ECCV 2026 paper ART fixes complex makeup transfer, releases first 2K dataset
jiqizhixin · x · 2026-09-15
The ECCV 2026 paper "Anchoring on Reality" (ART) tackles complex makeup transfer (glitter, stickers, artistic face paint), where existing methods blur textures, lose patterns, or shift identity. The authors identify the core bottleneck as the "pseudo-target ceiling" — unsupervised methods lack ground truth for the transferred result — and reframe makeup transfer as a supervised task anchored on reality. They also release MF2K, the first 2K-resolution real-scene makeup dataset with artistic makeup subsets. ART ranks first on MSimG and achieves the lowest L2-M error, preserving glitter placement, paint patterns, and rhinestone positions pixel-perfectly while strictly maintaining facial structure and identity.
More from Research
- Jay Alammar at PyData: ten questions that explain benchmark score gaps — JayAlammar · 2026-09-15
- RLE-Bench: 48 Tasks Benchmark LLM Agents on Full Robotics Engineering, Not Just Control — daibond_alpha · 2026-09-15
- BrainGPT creator: AI discoveries will soon be as explainable as quantum mechanics to a dog — every · 2026-09-15
- Ethan Mollick tests GPT on Linear A, warns it's 'researchslop' until GPT-6 cracks it — emollick · 2026-09-15
- Benchmark tests 71 AI personal assistants across 15 dimensions, Muse tops at 9.1 — ai · 2026-09-15
- FlyWire publishes DIY guide to simulate a fly brain with ~160k neurons — patrickmineault · 2026-09-15