no code implementations • 3 Jan 2024 • Jinyang Yuan, Tonglin Chen, Zhimeng Shen, Bin Li, xiangyang xue
This ability is essential for humans to identify the same object while moving and to learn from vision efficiently.
no code implementations • 15 Feb 2022 • Jinyang Yuan, Tonglin Chen, Bin Li, xiangyang xue
In this survey, we first outline the current progress on reconstruction-based compositional scene representation learning with deep neural networks, including development history and categorizations of existing methods from the perspectives of the modeling of visual scenes and the inference of scene representations; then provide benchmarks, including an open source toolbox to reproduce the benchmark experiments, of representative methods that consider the most extensively studied problem setting and form the foundation for other methods; and finally discuss the limitations of existing methods and future directions of this research topic.
no code implementations • 7 Dec 2021 • Jinyang Yuan, Bin Li, xiangyang xue
When observing a visual scene that contains multiple objects from multiple viewpoints, humans are able to perceive the scene in a compositional way from each viewpoint, while achieving the so-called "object constancy" across different viewpoints, even though the exact viewpoints are untold.
1 code implementation • 19 Mar 2021 • Jinyang Yuan, Bin Li, xiangyang xue
The proposed ADI framework focuses on the acquisition and utilization of knowledge, and is complementary to existing deep generative models proposed for compositional scene representation.
1 code implementation • 7 Feb 2019 • Jinyang Yuan, Bin Li, xiangyang xue
Different from existing methods, the proposed method disentangles the attributes of an object into ``shape'' and ``appearance'' which are modeled separately by the mixture weights and the mixture components.