SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting
Bo Li, Jiahao Kang, Yubo Ma, Feng-Lin Liu, Bin Liu, Fang-Lue Zhang, Lin Gao

TL;DR
SketchFaceGS is a novel real-time framework that generates and edits photorealistic 3D head models from 2D sketches using a Transformer-based architecture and UV feature refinement.
Contribution
It introduces the first sketch-driven method for real-time 3D Gaussian head modeling, combining coarse-to-fine architecture with UV Mask Fusion for precise editing.
Findings
Outperforms existing methods in generation fidelity.
Enables real-time, free-viewpoint editing from sketches.
Produces high-quality, editable 3D heads in a single pass.
Abstract
3D Gaussian representations have emerged as a powerful paradigm for digital head modeling, achieving photorealistic quality with real-time rendering. However, intuitive and interactive creation or editing of 3D Gaussian head models remains challenging. Although 2D sketches provide an ideal interaction modality for fast, intuitive conceptual design, they are sparse, depth-ambiguous, and lack high-frequency appearance cues, making it difficult to infer dense, geometrically consistent 3D Gaussian structures from strokes - especially under real-time constraints. To address these challenges, we propose SketchFaceGS, the first sketch-driven framework for real-time generation and editing of photorealistic 3D Gaussian head models from 2D sketches. Our method uses a feed-forward, coarse-to-fine architecture. A Transformer-based UV feature-prediction module first reconstructs a coarse but…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
