Moran Li
Research Subjects
Research Interests
Moran Li has a total of 27 co-authors. Here are the top co-authors by number of shared publications:
- Nong Sang
Huazhong University of Science and Technology
4 shared publications - Chengjie Wang
YouTu Lab, Tencent, Shanghai, China
3 shared publications - Jiangning Zhang
Zhejiang University
3 shared publications - Weijian Cao
Tencent Youtu Lab, Shanghai, China
3 shared publications - Chongyang Ma
Kuaishou Technology, Beijing, China
2 shared publications - Haibin Huang
Institute of Artificial Intelligence (TeleAI), China Telecom, Shanghai, China
2 shared publications
Latest Publications
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10296-10304
StrandDesigner: Towards Practical Strand Generation with Sketch Guidance
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10296-10304
Open AccessStrandDesigner: Towards Practical Strand Generation with Sketch Guidance
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13743-13750
Identity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 13743-13750
Open AccessIdentity-Preserving Text-to-Video Generation Guided by Simple yet Effective Spatial-Temporal Decoupled Representations
- 29 October 2024
- Published by Springer Nature
- p. 93-109
FreeMotion: A Unified Framework for Number-Free Text-to-Motion Synthesis
- 29 October 2024
- Published by Springer Nature
- p. 93-109
FreeMotion: A Unified Framework for Number-Free Text-to-Motion Synthesis
- Open Access
- 16 May 2023
- Published by Elsevier in Graphical Models
- Vol. 127
Camera distance helps 3D hand pose estimated from a single RGB image
- 16 May 2023
- Published by Elsevier in Graphical Models
- Vol. 127
Open AccessCamera distance helps 3D hand pose estimated from a single RGB image
- Open Access
Implicit Neural Deformation for Sparse-View Face Reconstruction
In this work, we present a new method for 3D face reconstruction from sparse-view RGB images. Unlike previous methods which are built upon 3D morphable models (3DMMs) with limited details, we leverage an implicit representation to encode rich geometric features. Our overall pipeline consists of two major components, including a geometry network, which learns a deformable neural signed distance function (SDF) as the 3D face representation, and a rendering network, which learns to render on-surface points of the neural SDF to match the input images via self-supervised optimization. To handle in-the-wild sparse-view input of the same target with different expressions at test time, we propose residual latent code to effectively expand the shape space of the learned implicit face representation as well as a novel view-switch loss to enforce consistency among different views. Our experimental results on several benchmark datasets demonstrate that our approach outperforms alternative baselines and achieves superior face reconstruction results compared to state-of-the-art methods.
Open AccessImplicit Neural Deformation for Sparse-View Face Reconstruction
In this work, we present a new method for 3D face reconstruction from sparse-view RGB images. Unlike previous methods which are built upon 3D morphable models (3DMMs) with limited details, we leverage an implicit representation to encode rich geometric features. Our overall pipeline consists of two major components, including a geometry network, which learns a deformable neural signed distance function (SDF) as the 3D face representation, and a rendering network, which learns to render on-surface points of the neural SDF to match the input images via self-supervised optimization. To handle in-the-wild sparse-view input of the same target with different expressions at test time, we propose residual latent code to effectively expand the shape space of the learned implicit face representation as well as a novel view-switch loss to enforce consistency among different views. Our experimental results on several benchmark datasets demonstrate that our approach outperforms alternative baselines and achieves superior face reconstruction results compared to state-of-the-art methods.
- 1 October 2022
- Published by Wiley in Computer Graphics Forum
- Vol. 41 (7) , 601-610
Implicit Neural Deformation for Sparse‐View Face Reconstruction
In this work, we present a new method for 3D face reconstruction from sparse‐view RGB images. Unlike previous methods which are built upon 3D morphable models (3DMMs) with limited details, we leverage an implicit representation to encode rich geometric features. Our overall pipeline consists of two major components, including a geometry network, which learns a deformable neural signed distance function (SDF) as the 3D face representation, and a rendering network, which learns to render on‐surface points of the neural SDF to match the input images via self‐supervised optimization. To handle in‐the‐wild sparse‐view input of the same target with different expressions at test time, we propose residual latent code to effectively expand the shape space of the learned implicit face representation as well as a novel view‐switch loss to enforce consistency among different views. Our experimental results on several benchmark datasets demonstrate that our approach outperforms alternative baselines and achieves superior face reconstruction results compared to state‐of‐the‐art methods.
