Category Level 6D Object Pose Estimation from a Single RGB Image using Diffusion

TL;DR

This paper presents a novel category-level 6D object pose estimation method from a single RGB image using diffusion models, eliminating the need for specific object models or depth data, and achieving state-of-the-art results.

Contribution

It introduces a diffusion-based approach combined with Mean Shift for robust pose estimation without requiring object models or depth information.

Findings

Outperforms current state-of-the-art on REAL275 dataset

Eliminates need for object-specific models or depth data

Uses diffusion models and Mean Shift for pose estimation

Abstract

Estimating the 6D pose and 3D size of an object from an image is a fundamental task in computer vision. Most current approaches are restricted to specific instances with known models or require ground truth depth information or point cloud captures from LIDAR. We tackle the harder problem of pose estimation for category-level objects from a single RGB image. We propose a novel solution that eliminates the need for specific object models or depth information. Our method utilises score-based diffusion models to generate object pose hypotheses to model the distribution of possible poses for the object. Unlike previous methods that rely on costly trained likelihood estimators to remove outliers before pose aggregation using mean pooling, we introduce a simpler approach using Mean Shift to estimate the mode of the distribution as the final pose estimate. Our approach outperforms the current state-of-the-art on the REAL275 dataset by a significant margin.