GANmouflage: 3D Object Nondetection with Texture Fields

TL;DR

This paper introduces GANmouflage, a novel method that uses texture fields and adversarial learning to camouflage 3D objects within scenes, making them difficult to detect from various viewpoints, and demonstrates its effectiveness through human studies.

Contribution

It presents the first approach to hide complex 3D object shapes in scenes using learned textures optimized for multiple viewpoints.

Findings

Textures significantly improve concealment over previous methods

The model effectively camouflages various object shapes from different viewpoints

Human studies confirm enhanced invisibility of camouflaged objects

Abstract

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/