Applications
Toward Real-World Adoption of Portrait Relighting via Hybrid Domain Knowledge Fusion
arXiv:2604.23094v1 Announce Type: new Abstract: The real-world adoption of portrait relighting is hindered by dataset domain gaps, camera sensitivity, and computational costs. We address these challen
arXiv:2604.23094v1 Announce Type: new Abstract: The real-world adoption of portrait relighting is hindered by dataset domain gaps, camera sensitivity, and computational costs. We address these challenges with Hybrid Domain Knowledge Fusion, a paradigm that fuses the specialized strengths of synthetic, One-Light-at-A-Time (OLAT), and real-world datasets into a compact model. Our approach features specialized prior models hardened by domain-aware adaptation, followed by augmented knowledge distillation into a lightweight student model with multi-domain expertise. Our method demonstrates a 6x to 240x inference speedup while maintaining state-of-the-art (SOTA) visual quality in the experiments. Additionally, we construct a massive, high-fidelity synthetic dataset with diverse ground-truth intrinsics to support our training pipeline.
Related
- Do Protective Perturbations Really Protect Portrait Privacy under Real-world Image Transformations?
- Bridging Restoration and Generation Manifolds in One-Step Diffusion for Real-World Super-Resolution
- The Second Challenge on Real-World Face Restoration at NTIRE 2026: Methods and Results
- Robust Deepfake Detection, NTIRE 2026 Challenge: Report
Source: arXiv cs.CV | 2026-04-28