single degraded face image, bypassing the need for high-resolution restoration.

Contribution

The paper presents a novel single-stage framework that extracts features directly from degraded images and synthesizes multi-view faces using a diffusion model, improving over traditional two-stage methods.

Findings

Outperforms two-stage approaches in consistency

Produces higher fidelity novel-view images

Handles degraded input images effectively

Abstract

We propose a novel one-stage method, NVB-Face, for generating consistent Novel-View images directly from a single Blind Face image. Existing approaches to novel-view synthesis for objects or faces typically require a high-resolution RGB image as input. When dealing with degraded images, the conventional pipeline follows a two-stage process: first restoring the image to high resolution, then synthesizing novel views from the restored result. However, this approach is highly dependent on the quality of the restored image, often leading to inaccuracies and inconsistencies in the final output. To address this limitation, we extract single-view features directly from the blind face image and introduce a feature manipulator that transforms these features into 3D-aware, multi-view latent representations. Leveraging the powerful generative capacity of a diffusion model, our framework synthesizes high-quality, consistent novel-view face images. Experimental results show that our method significantly outperforms traditional two-stage approaches in both consistency and fidelity.