3D style transfer aims to render stylized novel views of 3D scenes with the
specified style, which requires high-quality rendering and keeping multi-view
consistency. Benefiting from the ability of 3D representation from Neural
Radiance Field (NeRF), existing methods learn the stylized NeRF by giving a
reference style from an image. However, they suffer the challenges of
high-quality stylization with texture details for multi-style transfer and
stylization with multimodal guidance. In this paper, we reveal that the same
objects in 3D scenes show various states (color tone, details, etc.) from
different views after stylization since previous methods optimized by
single-view image-based style loss functions, leading NeRF to tend to smooth
texture details, further resulting in low-quality rendering. To tackle these
problems, we propose a novel Multimodal-guided 3D Multi-style transfer of NeRF,
termed MM-NeRF, which achieves high-quality 3D multi-style rendering with
texture details and can be driven by multimodal-style guidance. First, MM-NeRF
adopts a unified framework to project multimodal guidance into CLIP space and
extracts multimodal style features to guide the multi-style stylization. To
relieve the problem of lacking details, we propose a novel Multi-Head Learning
Scheme (MLS), in which each style head predicts the parameters of the color
head of NeRF. MLS decomposes the learning difficulty caused by the
inconsistency of multi-style transfer and improves the quality of stylization.
In addition, the MLS can generalize pre-trained MM-NeRF to any new styles by
adding heads with small training costs (a few minutes). Extensive experiments
on three real-world 3D scene datasets show that MM-NeRF achieves high-quality
3D multi-style stylization with multimodal guidance, keeps multi-view
consistency, and keeps semantic consistency of multimodal style guidance. Codes
will be released later.

本文提出了一种名为 MM-NeRF 的新颖多模态引导的 3D 多风格迁移方法，通过投影多模态引导到 CLIP 空间并提取多模态风格特征来指导多风格的风格化，同时使用多头学习方案（MLS）解决了多风格迁移的不一致性和提升了风格化的质量。

MM-NeRF：多模态引导的三维多风格神经辐射场转换

MM-NeRF: Multimodal-Guided 3D Multi-Style Transfer of Neural Radiance  Field

Unsupervised text style transfer task aims to rewrite a text into target
style while preserving its main content. Traditional methods rely on the use of
a fixed-sized vector to regulate text style, which is difficult to accurately
convey the style strength for each individual token. In fact, each token of a
text contains different style intensity and makes different contribution to the
overall style. Our proposed method addresses this issue by assigning individual
style vector to each token in a text, allowing for fine-grained control and
manipulation of the style strength. Additionally, an adversarial training
framework integrated with teacher-student learning is introduced to enhance
training stability and reduce the complexity of high-dimensional optimization.
The results of our experiments demonstrate the efficacy of our method in terms
of clearly improved style transfer accuracy and content preservation in both
two-style transfer and multi-style transfer settings.

该研究提出了一种通过为每个单词分配个体风格向量来进行细粒度控制和操作的无监督文本风格转移方法，并引入了一种教师 - 学生学习集成的对抗训练框架以提高训练稳定性和降低高维优化的复杂性，实验结果表明其在两种和多种风格转移中具有明显改进的风格转移准确性和内容保留。

MSSRNet: 基于顺序风格表示的无监督文本风格转换

MSSRNet: Manipulating Sequential Style Representation for Unsupervised  Text Style Transfer

Recent neural style transfer frameworks have obtained astonishing visual
quality and flexibility in Single-style Transfer (SST), but little attention
has been paid to Multi-style Transfer (MST) which refers to simultaneously
transferring multiple styles to the same image. Compared to SST, MST has the
potential to create more diverse and visually pleasing stylization results. In
this paper, we propose the first MST framework to automatically incorporate
multiple styles into one result based on regional semantics. We first improve
the existing SST backbone network by introducing a novel multi-level feature
fusion module and a patch attention module to achieve better semantic
correspondences and preserve richer style details. For MST, we designed a
conceptually simple yet effective region-based style fusion module to insert
into the backbone. It assigns corresponding styles to content regions based on
semantic matching, and then seamlessly combines multiple styles together.
Comprehensive evaluations demonstrate that our framework outperforms existing
works of SST and MST.

本文提出了一种基于区域语义的多样式迁移框架，其中引入了新的多级特征融合模块和补丁注意力模块来实现更好的语义对应和保留更丰富的样式细节，并使用区域风格融合模块将多个样式无缝地结合在一起，实现更丰富、更美观的多样式迁移结果。