Details
| Original language | English |
|---|---|
| Title of host publication | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops |
| Subtitle of host publication | CVPRW |
| Publisher | IEEE Computer Society |
| Pages | 3739-3743 |
| Number of pages | 5 |
| ISBN (electronic) | 9798350302493 |
| ISBN (print) | 979-8-3503-0250-9 |
| Publication status | Published - 2023 |
| Event | 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPRW 2023 - Vancouver, Canada Duration: 17 Jun 2023 → 24 Jun 2023 |
Publication series
| Name | IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops |
|---|---|
| Volume | 2023-June |
| ISSN (Print) | 2160-7508 |
| ISSN (electronic) | 2160-7516 |
Abstract
Monocular depth estimation is an essential but ill-posed (computer) vision task. While human visual perception of depth relies on several monocular depth clues, such as occlusion of objects, relative height, usual object size, linear perspective, deep learning models have to implicitly learn these cues from labeled training data to determine depth. In this paper, we investigate whether monocular depth criteria from human vision are violated for certain image instances given a model's predictions. We consider the task of depth estimation as a ranking problem, i.e., for a given pair of points, we estimate which point is nearer to the camera. In particular, we model four monocular depth criteria to automatically predict a subset of point pairs and infer their depth relation. Our experiments show that the implemented depth criteria achieve comparable performance to deep learning models. This allows the investigation of models with regard to the plausibility of predictions by finding image instances where the prediction is incorrect according to modeled human visual perception.
ASJC Scopus subject areas
- Computer Science(all)
- Computer Vision and Pattern Recognition
- Engineering(all)
- Electrical and Electronic Engineering
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops: CVPRW. IEEE Computer Society, 2023. p. 3739-3743 (IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops; Vol. 2023-June).
Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
}
TY - GEN
T1 - Analyzing Results of Depth Estimation Models with Monocular Criteria
AU - Theiner, Jonas
AU - Nommensen, Nils
AU - Rhotert, Jim
AU - Springstein, Matthias
AU - Muller-Budack, Eric
AU - Ewerth, Ralph
N1 - Funding Information: Acknowledgment This work was funded by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – project number 420493178.
PY - 2023
Y1 - 2023
N2 - Monocular depth estimation is an essential but ill-posed (computer) vision task. While human visual perception of depth relies on several monocular depth clues, such as occlusion of objects, relative height, usual object size, linear perspective, deep learning models have to implicitly learn these cues from labeled training data to determine depth. In this paper, we investigate whether monocular depth criteria from human vision are violated for certain image instances given a model's predictions. We consider the task of depth estimation as a ranking problem, i.e., for a given pair of points, we estimate which point is nearer to the camera. In particular, we model four monocular depth criteria to automatically predict a subset of point pairs and infer their depth relation. Our experiments show that the implemented depth criteria achieve comparable performance to deep learning models. This allows the investigation of models with regard to the plausibility of predictions by finding image instances where the prediction is incorrect according to modeled human visual perception.
AB - Monocular depth estimation is an essential but ill-posed (computer) vision task. While human visual perception of depth relies on several monocular depth clues, such as occlusion of objects, relative height, usual object size, linear perspective, deep learning models have to implicitly learn these cues from labeled training data to determine depth. In this paper, we investigate whether monocular depth criteria from human vision are violated for certain image instances given a model's predictions. We consider the task of depth estimation as a ranking problem, i.e., for a given pair of points, we estimate which point is nearer to the camera. In particular, we model four monocular depth criteria to automatically predict a subset of point pairs and infer their depth relation. Our experiments show that the implemented depth criteria achieve comparable performance to deep learning models. This allows the investigation of models with regard to the plausibility of predictions by finding image instances where the prediction is incorrect according to modeled human visual perception.
UR - http://www.scopus.com/inward/record.url?scp=85170820212&partnerID=8YFLogxK
U2 - 10.1109/CVPRW59228.2023.00385
DO - 10.1109/CVPRW59228.2023.00385
M3 - Conference contribution
AN - SCOPUS:85170820212
SN - 979-8-3503-0250-9
T3 - IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
SP - 3739
EP - 3743
BT - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
PB - IEEE Computer Society
T2 - 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPRW 2023
Y2 - 17 June 2023 through 24 June 2023
ER -