Lei Liu
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
Lei Liu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Zhenghao Chen
University of Newcastle, Newcastle, Australia
5 shared publications - Dong Xu
The University of Hong Kong, Hong Kong, Hong Kong
4 shared publications Can Wang
School of Computing and Data Science, The University of Hong Kong, Pokfulam, Hong Kong
1 shared publicationDong Xu
1 shared publication- Lebin Zhou
Santa Clara University, Santa Clara, CA, USA
1 shared publication - Wei Jiang
Futurewei Technologies Inc., San José, CA, USA
1 shared publication
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1015-1024
Versatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 1015-1024
Open AccessVersatile Video Representation via Feed-Forward 2D Gaussian Splatting Tokenization
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 71-80
M 3 ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward Compression
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 71-80
Open AccessM 3 ISR: A Multi-Modal Multi-View Benchmark for 3D/4D Gaussian Splatting and Feedforward Compression
- 11 July 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
An efficient adaptive compression method for human perception and machine vision tasks
- 11 July 2026
- Published by Elsevier in Pattern Recognition
- Vol. 180
An efficient adaptive compression method for human perception and machine vision tasks
- 17 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (7) , 10405-10417
4DGS-Craft: Consistent and Interactive 4D Gaussian Splatting Editing
Recent advances in 4D Gaussian Splatting (4DGS) editing still face challenges with view, temporal, and non-editing region consistency, as well as with handling complex text instructions. To address these issues, we propose 4DGS-Craft, a consistent and interactive 4DGS editing framework. We first introduce a 4D-aware InstructPix2Pix model to ensure both view and temporal consistency. This model incorporates 4D VGGT geometry features extracted from the initial scene, enabling it to capture underlying 4D geometric structures during editing. We further enhance this model with a multi-view grid module that enforces consistency by iteratively refining multi-view input images while jointly optimizing the underlying 4D scene. Furthermore, we preserve the consistency of non-edited regions through a novel Gaussian selection mechanism, which identifies and optimizes only the Gaussians within the edited regions. Beyond consistency, facilitating user interaction is also crucial for effective 4DGS editing. Therefore, we design an LLM-based module for user intent understanding. This module employs a user instruction template to define atomic editing operations and leverages an LLM for reasoning. As a result, our framework can interpret user intent and decompose complex instructions into a logical sequence of atomic operations, enabling it to handle intricate user commands and further enhance editing performance. Compared to related works, our approach enables more consistent and controllable 4D scene editing.
- 17 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 36 (7) , 10405-10417
4DGS-Craft: Consistent and Interactive 4D Gaussian Splatting Editing
Recent advances in 4D Gaussian Splatting (4DGS) editing still face challenges with view, temporal, and non-editing region consistency, as well as with handling complex text instructions. To address these issues, we propose 4DGS-Craft, a consistent and interactive 4DGS editing framework. We first introduce a 4D-aware InstructPix2Pix model to ensure both view and temporal consistency. This model incorporates 4D VGGT geometry features extracted from the initial scene, enabling it to capture underlying 4D geometric structures during editing. We further enhance this model with a multi-view grid module that enforces consistency by iteratively refining multi-view input images while jointly optimizing the underlying 4D scene. Furthermore, we preserve the consistency of non-edited regions through a novel Gaussian selection mechanism, which identifies and optimizes only the Gaussians within the edited regions. Beyond consistency, facilitating user interaction is also crucial for effective 4DGS editing. Therefore, we design an LLM-based module for user intent understanding. This module employs a user instruction template to define atomic editing operations and leverages an LLM for reasoning. As a result, our framework can interpret user intent and decompose complex instructions into a logical sequence of atomic operations, enabling it to handle intricate user commands and further enhance editing performance. Compared to related works, our approach enables more consistent and controllable 4D scene editing.
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8341-8350
3D Gaussian Splatting Data Compression with Mixture of Priors
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 8341-8350
Open Access3D Gaussian Splatting Data Compression with Mixture of Priors
- Open Access
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8047-8056
ICMH-Net: Neural Image Compression Towards both Machine Vision and Human Vision
- 26 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 8047-8056
Open AccessICMH-Net: Neural Image Compression Towards both Machine Vision and Human Vision