Chen Yiwen

I am Yiwen, a third year Ph.D. student at Nanyang Technological University focusing on 3D AIGC, with S-Lab. I am fortunate to be supervised by Prof. Guosheng lin. I got my Bachelor’s degree in Computer Science at Beihang University in 2022, where I spent a wonderful time working with Prof. Si Liu.

Email / Google Scholar / Github / Twitter

Research

My research interests lie on 3D Generation, Gaussian Splatting, Diffusion Models. I am eager to investigate the infinite potential of AIGC.

	MeshAnything V2: Artist-Created Mesh Generation With Adjacent Mesh Tokenization Yiwen Chen, Yikai Wang, Yihao Luo, Zhengyi Wang, Zilong Chen, Jun Zhu, Chi Zhang, Guosheng Lin arxiv, 2024 project page / code / arXiv Introduce Adjacent Mesh Tokenization for efficient and high quality mesh generation.
	MeshAnything: Artist-Created Mesh Generation with Autoregressive Transformers Yiwen Chen, Tong He, Di Huang, Weicai Ye, Sijin Chen, Jiaxiang Tang, Xin Chen, Zhongang Cai, Lei Yang, Gang Yu, Guosheng Lin, Chi Zhang arxiv, 2024 project page / code / arXiv Convert anything into meshes like human artists.
	Learn to Optimize Denoising Scores for 3D Generation: A Unified and Improved Diffusion Prior on NeRF and 3D Gaussian Splatting. Xiaofeng Yang, Yiwen Chen, Cheng Chen, Chi Zhang, Yi Xu, Xulei Yang, Fayao Liu, Guosheng Lin arxiv, 2023 project page / code / arXiv A unified framework aimed at enhancing the diffusion priors for 3D generation tasks.
	GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting. Yiwen Chen, Zilong Chen, Chi Zhang, Feng Wang, Xiaofeng Yang, Yikai Wang, Zhongang Cai, Lei Yang, Huaping Liu, Guosheng Lin CVPR, 2024 project page / code / arXiv GaussianEditor provides controllable, diverse, and interactive high-resolution 3D editing, needing only 2-7 minutes and 10-20GB of GPU memory on a single A6000 GPU.
	IT3D: Improved Text-to-3D Generation with Explicit View Synthesis. Yiwen Chen, Chi Zhang, Xiaofeng Yang, Zhongang Cai, Gang Yu, Lei Yang, Guosheng Lin AAAI, 2024 project page / arXiv IT3D attempts to solve oversaturation and unrealistic problems of text-to-3D methods through explicit view synthesis.
	StyleAvatar3D: Leveraging Image-Text Diffusion Models for High-Fidelity 3D Avatar Generation Chi Zhang, Yiwen Chen, Yijun Fu, Zhenglin Zhou, Gang Yu, Billzb Wang, BIN FU, Tao Chen, Guosheng Lin, Chunhua Shen arxiv, 2023 project page / arXiv StyleAvatar3D generates multi-view images of avatars in various styles without the need of real world datasets.
	MoDA: Modeling Deformable 3D Objects from Casual Videos Chaoyue Song, Tianyi Chen, Yiwen Chen, Jiacheng Wei, Chuan-Sheng Foo, Fayao Liu, Guosheng Lin Arxiv, 2023 project page / code / arXiv MoDA models the shape, texture and motion of deformable 3D objects from monocular casual videos.
	StyleRF: Zero-shot 3D Style Transfer of Neural Radiance Fields Kunhao Liu, Fangneng Zhan, Yiwen Chen, Jiahui Zhang, Yingchen Yu, Abdulmotaleb El Saddik, Shijian Lu, Eric Xing, CVPR, 2023 project page / code / arXiv StyleRF is a new 3D style transfer technique that resolves the dilemma of accurate geometry reconstruction, high-quality stylization, and being generalizable to arbitrary new styles.

Web page design credit to Jon Barron