Hybrid Domain Knowledge Fusion distills expertise from specialized models across synthetic, OLAT, and real datasets into a lightweight student model for state-of-the-art portrait relighting with 6x-240x faster inference.
arXiv preprint arXiv:2510.23494 (2025)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Toward Real-World Adoption of Portrait Relighting via Hybrid Domain Knowledge Fusion
Hybrid Domain Knowledge Fusion distills expertise from specialized models across synthetic, OLAT, and real datasets into a lightweight student model for state-of-the-art portrait relighting with 6x-240x faster inference.