GANmouflage: 3D Object Nondetection with Texture Fields
This addresses the problem of object nondetection for applications in security or privacy, representing a novel approach for complex shapes.
The paper tackles the problem of camouflaging 3D objects in scenes by learning textures that make them difficult to detect from multiple viewpoints, achieving significantly better concealment than previous methods in a human visual search study.
We propose a method that learns to camouflage 3D objects within scenes. Given an object's shape and a distribution of viewpoints from which it will be seen, we estimate a texture that will make it difficult to detect. Successfully solving this task requires a model that can accurately reproduce textures from the scene, while simultaneously dealing with the highly conflicting constraints imposed by each viewpoint. We address these challenges with a model based on texture fields and adversarial learning. Our model learns to camouflage a variety of object shapes from randomly sampled locations and viewpoints within the input scene, and is the first to address the problem of hiding complex object shapes. Using a human visual search study, we find that our estimated textures conceal objects significantly better than previous methods. Project site: https://rrrrrguo.github.io/ganmouflage/