PolyU's OmniColor unifies multi-signal lineart colorization in an ECCV 2026 paper
jiqizhixin · x · 2026-09-05
Hong Kong Polytechnic University and Sichuan University present OmniColor, an ECCV 2026 framework for unified multi-modal lineart colorization. Animators juggle conflicting signals — text descriptions, sparse color scribbles, character reference sheets, recent frames — and existing methods handle at most one or two. OmniColor splits inputs into spatially-aligned conditions (lineart, color hints, frames) needing pixel-level precision and semantic reference conditions (text, character images), each with its own encoding strategy, training objective and redundancy elimination, combined via an adaptive gating module to support any combination of control signals.
More from Multimodal
- Asked GPT-6 to Make 'Art' — It Drew Every Detail With Python Code — Worldly_Beginning647 · 2026-09-05
- AI video walks through Sapiens' human history timeline — waterarttrkgl · 2026-09-05
- User locally generates suspense short film with MiniMax H3 ref-to-video in ComfyUI — Fleabum · 2026-09-05
- invideo demos chat-based editing agent that remixes video in 30 minutes — azed_ai · 2026-09-05
- FrankenTTS: pure-Rust Qwen3-TTS port runs voice cloning entirely in your browser — BLUECOW009 · 2026-09-05
- GPT-6 Astra generates Star Destroyers with full interiors, working elevators and hangars — ChrisGPT · 2026-09-05