- 1 October 2022
- Published by Wiley in Computer Graphics Forum
- Vol. 41 (7) , 601-610
Implicit Neural Deformation for Sparse‐View Face Reconstruction
In this work, we present a new method for 3D face reconstruction from sparse‐view RGB images. Unlike previous methods which are built upon 3D morphable models (3DMMs) with limited details, we leverage an implicit representation to encode rich geometric features. Our overall pipeline consists of two major components, including a geometry network, which learns a deformable neural signed distance function (SDF) as the 3D face representation, and a rendering network, which learns to render on‐surface points of the neural SDF to match the input images via self‐supervised optimization. To handle in‐the‐wild sparse‐view input of the same target with different expressions at test time, we propose residual latent code to effectively expand the shape space of the learned implicit face representation as well as a novel view‐switch loss to enforce consistency among different views. Our experimental results on several benchmark datasets demonstrate that our approach outperforms alternative baselines and achieves superior face reconstruction results compared to state‐of‐the‐art methods.
- 1 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 31 (12) , 4883-4894
Latent Distribution-Based 3D Hand Pose Estimation From Monocular RGB Images
In this article, we propose a novel compressed latent distribution representation for 3D hand pose estimation from monocular RGB images to alleviate the channel correspondence problem. The channel correspondence problem occurs when the 2D and depth coordinates are estimated from independent feature maps, which means the 2D and depth channel sequences may not match during the cross-dataset inference. In contrast, we propose a compressed latent distribution representation that the 2D and depth feature maps for each joint are interconnected and inter-constrained more directly, effectively alleviating the channel correspondence problem and improving cross-dataset performance. Moreover, we design an efficient encoder-decoder network that can maintain the resolution of feature maps to enable better hand feature extraction from monocular RGB images. In this work, the overall pipeline contains two branches: one is the 2D hand pose estimation branch based on a latent heatmap representation (LHR); the other is the 3D hand pose estimation branch based on our proposed latent distribution representation (LDR). In this way, the 2D estimation branch serves as guidance for the 3D branch, which simplifies the optimization of the overall network and results in a more rapid convergence during training. The results on several benchmark datasets (including STB, RHD, and the most recently released InterHand2.6M) demonstrate that our proposed method achieves state-of-the-art (SOTA) performance.
- 1 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 31 (12) , 4883-4894
Latent Distribution-Based 3D Hand Pose Estimation From Monocular RGB Images
In this article, we propose a novel compressed latent distribution representation for 3D hand pose estimation from monocular RGB images to alleviate the channel correspondence problem. The channel correspondence problem occurs when the 2D and depth coordinates are estimated from independent feature maps, which means the 2D and depth channel sequences may not match during the cross-dataset inference. In contrast, we propose a compressed latent distribution representation that the 2D and depth feature maps for each joint are interconnected and inter-constrained more directly, effectively alleviating the channel correspondence problem and improving cross-dataset performance. Moreover, we design an efficient encoder-decoder network that can maintain the resolution of feature maps to enable better hand feature extraction from monocular RGB images. In this work, the overall pipeline contains two branches: one is the 2D hand pose estimation branch based on a latent heatmap representation (LHR); the other is the 3D hand pose estimation branch based on our proposed latent distribution representation (LDR). In this way, the 2D estimation branch serves as guidance for the 3D branch, which simplifies the optimization of the overall network and results in a more rapid convergence during training. The results on several benchmark datasets (including STB, RHD, and the most recently released InterHand2.6M) demonstrate that our proposed method achieves state-of-the-art (SOTA) performance.