Improved Style Transfer by Respecting Inter-layer Correlations
원문 초록
A popular series of style transfer methods apply a style to a content image by controlling mean and covariance of values in early layers of a feature stack. This is insufficient for transferring styles that have strong structure across spatial scales like, e.g., textures where dots lie on long curves. This paper demonstrates that controlling inter-layer correlations yields visible improvements in style transfer methods. We achieve this control by computing cross-layer, rather than within-layer, gram matrices. We find that (a) cross-layer gram matrices are sufficient to control within-layer statistics. Inter-layer correlations improves style transfer and texture synthesis. The paper shows numerous examples on "hard" real style transfer problems (e.g. long scale and hierarchical patterns); (b) a fast approximate style transfer method can control cross-layer gram matrices; (c) we demonstrate that multiplicative, rather than additive style and content loss, results in very good style transfer. Multiplicative loss produces a visible emphasis on boundaries, and means that one hyper-parameter can be eliminated.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Volumetric Temporal Texture Synthesis for Smoke Stylization using Neural Cellular Automata
Dynamic Neural Style Transfer for Artistic Image Generation using VGG19
Hunyuan3D 2.5: Towards High-Fidelity 3D Assets Generation with Ultimate Details
SA-LUT: Spatial Adaptive 4D Look-Up Table for Photorealistic Style Transfer
TexTailor: Customized Text-aligned Texturing via Effective Resampling
Implicit Inversion turns CLIP into a Decoder
토론
이 논문과 연결된 포럼 글이 아직 없습니다.