GIST: Towards Photorealistic Style Transfer via Multiscale Geometric
Representations
GIST: Towards Photorealistic Style Transfer via Multiscale Geometric
Representations
State-of-the-art Style Transfer methods often leverage pre-trained encoders optimized for discriminative tasks, which may not be ideal for image synthesis. This can result in significant artifacts and loss of photorealism. Motivated by the ability of multiscale geometric image representations to capture fine-grained details and global structure, we propose GIST: Geometric-based …