CompenHR: Efficient Full Compensation for High-resolution Projector
This work addresses a practical issue in projector-camera systems for high-resolution applications, offering an incremental improvement over existing methods.
The paper tackles the problem of full projector compensation for high-resolution setups, which is impractical with existing deep learning methods due to training time and memory costs, and proposes a solution that improves efficiency and quality, demonstrating clear advantages in experiments.
Full projector compensation is a practical task of projector-camera systems. It aims to find a projector input image, named compensation image, such that when projected it cancels the geometric and photometric distortions due to the physical environment and hardware. State-of-the-art methods use deep learning to address this problem and show promising performance for low-resolution setups. However, directly applying deep learning to high-resolution setups is impractical due to the long training time and high memory cost. To address this issue, this paper proposes a practical full compensation solution. Firstly, we design an attention-based grid refinement network to improve geometric correction quality. Secondly, we integrate a novel sampling scheme into an end-to-end compensation network to alleviate computation and introduce attention blocks to preserve key features. Finally, we construct a benchmark dataset for high-resolution projector full compensation. In experiments, our method demonstrates clear advantages in both efficiency and quality.