3 papers
cs.CV2025
OptiScene: LLM-driven Indoor Scene Layout Generation via Scaled Human-aligned Data Synthesis and Multi-Stage Preference Optimization
Yixuan Yang, Zhen Luo, Tongsheng Ding +5
Automatic indoor layout generation has attracted increasing attention due to its potential in interior design, virtual environment construction, and embodied AI. Existing methods f…
cs.CV2025
Advancing Video Anomaly Detection: A Bi-Directional Hybrid Framework for Enhanced Single- and Multi-Task Approaches
Guodong Shen, Yuqi Ouyang, Junru Lu +2
Despite the prevailing transition from single-task to multi-task approaches in video anomaly detection, we observe that many adopt sub-optimal frameworks for individual proxy tasks…
cs.CV2025
RefComp: A Reference-guided Unified Framework for Unpaired Point Cloud Completion
Yixuan Yang, Jinyu Yang, Zixiang Zhao +2
The unpaired point cloud completion task aims to complete a partial point cloud by using models trained with no ground truth. Existing unpaired point cloud completion methods are c…