2024 CVPR CVPR 2024

Geometry Transfer for Stylizing Radiance Fields

Abstract

Shape and geometric patterns are essential in defining stylistic identity. However current 3D style transfer methods predominantly focus on transferring colors and textures often overlooking geometric aspects. In this paper we introduce Geometry Transfer a novel method that leverages geometric deformation for 3D style transfer. This technique employs depth maps to extract a style guide subsequently applied to stylize the geometry of radiance fields. Moreover we propose new techniques that utilize geometric cues from the 3D scene thereby enhancing aesthetic expressiveness and more accurately reflecting intended styles. Our extensive experiments show that Geometry Transfer enables a broader and more expressive range of stylizations thereby significantly expanding the scope of 3D style transfer.

🌉 Interdisciplinary Bridge — Computer Science and Computer Vision and Deep Learning
🧭 Keyword Pioneer — geometry transfer
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Deep Learning, Healthcare & Medicine, Interdisciplinary, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Robotics, Security & Privacy, Speech & Audio