Yiyuan Liang

Masaaki Yamauchi, Yiyuan Liang, Hiroko Hara et al.

Smart home automation that adapts to a user's emotional state can enhance psychological safety in daily living environments. This study proposes an emotion-aware automation framework guided by the emotional Biologically Inspired Cognitive Architecture (eBICA), which integrates appraisal, somatic responses, and behavior selection. We conducted a proof-of-concept experiment in a pseudo-smart-home environment, where participants were exposed to an anxiety-inducing event followed by a comfort-inducing automation. State anxiety (STAI-S) was measured throughout the task sequence. The results showed a significant reduction in STAI-S immediately after introducing the avoidance automation, demonstrating that emotion-based control can effectively promote psychological safety. Furthermore, an analysis of individual characteristics suggested that personality and anxiety-related traits modulate the degree of relief, indicating the potential for personalized emotion-adaptive automation. Overall, this study provides empirical evidence that eBICA-based emotional control can function effectively in smart home environments and offers a foundation for next-generation affective home automation systems.

Yiyuan Liang, Zhiying Yan, Liqun Chen et al.

Vision-centric autonomous driving systems require diverse data for robust training and evaluation, which can be augmented by manipulating object positions and appearances within existing scene captures. While recent advancements in diffusion models have shown promise in video editing, their application to object manipulation in driving scenarios remains challenging due to imprecise positional control and difficulties in preserving high-fidelity object appearances. To address these challenges in position and appearance control, we introduce DriveEditor, a diffusion-based framework for object editing in driving videos. DriveEditor offers a unified framework for comprehensive object editing operations, including repositioning, replacement, deletion, and insertion. These diverse manipulations are all achieved through a shared set of varying inputs, processed by identical position control and appearance maintenance modules. The position control module projects the given 3D bounding box while preserving depth information and hierarchically injects it into the diffusion process, enabling precise control over object position and orientation. The appearance maintenance module preserves consistent attributes with a single reference image by employing a three-tiered approach: low-level detail preservation, high-level semantic maintenance, and the integration of 3D priors from a novel view synthesis model. Extensive qualitative and quantitative evaluations on the nuScenes dataset demonstrate DriveEditor's exceptional fidelity and controllability in generating diverse driving scene edits, as well as its remarkable ability to facilitate downstream tasks. Project page: https://yvanliang.github.io/DriveEditor.

Zhiying Yan, Yiyuan Liang, Shilv Cai et al.

Semantic 4D Gaussians can be used for reconstructing and understanding dynamic scenes, with temporal variations than static scenes. Directly applying static methods to understand dynamic scenes will fail to capture the temporal features. Few works focus on dynamic scene understanding based on Gaussian Splatting, since once the same update strategy is employed for both dynamic and static parts, regardless of the distinction and interaction between Gaussians, significant artifacts and noise appear. We propose Dual-Hierarchical Optimization (DHO), which consists of Hierarchical Gaussian Flow and Hierarchical Gaussian Guidance in a divide-and-conquer manner. The former implements effective division of static and dynamic rendering and features. The latter helps to mitigate the issue of dynamic foreground rendering distortion in textured complex scenes. Extensive experiments show that our method consistently outperforms the baselines on both synthetic and real-world datasets, and supports various downstream tasks. Project Page: https://sweety-yan.github.io/DHO.