Interactive Occlusion Boundary Estimation through Exploitation of Synthetic Data
This work advances scene understanding for computer vision researchers by providing new tools and benchmarks for occlusion boundary estimation, though it is incremental in combining interactive mechanisms with synthetic data approaches.
The paper tackles the problem of interactive occlusion boundary estimation by introducing MS³PE, a multi-scribble-guided deep learning framework that surpasses seven state-of-the-art interactive segmentation methods, and addresses data scarcity through synthetic data generation with Mesh2OB, creating the OB-FUTURE benchmark and OB-LIGM real-world benchmark.
Occlusion boundaries (OBs) geometrically localize occlusion events in 2D images and provide critical cues for scene understanding. In this paper, we present the first systematic study of Interactive Occlusion Boundary Estimation (IOBE), introducing MS\textsuperscript{3}PE, a novel multi-scribble-guided deep-learning framework that advances IOBE through two key innovations: (1) an intuitive multi-scribble interaction mechanism, and (2) a 3-encoding-path network enhanced with multi-scale strip convolutions. Our MS\textsuperscript{3}PE surpasses adapted baselines from seven state-of-the-art interactive segmentation methods, and demonstrates strong potential for OB benchmark construction through our real-user experiment. Besides, to address the scarcity of well-annotated real-world data, we propose using synthetic data for training IOBE models, and developed Mesh2OB, the first automated tool for generating precise ground-truth OBs from 3D scenes with self-occlusions explicitly handled, enabling creation of the OB-FUTURE synthetic benchmark that facilitates generalizable training without domain adaptation. Finally, we introduce OB-LIGM, a high-quality real-world benchmark comprising 120 meticulously annotated high-resolution images advancing evaluation standards in OB research. Source code and resources are available at https://github.com/xul-ops/IOBE.