Neural Refinement for Absolute Pose Regression with Feature Synthesis
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916142555070464 |
|---|---|
| author | Chen, Shuai Bhalgat, Yash Li, Xinghui Bian, Jiawang Li, Kejie Wang, Zirui Prisacariu, Victor Adrian |
| author_facet | Chen, Shuai Bhalgat, Yash Li, Xinghui Bian, Jiawang Li, Kejie Wang, Zirui Prisacariu, Victor Adrian |
| contents | Absolute Pose Regression (APR) methods use deep neural networks to directly regress camera poses from RGB images. However, the predominant APR architectures only rely on 2D operations during inference, resulting in limited accuracy of pose estimation due to the lack of 3D geometry constraints or priors. In this work, we propose a test-time refinement pipeline that leverages implicit geometric constraints using a robust feature field to enhance the ability of APR methods to use 3D information during inference. We also introduce a novel Neural Feature Synthesizer (NeFeS) model, which encodes 3D geometric features during training and directly renders dense novel view features at test time to refine APR methods. To enhance the robustness of our model, we introduce a feature fusion module and a progressive training strategy. Our proposed method achieves state-of-the-art single-image APR accuracy on indoor and outdoor datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2303_10087 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Neural Refinement for Absolute Pose Regression with Feature Synthesis Chen, Shuai Bhalgat, Yash Li, Xinghui Bian, Jiawang Li, Kejie Wang, Zirui Prisacariu, Victor Adrian Computer Vision and Pattern Recognition Absolute Pose Regression (APR) methods use deep neural networks to directly regress camera poses from RGB images. However, the predominant APR architectures only rely on 2D operations during inference, resulting in limited accuracy of pose estimation due to the lack of 3D geometry constraints or priors. In this work, we propose a test-time refinement pipeline that leverages implicit geometric constraints using a robust feature field to enhance the ability of APR methods to use 3D information during inference. We also introduce a novel Neural Feature Synthesizer (NeFeS) model, which encodes 3D geometric features during training and directly renders dense novel view features at test time to refine APR methods. To enhance the robustness of our model, we introduce a feature fusion module and a progressive training strategy. Our proposed method achieves state-of-the-art single-image APR accuracy on indoor and outdoor datasets. |
| title | Neural Refinement for Absolute Pose Regression with Feature Synthesis |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2303.10087 |