拡散モデルによる動画生成におけるロボットの形状と位置の保持
Robot Shape and Location Retention in Video Generation Using Diffusion Models
拡散モデルを用いて、移動ロボットの形状と位置を正確に保持した動画を生成する手法を提案し、衝突検出モデルの学習データ作成を容易にした。
著者: Peng Wang, Zhihao Guo, Abdul Latheef Sait, Minh Huy Pham
分類: cs.RO
原文アブストラクト
Diffusion models have marked a significant milestone in the enhancement of image and video generation technologies. However, generating videos that precisely retain the shape and location of moving objects such as robots remains a challenge. This paper presents diffusion models specifically tailored to generate videos that accurately maintain the shape and location of mobile robots. This development offers substantial benefits to those working on detecting dangerous interactions between humans and robots by facilitating the creation of training data for collision detection models, circumventing the need for collecting data from the real world, which often involves legal and ethical issues. Our models incorporate techniques such as embedding accessible robot pose information and applying semantic mask regulation within the ConvNext backbone network. These techniques are designed to refine intermediate outputs, therefore improving the retention performance of shape and location. Through extensive experimentation, our models have demonstrated notable improvements in maintaining the shape and location of different robots, as well as enhancing overall video generation quality, compared to the benchmark diffusion model. Codes will be opensourced at \href{https://github.com/PengPaulWang/diffusion-robots}{Github}.
