Ref-NPR: Reference-Based Non-Photorealistic Radiance Fields for Controllable Scene Stylization
원문 초록
Current 3D scene stylization methods transfer textures and colors as styles using arbitrary style references, lacking meaningful semantic correspondences. We introduce Reference-Based Non-Photorealistic Radiance Fields (Ref-NPR) to address this limitation. This controllable method stylizes a 3D scene using radiance fields with a single stylized 2D view as a reference. We propose a ray registration process based on the stylized reference view to obtain pseudo-ray supervision in novel views. Then we exploit semantic correspondences in content images to fill occluded regions with perceptually similar styles, resulting in non-photorealistic and continuous novel view sequences. Our experimental results demonstrate that Ref-NPR outperforms existing scene and video stylization methods regarding visual quality and semantic correspondence. The code and data are publicly available on the project page at https://ref-npr.github.io.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Semantic Correspondence: Unified Benchmarking and a Strong Baseline
TC-MGC: Text-Conditioned Multi-Grained Contrastive Learning for Text-Video Retrieval
Evaluation of Multilingual Image Captioning: How far can we get with CLIP models?
Multi-Level Correlation Network For Few-Shot Image Classification
CleanDIFT: Diffusion Features without Noise
Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
토론
이 논문과 연결된 포럼 글이 아직 없습니다.