add new paper

_pages/about.md

@@ -39,7 +39,13 @@ I'm Yiqian Wu (吴奕谦), a third-year (2021-now) Ph.D. student in State Key La
 
    **Yiqian Wu**, Jing Zhang, Hongbo Fu, Xiaogang Jin.
 
-3. [Deep Real-time Volumetric Rendering Using Multi-feature Fusion](https://onethousandwu.com/publication/mrpnn)
+3. [Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning](https://onethousandwu.com/publication/enhancing_the_authenticity_of_rendered_portraits)
+
+   Preprint
+
+   Luyuan Wang*, **Yiqian Wu\*** (\*Equal Contribution), Yongliang Yang, Chen Liu, Xiaogang Jin
+
+4. [Deep Real-time Volumetric Rendering Using Multi-feature Fusion](https://onethousandwu.com/publication/mrpnn)
 
    ACM SIGGRAPH 2023 Conference Proceedings (SIGGRAPH '23). Association for Computing Machinery, New York, NY, USA, Article 61, 1–10.
 

_pages/cv.md

@@ -50,7 +50,13 @@ Sep. 2017 - Jun. 2021
 
    **Yiqian Wu**, Jing Zhang, Hongbo Fu, Xiaogang Jin.
 
-3. [Deep Real-time Volumetric Rendering Using Multi-feature Fusion](https://onethousandwu.com/publication/mrpnn)
+3. [Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning](https://onethousandwu.com/publication/enhancing_the_authenticity_of_rendered_portraits)
+
+   Preprint
+
+   Luyuan Wang*, **Yiqian Wu\*** (\*Equal Contribution), Yongliang Yang, Chen Liu, Xiaogang Jin
+
+4. [Deep Real-time Volumetric Rendering Using Multi-feature Fusion](https://onethousandwu.com/publication/mrpnn)
 
    ACM SIGGRAPH 2023 Conference Proceedings (SIGGRAPH '23). Association for Computing Machinery, New York, NY, USA, Article 61, 1–10.
 

_publications/enhancing_the_authenticity_of_rendered_portraits.md

@@ -0,0 +1,44 @@
+---
+title: "Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning"
+collection: publications
+permalink: /publication/enhancing_the_authenticity_of_rendered_portraits
+excerpt: 'Luyuan Wang*, **Yiqian Wu\*** (\*Equal Contribution), [Yongliang Yang](https://www.yongliangyang.net/), Chen Liu, [Xiaogang Jin](http://www.cad.zju.edu.cn/home/jin/).'
+date: 2023-10-06
+venue: 'Preprints'
+paperurl: 'https://arxiv.org/abs/2310.04194'
+citation: 'http://oneThousand1000.github.io/files/bibtex/enhancing_the_authenticity_of_rendered_portraits.html'
+code: 'coming soon'
+video: 'coming soon'
+supplementary_materials: 'coming soon'
+project_page: 'coming soon'
+year: '2023'
+---
+![enhancing_the_authenticity_of_rendered_portraits](http://oneThousand1000.github.io/images/publications/enhancing_the_authenticity_of_rendered_portraits.png)
+
+<b>Abstract:</b>
+
+Despite rapid advances in computer graphics, creating high-quality photo-realistic virtual portraits is prohibitively expensive. Furthermore, the well-known ''uncanny valley'' effect in rendered portraits has a significant impact on the user experience, especially when the depiction closely resembles a human likeness, where any minor artifacts can evoke feelings of eeriness and repulsiveness. In this paper, we present a novel photo-realistic portrait generation framework that can effectively mitigate the ''uncanny valley'' effect and improve the overall authenticity of rendered portraits. Our key idea is to employ transfer learning to learn an identity-consistent mapping from the latent space of rendered portraits to that of real portraits. During the inference stage, the input portrait of an avatar can be directly transferred to a realistic portrait by changing its appearance style while maintaining the facial identity. To this end, we collect a new dataset, **D**az-**R**endered-**F**aces-**HQ** (**DRFHQ**), that is specifically designed for rendering-style portraits. We leverage this dataset to fine-tune the StyleGAN2 generator, using our carefully crafted framework, which helps to preserve the geometric and color features relevant to facial identity. We evaluate our framework using portraits with diverse gender, age, and race variations. Qualitative and quantitative evaluations and ablation studies show the advantages of our method compared to state-of-the-art approaches.
+
+
+
+[Paper](https://arxiv.org/abs/2310.04194) 
+
+[Video](coming soon) 
+
+[Suppl](coming soon) 
+
+[Project Page](coming soon)
+
+
+
+Recommended citation: 
+```
+@misc{wang2023enhancing,
+      title={Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning}, 
+      author={Luyuan Wang and Yiqian Wu and Yongliang Yang and Chen Liu and Xiaogang Jin},
+      year={2023},
+      eprint={2310.04194},
+      archivePrefix={arXiv},
+      primaryClass={cs.CV}
+}
+```

_publications/lpff-dataset.md

@@ -35,12 +35,12 @@ In this paper, we present **LPFF**, a large-pose Flickr face dataset comprised o
 
 Recommended citation: 
 ```
-@misc{wu2023lpff,
-      title={LPFF: A Portrait Dataset for Face Generators Across Large Poses}, 
-      author={Yiqian Wu and Jing Zhang and Hongbo Fu and Xiaogang Jin},
-      year={2023},
-      eprint={2303.14407},
-      archivePrefix={arXiv},
-      primaryClass={cs.CV}
+@InProceedings{Wu_2023_ICCV,
+    author    = {Wu, Yiqian and Zhang, Jing and Fu, Hongbo and Jin, Xiaogang},
+    title     = {LPFF: A Portrait Dataset for Face Generators Across Large Poses},
+    booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
+    month     = {October},
+    year      = {2023},
+    pages     = {20327-20337}
 }
 ```

files/bibtex/enhancing_the_authenticity_of_rendered_portraits.html

@@ -0,0 +1,10 @@
+
+<p>@misc{wang2023enhancing,<br>
+      title={Enhancing the Authenticity of Rendered Portraits with Identity-Consistent Transfer Learning}, <br>
+      author={Luyuan Wang and Yiqian Wu and Yongliang Yang and Chen Liu and Xiaogang Jin},<br>
+      year={2023},<br>
+      eprint={2310.04194},<br>
+      archivePrefix={arXiv},<br>
+      primaryClass={cs.CV}<br>
+}<p>
+