# Bi-objective Optimization for Robust RGB-D Visual Odometry

Source: [Bi-objective Optimization for Robust RGB-D Visual Odometry](<https://www.sota2.com/research/paper/68fa61971e209131ce9f4ed6>)

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

Data updated: 2025-12-14T16:35:31.076Z

Authors: Tao Han, Chao Xu, Ryan Loxton, Lei Xie

Published: 2014-11-27T02:37:41.000Z

## Abstract

This paper considers a new bi-objective optimization formulation for robust RGB-D visual odometry. We investigate two methods for solving the proposed bi-objective optimization problem: the weighted sum method (in which the objective functions are combined into a single objective function) and the bounded objective method (in which one of the objective functions is optimized and the value of the other objective function is bounded via a constraint). Our experimental results for the open source TUM RGB-D dataset show that the new bi-objective optimization formulation is superior to several existing RGB-D odometry methods. In particular, the new formulation yields more accurate motion estimates and is more robust when textural or structural features in the image sequence are lacking.

## 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.

- [Visual Odometry on TUM RGB-D poor structure, rich texture, far (sequences 5-8)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-poor-structure-rich-texture-far-sequences-5-8.md>): Visual Odometry; TUM RGB-D poor structure, rich texture, far (sequences 5-8); RMSE (m/s): 0.078033.

- [Visual Odometry on TUM RGB-D rich structure poor texture far (sequences 5-8)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-rich-structure-poor-texture-far-sequences-5-8.md>): Visual Odometry; TUM RGB-D rich structure poor texture far (sequences 5-8); RMSE (m/s): 0.066008.

- [Visual Odometry on TUM RGB-D poor structure, poor texture, far (sequences 5-8)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-poor-structure-poor-texture-far-sequences-5-8.md>): Visual Odometry; TUM RGB-D poor structure, poor texture, far (sequences 5-8); RMSE (m/s): 0.123848.

- [Visual Odometry on TUM RGB-D rich structure rich texture far (sequences 5-8)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-rich-structure-rich-texture-far-sequences-5-8.md>): Visual Odometry; TUM RGB-D rich structure rich texture far (sequences 5-8); RMSE (m/s): 0.014284.

- [Visual Odometry on TUM RGB-D poor structure, rich texture, close (1st-4th sequences)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-poor-structure-rich-texture-close-1st-4th-sequences.md>): Visual Odometry; TUM RGB-D poor structure, rich texture, close (1st-4th sequences); RMSE (m/s): 0.032715.

- [Visual Odometry on TUM RGB-D rich structure, poor texture, close (1st-4th sequences)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-rich-structure-poor-texture-close-1st-4th-sequences.md>): Visual Odometry; TUM RGB-D rich structure, poor texture, close (1st-4th sequences); RMSE (m/s): 0.088853.

- [Visual Odometry on TUM RGB-D rich structure rich texture close (sequences 1-4)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-rich-structure-rich-texture-close-sequences-1-4.md>): Visual Odometry; TUM RGB-D rich structure rich texture close (sequences 1-4); RMSE (m/s): 0.015101.

- [Visual Odometry on TUM RGB-D poor structure, poor texture, close (1st-4th sequences)](<https://www.sota2.com/research/sota/visual-odometry-on-tum-rgb-d-poor-structure-poor-texture-close-1st-4th-sequences.md>): Visual Odometry; TUM RGB-D poor structure, poor texture, close (1st-4th sequences); RMSE (m/s): 0.178571.

- [RGB-D Odometry on TUM RGB-D Structure vs. Texture category](<https://www.sota2.com/research/sota/rgb-d-odometry-on-tum-rgb-d-structure-vs-texture-category.md>): RGB-D odometry; TUM RGB-D Structure vs. Texture category; Runtime: 22.99.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1411.7445>)

[PDF](<https://arxiv.org/pdf/1411.7445.pdf>)
