FocalPose++: Focal Length and Object Pose Estimation via Render and Compare

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F25%3A00380610" target="_blank" >RIV/68407700:21230/25:00380610 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21730/25:00380610

Výsledek na webu

<a href="https://doi.org/10.1109/TPAMI.2024.3475638" target="_blank" >https://doi.org/10.1109/TPAMI.2024.3475638</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TPAMI.2024.3475638" target="_blank" >10.1109/TPAMI.2024.3475638</a>

Jazyk výsledku

angličtina

Název v původním jazyce

FocalPose++: Focal Length and Object Pose Estimation via Render and Compare

Popis výsledku v původním jazyce

We introduce FocalPose++, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known object. The contributions of this work are threefold. First, we derive a focal length update rule that extends an existing state-of-the-art render-and-compare 6D pose estimator to address the joint estimation task. Second, we investigate several different loss functions for jointly estimating the object pose and focal length. We find that a combination of direct focal length regression with a reprojection loss disentangling the contribution of translation, rotation, and focal length leads to improved results. Third, we explore the effect of different synthetic training data on the performance of our method. Specifically, we investigate different distributions used for sampling object's 6D pose and camera's focal length when rendering the synthetic images, and show that parametric distribution fitted on real training data works the best. We show results on three challenging benchmark datasets that depict known 3D models in uncontrolled settings. We demonstrate that our focal length and 6D pose estimates have lower error than the existing state-of-the-art methods.

Název v anglickém jazyce

FocalPose++: Focal Length and Object Pose Estimation via Render and Compare

Popis výsledku anglicky

We introduce FocalPose++, a neural render-and-compare method for jointly estimating the camera-object 6D pose and camera focal length given a single RGB input image depicting a known object. The contributions of this work are threefold. First, we derive a focal length update rule that extends an existing state-of-the-art render-and-compare 6D pose estimator to address the joint estimation task. Second, we investigate several different loss functions for jointly estimating the object pose and focal length. We find that a combination of direct focal length regression with a reprojection loss disentangling the contribution of translation, rotation, and focal length leads to improved results. Third, we explore the effect of different synthetic training data on the performance of our method. Specifically, we investigate different distributions used for sampling object's 6D pose and camera's focal length when rendering the synthetic images, and show that parametric distribution fitted on real training data works the best. We show results on three challenging benchmark datasets that depict known 3D models in uncontrolled settings. We demonstrate that our focal length and 6D pose estimates have lower error than the existing state-of-the-art methods.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

—

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Pattern Analysis and Machine Intelligence

ISSN

0162-8828

e-ISSN

1939-3539

Svazek periodika

47

Číslo periodika v rámci svazku

2

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

18

Strana od-do

755-772

Kód UT WoS článku

001395340500016

EID výsledku v databázi Scopus

2-s2.0-85207033812