Improving 2D-3D Dense Correspondences with Diffusion Models for 6D Object Pose Estimation
This work addresses the challenge of occlusion, clutter, and material properties in 6D object pose estimation, which is incremental as it applies a known superior method (diffusion models) to an existing task.
The study tackled the problem of improving 2D-3D dense correspondences for 6D object pose estimation by comparing GAN-based and diffusion-based image-to-image translation models, finding that the diffusion model outperformed the GAN, indicating potential for further enhancements in pose estimation accuracy.
Estimating 2D-3D correspondences between RGB images and 3D space is a fundamental problem in 6D object pose estimation. Recent pose estimators use dense correspondence maps and Point-to-Point algorithms to estimate object poses. The accuracy of pose estimation depends heavily on the quality of the dense correspondence maps and their ability to withstand occlusion, clutter, and challenging material properties. Currently, dense correspondence maps are estimated using image-to-image translation models based on GANs, Autoencoders, or direct regression models. However, recent advancements in image-to-image translation have led to diffusion models being the superior choice when evaluated on benchmarking datasets. In this study, we compare image-to-image translation networks based on GANs and diffusion models for the downstream task of 6D object pose estimation. Our results demonstrate that the diffusion-based image-to-image translation model outperforms the GAN, revealing potential for further improvements in 6D object pose estimation models.