Zilong Dong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Zilong Dong has a total of 101 co-authors. Here are the top co-authors by number of shared publications:
- Weihao Yuan
Nanjing University, Nanjing, China
7 shared publications - Yisheng He
Alibaba Group, Hangzhou, China
6 shared publications - Siyu Zhu
Shanghai Innovation Institute, Shanghai, China and Fudan University, Shanghai, China
5 shared publications Liefeng Bo
Institute of Intelligent Computing, Alibaba Group
3 shared publicationsQi Zuo
Alibaba Group
3 shared publications- Xiaodong Gu
Alibaba Group, Hangzhou, China
3 shared publications
Latest Publications
- Open Access
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2825-2834
WebSplatter: Efficient and Faithful In-Browser 3D Gaussian Splatting across Devices via WebGPU
- 9 November 2026
- Published by Association for Computing Machinery (ACM)
- p. 2825-2834
Open AccessWebSplatter: Efficient and Faithful In-Browser 3D Gaussian Splatting across Devices via WebGPU
- 2 October 2026
- Published by Springer Nature
- p. 297-315
: Feed- Human Reconstruction and Interpolation from Uncalibrated Sparse-View Videos
- 2 October 2026
- Published by Springer Nature
- p. 297-315
: Feed- Human Reconstruction and Interpolation from Uncalibrated Sparse-View Videos
- Open Access
WebSplatter: Enabling Cross-Device Efficient Gaussian Splatting in Web Browsers via WebGPU
We present WebSplatter, an end-to-end GPU rendering pipeline for the heterogeneous web ecosystem. Unlike naive ports, WebSplatter introduces a wait-free hierarchical radix sort that circumvents the lack of global atomics in WebGPU, ensuring deterministic execution across diverse hardware. Furthermore, we propose an opacity-aware geometry culling stage that dynamically prunes splats before rasterization, significantly reducing overdraw and peak memory footprint. Evaluation demonstrates that WebSplatter consistently achieves 1.2$\times$ to 4.5$\times$ speedups over state-of-the-art web viewers.
Open AccessWebSplatter: Enabling Cross-Device Efficient Gaussian Splatting in Web Browsers via WebGPU
We present WebSplatter, an end-to-end GPU rendering pipeline for the heterogeneous web ecosystem. Unlike naive ports, WebSplatter introduces a wait-free hierarchical radix sort that circumvents the lack of global atomics in WebGPU, ensuring deterministic execution across diverse hardware. Furthermore, we propose an opacity-aware geometry culling stage that dynamically prunes splats before rasterization, significantly reducing overdraw and peak memory footprint. Evaluation demonstrates that WebSplatter consistently achieves 1.2$\times$ to 4.5$\times$ speedups over state-of-the-art web viewers.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 8719-8733
MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 35, 8719-8733
MulSMo: Multimodal Stylized Motion Generation by Bidirectional Control Flow
- Open Access
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
High-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation
- 14 December 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-10
Open AccessHigh-Fidelity Dynamic Portrait Animation via Direct Preference Optimization and Temporal Motion Modulation
- Open Access
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10142-10151
CoProSketch: Controllable and Progressive Sketch Generation with Diffusion Model
- 27 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 10142-10151
Open AccessCoProSketch: Controllable and Progressive Sketch Generation with Diffusion Model
- 31 August 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Linguistic query-guided mask generation for referring image segmentation
- 31 August 2025
- Published by Elsevier in Pattern Recognition
- Vol. 172
Linguistic query-guided mask generation for referring image segmentation
- Open Access
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
LAM: Large Avatar Model for One-shot Animatable Gaussian Head
- 27 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 1-13
Open AccessLAM: Large Avatar Model for One-shot Animatable Gaussian Head
- Top Cited Papers
- 27 November 2024
- Published by Springer Nature
- p. 145-162
Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance
- 27 November 2024
- Published by Springer Nature
- p. 145-162
Top Cited PapersChamp: Controllable and Consistent Human Image Animation with 3D Parametric Guidance