SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918459374305280 |
|---|---|
| author | Li, Bo Kang, Jiahao Ma, Yubo Liu, Feng-Lin Liu, Bin Zhang, Fang-Lue Gao, Lin |
| author_facet | Li, Bo Kang, Jiahao Ma, Yubo Liu, Feng-Lin Liu, Bin Zhang, Fang-Lue Gao, Lin |
| contents | 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 geometrically consistent UV feature map from the input sketch, and then a 3D UV feature enhancement module refines it with high-frequency, photorealistic detail to produce a high-fidelity 3D head. For editing, we introduce a UV Mask Fusion technique combined with a layer-by-layer feature-fusion strategy, enabling precise, real-time, free-viewpoint modifications. Extensive experiments show that SketchFaceGS outperforms existing methods in both generation fidelity and editing flexibility, producing high-quality, editable 3D heads from sketches in a single forward pass. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_19202 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting Li, Bo Kang, Jiahao Ma, Yubo Liu, Feng-Lin Liu, Bin Zhang, Fang-Lue Gao, Lin Graphics Computer Vision and Pattern Recognition 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 geometrically consistent UV feature map from the input sketch, and then a 3D UV feature enhancement module refines it with high-frequency, photorealistic detail to produce a high-fidelity 3D head. For editing, we introduce a UV Mask Fusion technique combined with a layer-by-layer feature-fusion strategy, enabling precise, real-time, free-viewpoint modifications. Extensive experiments show that SketchFaceGS outperforms existing methods in both generation fidelity and editing flexibility, producing high-quality, editable 3D heads from sketches in a single forward pass. |
| title | SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting |
| topic | Graphics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.19202 |