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

Nov 16, 2026

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

High-resolution facial datasets with consistent UV-mapped geometry, albedo, and physically based displacement are scarce, yet such assets are essential for photorealistic digital-human rendering. Existing 3D face generation methods are often slow, single-modality, or require large specialized datasets. Meanwhile, large image diffusion models encode strong facial priors but do not natively produce lighting-independent textures, pore-scale displacement, or UV-aligned geometry. We present FaceRiff, a unified, data- and parameter-efficient framework for generating complete 3D face assets (mesh, albedo, and displacement) directly from text in a shared UV space. FaceRiff adapts a pretrained SDXL backbone with task-specific LoRA adapters and uses UV normal maps as geometric conditioning: per-instance normals guide albedo and displacement synthesis, while a dataset-mean normal provides a canonical spatial anchor for mesh generation. Using only 2,049 scans from approximately 350 identities and training on a single GPU, FaceRiff updates less than 3% of the backbone parameters per task and produces render-ready 3D face assets without per-instance optimization. Compared with FaceG2E and DreamFace, FaceRiff produces greater per-prompt diversity while preserving prompt alignment and fixed-topology UV consistency, and additionally generates lighting-independent albedo suitable for PBR relighting and pore-scale displacement absent from prior text-driven baselines. A blind study with 45 industry professionals shows that FaceRiff achieves substantially higher perceived realism than DreamFace, approaching that of real captures. Overall, FaceRiff demonstrates that pretrained diffusion priors can be adapted to unified 3D face asset synthesis under limited data.
May 25, 2026

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

Creating images from noise is image generation; reconstructing fine details from coarse inputs is super-resolution. Despite their practical differences, both can be understood as reversing information loss across scales. We introduce SKILD\textbf{SKILD}, a S\textbf{S}cale-invariant K\textbf{K}-Space I\textbf{I}mage L\textbf{L}earning D\textbf{D}iffusion model that unifies generation and continuous super-resolution within a single unconditional framework. Both natural images and critical physical systems exhibit scale invariance, and we leverage it to design a forward process that attenuates image content from fine to coarse scales while injecting spectrum-matched Gaussian noise, making scale an explicit coordinate of the diffusion dynamics. The same trained reverse process performs generation and continuous super-resolution by varying only the starting timestep: no task-specific architecture, no conditioning branch, no classifier-free guidance, no retraining per scale factor\textit{no task-specific architecture, no conditioning branch, no classifier-free guidance, no retraining per scale factor}. Empirically, SKILD reaches FID 2.612.61 and Inception Score 9.659.65 on unconditional CIFAR-10, performs 2×2\times--8×8\times super-resolution on ImageNet from a single unconditional checkpoint while outperforming conditional models across perceptual metrics, and reconstructs critical Ising models whose connected four-point correlations closely track the ground truth.
May 13, 2026

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

Face image super-resolution aims to recover high-resolution facial images from severely degraded inputs. Under extreme upscaling factors, fine facial details are often lost, making accurate reconstruction challenging. Existing methods typically rely on heavy network architectures, adversarial training schemes, or separate alignment networks, increasing model complexity and computational cost. To address these issues, we propose a lightweight U-Net based-architecture designed to reconstructs 128×128128{ \times }128 facial images from severely degraded 16×1616{ \times }16 inputs, achieving an 8×8 \times magnification. A key contribution is a novel auxiliary-training-free supervision strategy that leverages heatmaps generated by YOLO-World, an open-vocabulary object detector, to localize key facial features such as eyes, nose, and mouth. These heatmaps are converted into spatial weights to form a heatmap-guided loss that emphasizes reconstruction errors in semantically important regions. Unlike prior methods that require dedicated landmark or alignment networks, our approach directly reuses detector outputs as supervision, maintaining an efficient training and inference pipeline. Experiments on the aligned CelebA dataset demonstrate that the proposed loss consistently improves quantitative metrics and produces sharper, more realistic reconstructions. Overall, our results show that lightweight networks can effectively exploit detection-driven priors for perceptually convincing extreme upscaling, without adversarial training or increased computational cost.