提升人体图像修复的保真度，通过扩增潜在空间通道实现。
LCUDiff: Latent Capacity Upgrade Diffusion for Faithful Human Body Restoration
- 将扩散模型潜空间从4通道升级至16通道，增强细节表达能力。
- 在合成与真实数据上均实现更高保真度和更少伪影。
- 适合需要高精度人体修复的应用场景，如影视修复、数字人生成。
现有针对以人物为中心图像修复的方法在人体修复（HBR）中常因保真度不足而受限。基于扩散模型的修复方法通常依赖预训练文本到图像扩散模型，其变分自编码器（VAE）会显著制约修复质量。本文提出LCUDiff，一种稳定的单步框架，将预训练潜空间扩散模型从4通道扩展至16通道。针对VAE微调，采用通道分裂蒸馏（CSD），使前4个通道保持与预训练先验一致，新增通道用于高效编码高频细节。进一步设计先验保持适配（PPA），平滑4通道扩散主干与16通道潜空间之间的不匹配。此外，提出解码器路由（DeR），基于修复质量评分对每张样本动态选择解码器，提升复杂条件下的视觉质量。在合成与真实世界数据集上的实验表明，该方法在轻微退化条件下实现更高保真度与更少伪影，同时保持单步效率。代码与模型将发布于https://github.com/gobunu/LCUDiff。
原文摘要 · Abstract (English)
Existing methods for restoring degraded human-centric images often struggle with insufficient fidelity, particularly in human body restoration (HBR). Recent diffusion-based restoration methods commonly adapt pre-trained text-to-image diffusion models, where the variational autoencoder (VAE) can significantly bottleneck restoration fidelity. We propose LCUDiff, a stable one-step framework that upgrades a pre-trained latent diffusion model from the 4-channel latent space to the 16-channel latent space. For VAE fine-tuning, channel splitting distillation (CSD) is used to keep the first four channels aligned with pre-trained priors while allocating the additional channels to effectively encode high-frequency details. We further design prior-preserving adaptation (PPA) to smoothly bridge the mismatch between 4-channel diffusion backbones and the higher-dimensional 16-channel latent. In addition, we propose a decoder router (DeR) for per-sample decoder routing using restoration-quality score annotations, which improves visual quality across diverse conditions. Experiments on synthetic and real-world datasets show competitive results with higher fidelity and fewer artifacts under mild degradations, while preserving one-step efficiency. The code and model will be at https://github.com/gobunu/LCUDiff.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。