Lin Zeng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Lin Zeng has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Boming Zhao
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
1 shared publication - Hujun Bao
State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China
1 shared publication - Rui Ma
School of Artificial Intelligence, Jilin University, Changchun, China
1 shared publication - Yinda Zhang
Google, Mountain View, CA, USA
1 shared publication - Yuan Li
Zhejiang University, Hangzhou, China
1 shared publication - Yujun Shen
Ant Group
1 shared publication
Latest Publications
- Open Access
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis
Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and robotics. Traditional approaches like video prediction and novel-view synthesis either lack the ability to forecast from arbitrary viewpoints or to predict temporal dynamics. In this paper, we introduce GaussianPrediction, a novel framework that empowers 3D Gaussian representations with dynamic scene modeling and future scenario synthesis in dynamic environments. GaussianPrediction can forecast future states from any viewpoint, using video observations of dynamic scenes. To this end, we first propose a 3D Gaussian canonical space with deformation modeling to capture the appearance and geometry of dynamic scenes, and integrate the lifecycle property into Gaussians for irreversible deformations. To make the prediction feasible and efficient, a concentric motion distillation approach is developed by distilling the scene motion with key points. Finally, a Graph Convolutional Network is employed to predict the motions of key points, enabling the rendering of photorealistic images of future scenarios. Our framework shows outstanding performance on both synthetic and real-world datasets, demonstrating its efficacy in predicting and rendering future environments. Code is available on the project webpage: https://zju3dv.github.io/gaussian-prediction.
- 13 July 2024
- Published by Association for Computing Machinery (ACM)
- p. 1-12
Open AccessGaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesis
Forecasting future scenarios in dynamic environments is essential for intelligent decision-making and navigation, a challenge yet to be fully realized in computer vision and robotics. Traditional approaches like video prediction and novel-view synthesis either lack the ability to forecast from arbitrary viewpoints or to predict temporal dynamics. In this paper, we introduce GaussianPrediction, a novel framework that empowers 3D Gaussian representations with dynamic scene modeling and future scenario synthesis in dynamic environments. GaussianPrediction can forecast future states from any viewpoint, using video observations of dynamic scenes. To this end, we first propose a 3D Gaussian canonical space with deformation modeling to capture the appearance and geometry of dynamic scenes, and integrate the lifecycle property into Gaussians for irreversible deformations. To make the prediction feasible and efficient, a concentric motion distillation approach is developed by distilling the scene motion with key points. Finally, a Graph Convolutional Network is employed to predict the motions of key points, enabling the rendering of photorealistic images of future scenarios. Our framework shows outstanding performance on both synthetic and real-world datasets, demonstrating its efficacy in predicting and rendering future environments. Code is available on the project webpage: https://zju3dv.github.io/gaussian-prediction.