Xianliang Huang, Jiajie Gou, Shuhang Chen, Zhizhou Zhong, Jihong Guan, Shuigeng Zhou
IDDR-NGP is a novel method that efficiently removes a variety of 3D scene distractors using a combination of 3D representations and 2D detectors, outperforming existing solutions in versatility and robustness.
The paper introduces IDDR-NGP, a new method for cleaning up 3D scenes by removing unwanted elements like snowflakes or confetti. Unlike existing methods that focus on specific types of distractions, IDDR-NGP can handle a wide range of them by using a combination of 3D scene modeling and 2D image detection. The approach has been tested on both synthetic and real-world distractions and shows promising results in restoring high-quality 3D scenes. This makes it a versatile tool for improving the clarity and quality of 3D visualizations.
