3D Visual Illusion Depth Estimation
This addresses the vulnerability of machine vision systems to perceptual illusions, which is an incremental improvement for depth estimation in AI and computer vision.
The paper tackled the problem of 3D visual illusions fooling machine depth estimation systems by collecting a dataset of 3k scenes and 200k images to evaluate SOTA methods, and proposed a framework using vision language model common sense to adaptively fuse depth cues, achieving SOTA performance.
3D visual illusion is a perceptual phenomenon where a two-dimensional plane is manipulated to simulate three-dimensional spatial relationships, making a flat artwork or object look three-dimensional in the human visual system. In this paper, we reveal that the machine visual system is also seriously fooled by 3D visual illusions, including monocular and binocular depth estimation. In order to explore and analyze the impact of 3D visual illusion on depth estimation, we collect a large dataset containing almost 3k scenes and 200k images to train and evaluate SOTA monocular and binocular depth estimation methods. We also propose a 3D visual illusion depth estimation framework that uses common sense from the vision language model to adaptively fuse depth from binocular disparity and monocular depth. Experiments show that SOTA monocular, binocular, and multi-view depth estimation approaches are all fooled by various 3D visual illusions, while our method achieves SOTA performance.