cs.CVNov 16, 2026

Domain-Tuned Diffusion Super-Resolution for 4K Facial Asset Maps

Authors: Elly Akhoundi, Mathieu Lamarre, Thibault Goyallon, Patrick Anderson, Étienne Danvoye

Organizations: Electronic Arts Vancouver, Canada · Electronic Arts Montréal, Canada · Electronic Arts Toronto, Canada

Abstract

Physically based facial assets require 4K albedo and displacement maps for cinematic close-ups, yet generative pipelines commonly produce them at only 1K. Naively applying photographic super-resolution is a poor fit: facial UV maps have domain-specific statistics, and displacement is a scalar height field whose errors directly distort geometry. We present a domain-tuned diffusion upscaler for 4x (1024 to 4096) facial asset super-resolution. Starting from a bilinearly upsampled map, we adapt a frozen SDXL backbone per modality with lightweight LoRA modules, while a Tile ControlNet preserves input structure as the diffusion prior restores pore- and wrinkle-scale detail. On held-out maps, our method produces sharper, more faithful detail than bilinear and off-the-shelf GAN and diffusion super-resolvers, reducing albedo LPIPS from 0.21 to 0.08 while avoiding misplaced or excessive displacement relief. These results show that lightweight domain adaptation can produce render-ready 4K facial asset maps without a custom super-resolution architecture.

Figures & tables

Explore similar work

CardsList
  1. FaceRiff: Data-Efficient Unified Text-to-3D Face Asset Synthesis via Geometric Conditioning

    Nov 16, 2026Elly Akhoundi, Mathieu Lamarre, Thibault Goyallon +23D Asset GenerationText-to-3D Generation

  2. Everything at Every Scale: Scale-Invariant Diffusion with Continuous Super-Resolution

    May 25, 2026Zixin Jessie Chen, Zhuo Chen, Archer Wang +4Diffusion-Based Image GenerationImage Super-Resolution

  3. You Only Landmark Once: Lightweight U-Net Face Super Resolution with YOLO-World Landmark Heatmaps

    May 13, 2026Riccardo Carraro, Anna Briotto, Endi Hysa +2Image Super-Resolution