Tracking by 3D Model Estimation of Unknown Objects in Videos

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00371803" target="_blank" >RIV/68407700:21230/23:00371803 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1109/ICCV51070.2023.01295" target="_blank" >https://doi.org/10.1109/ICCV51070.2023.01295</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCV51070.2023.01295" target="_blank" >10.1109/ICCV51070.2023.01295</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Tracking by 3D Model Estimation of Unknown Objects in Videos

Popis výsledku v původním jazyce

Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue that this representation is limited and instead propose to guide and improve 2D tracking with an explicit object representation, namely the textured 3D shape and 6DoF pose in each video frame. Our representation tackles a complex long-term dense correspondence problem between all 3D points on the object for all video frames, including frames where some points are invisible. To achieve that, the estimation is driven by re-rendering the input video frames as well as possible through differentiable rendering, which has not been used for tracking before. The proposed optimization minimizes a novel loss function to estimate the best 3D shape, texture, and 6DoF pose. We improve the state-of-the-art in 2D segmentation tracking on three different datasets with mostly rigid objects.

Název v anglickém jazyce

Tracking by 3D Model Estimation of Unknown Objects in Videos

Popis výsledku anglicky

Most model-free visual object tracking methods formulate the tracking task as object location estimation given by a 2D segmentation or a bounding box in each video frame. We argue that this representation is limited and instead propose to guide and improve 2D tracking with an explicit object representation, namely the textured 3D shape and 6DoF pose in each video frame. Our representation tackles a complex long-term dense correspondence problem between all 3D points on the object for all video frames, including frames where some points are invisible. To achieve that, the estimation is driven by re-rendering the input video frames as well as possible through differentiable rendering, which has not been used for tracking before. The proposed optimization minimizes a novel loss function to estimate the best 3D shape, texture, and 6DoF pose. We improve the state-of-the-art in 2D segmentation tracking on three different datasets with mostly rigid objects.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

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

Projekt

<a href="/cs/project/EF16_019%2F0000765" target="_blank" >EF16_019/0000765: Výzkumné centrum informatiky</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Název statě ve sborníku

ICCV2023: Proceedings of the International Conference on Computer Vision

ISBN

979-8-3503-0719-1

ISSN

1550-5499

e-ISSN

2380-7504

Počet stran výsledku

11

Strana od-do

14040-14050

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Paris

Datum konání akce

2. 10. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001169499006047