# Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes

Source: [Unified Category-Level Object Detection and Pose Estimation from RGB Images using 3D Prototypes](<https://www.sota2.com/research/paper/68fa7a6a1e209131cea830ea>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-27T06:59:41.376Z

Authors: Tom Fischer, Xiaojie Zhang, Eddy Ilg

Published: 2025-08-04T07:57:39.000Z

## Abstract

Recognizing objects in images is a fundamental problem in computer vision. Although detecting objects in 2D images is common, many applications require determining their pose in 3D space. Traditional category-level methods rely on RGB-D inputs, which may not always be available, or employ two-stage approaches that use separate models and representations for detection and pose estimation. For the first time, we introduce a unified model that integrates detection and pose estimation into a single framework for RGB images by leveraging neural mesh models with learned features and multi-model RANSAC. Our approach achieves state-of-the-art results for RGB category-level pose estimation on REAL275, improving on the current state-of-the-art by 22.9% averaged across all scale-agnostic metrics. Finally, we demonstrate that our unified method exhibits greater robustness compared to single-stage baselines. Our code and models are available at https://github.com/Fischer-Tom/unified-detection-and-pose-estimation.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Category-level 6D Object Pose Estimation on REAL275](<https://www.sota2.com/research/sota/category-level-6d-object-pose-estimation-on-real275.md>): Category-level 6D Object Pose Estimation; REAL275; mAP (10°5cm): not recorded.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2508.02157>)

[PDF](<https://arxiv.org/pdf/2508.02157.pdf>)
