Lingzhi Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Lingzhi Li has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Li Shen
Alibaba Group
2 shared publications - Chao Xin
State Key Laboratory of Genetics and Development of Complex Phenotypes, School of Life Sciences and Human Phenome Institute, Fudan University, Shanghai 200433, China
1 shared publication - Dianchen Wang
Department of Hernia and Abdominal Wall Surgery, The First Affiliated Hospital of Zhengzhou University, Zhengzhou, China
1 shared publication - Guangyuan Wang
Tongyi Lab, Alibaba, Hangzhou, China
1 shared publication - Jing Zhang
Department of Gastroenterology, Peking University Third Hospital, Beijing 100191, China
1 shared publication - Ping Tan
Hong Kong University of Science and Technology, Hong Kong, Hong Kong
1 shared publication
Latest Publications
- Open Access
- 23 December 2023
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 169, 107846
Transformer guided self-adaptive network for multi-scale skin lesion image segmentation
- 23 December 2023
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 169, 107846
Open AccessTransformer guided self-adaptive network for multi-scale skin lesion image segmentation
- Open Access
- 21 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (5) , 1-15
High-Resolution Volumetric Reconstruction for Clothed Humans
We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1–6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and demonstrate that better performance can be achieved with proper system design. The volumetric representation offers significant advantages in leveraging 3D spatial context through 3D convolutions, and the notorious quantization error is largely negligible with a reasonably large yet affordable volume resolution, e.g., 512. To handle memory and computation costs, we propose a sophisticated coarse-to-fine strategy with voxel culling and subspace sparse convolution. Our method starts with a discretized visual hull to compute a coarse shape and then focuses on a narrow band nearby the coarse shape for refinement. Once the shape is reconstructed, we adopt an image-based rendering approach, which computes the colors of surface points by blending input images with learned weights. Extensive experimental results show that our method significantly reduces the mean point-to-surface (P2S) precision of state-of-the-art methods by more than 50% to achieve approximately 2mm accuracy with a 512 volume resolution. Additionally, images rendered from our textured model achieve a higher peak signal-to-noise ratio (PSNR) compared to state-of-the-art methods.
- 21 August 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Graphics
- Vol. 42 (5) , 1-15
Open AccessHigh-Resolution Volumetric Reconstruction for Clothed Humans
We present a novel method for reconstructing clothed humans from a sparse set of, e.g., 1–6 RGB images. Despite impressive results from recent works employing deep implicit representation, we revisit the volumetric approach and demonstrate that better performance can be achieved with proper system design. The volumetric representation offers significant advantages in leveraging 3D spatial context through 3D convolutions, and the notorious quantization error is largely negligible with a reasonably large yet affordable volume resolution, e.g., 512. To handle memory and computation costs, we propose a sophisticated coarse-to-fine strategy with voxel culling and subspace sparse convolution. Our method starts with a discretized visual hull to compute a coarse shape and then focuses on a narrow band nearby the coarse shape for refinement. Once the shape is reconstructed, we adopt an image-based rendering approach, which computes the colors of surface points by blending input images with learned weights. Extensive experimental results show that our method significantly reduces the mean point-to-surface (P2S) precision of state-of-the-art methods by more than 50% to achieve approximately 2mm accuracy with a 512 volume resolution. Additionally, images rendered from our textured model achieve a higher peak signal-to-noise ratio (PSNR) compared to state-of-the-art methods.
- Open Access
- 22 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Your3dEmoji: Creating Personalized Emojis via One-shot 3D-aware Cartoon Avatar Synthesis
Creating cartoon-style avatars has drawn growing attention recently, however previous methods only learn face cartoonization in the 2D image level. In this paper, we propose a novel 3D generative model to translate a real-world face image into its corresponding 3D avatar with only a single style example provided. To bridge the gap between 2D real faces and 3D cartoon avatars, we leverage the state-of-the-art StyleGAN and its style-mixing property to produce a 2D paired cartoonized face dataset. We then finetune a pretrained 3D GAN with the pair data in a dual-learning mechanism to get the final synthesized 3D avatar. Furthermore, we analyze the latent space of our model, enabling manual control in what degree a style is applied. Our model is 3D-aware in the sense and also able to do attribute editing, such as smile, age, etc directly in the 3D domain. Experimental results demonstrate that our method can produce high-fidelity cartoonized avatars with true-to-life 3D geometry.
- 22 November 2022
- Published by Association for Computing Machinery (ACM)
- p. 1-4
Open AccessYour3dEmoji: Creating Personalized Emojis via One-shot 3D-aware Cartoon Avatar Synthesis
Creating cartoon-style avatars has drawn growing attention recently, however previous methods only learn face cartoonization in the 2D image level. In this paper, we propose a novel 3D generative model to translate a real-world face image into its corresponding 3D avatar with only a single style example provided. To bridge the gap between 2D real faces and 3D cartoon avatars, we leverage the state-of-the-art StyleGAN and its style-mixing property to produce a 2D paired cartoonized face dataset. We then finetune a pretrained 3D GAN with the pair data in a dual-learning mechanism to get the final synthesized 3D avatar. Furthermore, we analyze the latent space of our model, enabling manual control in what degree a style is applied. Our model is 3D-aware in the sense and also able to do attribute editing, such as smile, age, etc directly in the 3D domain. Experimental results demonstrate that our method can produce high-fidelity cartoonized avatars with true-to-life 3D geometry.