MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914882871361536 |
|---|---|
| author | Oh, Youngmin Kim, Hyung-Il Kim, Seong Tae Kim, Jung Uk |
| author_facet | Oh, Youngmin Kim, Hyung-Il Kim, Seong Tae Kim, Jung Uk |
| contents | Monocular 3D object detection is an important challenging task in autonomous driving. Existing methods mainly focus on performing 3D detection in ideal weather conditions, characterized by scenarios with clear and optimal visibility. However, the challenge of autonomous driving requires the ability to handle changes in weather conditions, such as foggy weather, not just clear weather. We introduce MonoWAD, a novel weather-robust monocular 3D object detector with a weather-adaptive diffusion model. It contains two components: (1) the weather codebook to memorize the knowledge of the clear weather and generate a weather-reference feature for any input, and (2) the weather-adaptive diffusion model to enhance the feature representation of the input feature by incorporating a weather-reference feature. This serves an attention role in indicating how much improvement is needed for the input feature according to the weather conditions. To achieve this goal, we introduce a weather-adaptive enhancement loss to enhance the feature representation under both clear and foggy weather conditions. Extensive experiments under various weather conditions demonstrate that MonoWAD achieves weather-robust monocular 3D object detection. The code and dataset are released at https://github.com/VisualAIKHU/MonoWAD. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16448 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection Oh, Youngmin Kim, Hyung-Il Kim, Seong Tae Kim, Jung Uk Computer Vision and Pattern Recognition Monocular 3D object detection is an important challenging task in autonomous driving. Existing methods mainly focus on performing 3D detection in ideal weather conditions, characterized by scenarios with clear and optimal visibility. However, the challenge of autonomous driving requires the ability to handle changes in weather conditions, such as foggy weather, not just clear weather. We introduce MonoWAD, a novel weather-robust monocular 3D object detector with a weather-adaptive diffusion model. It contains two components: (1) the weather codebook to memorize the knowledge of the clear weather and generate a weather-reference feature for any input, and (2) the weather-adaptive diffusion model to enhance the feature representation of the input feature by incorporating a weather-reference feature. This serves an attention role in indicating how much improvement is needed for the input feature according to the weather conditions. To achieve this goal, we introduce a weather-adaptive enhancement loss to enhance the feature representation under both clear and foggy weather conditions. Extensive experiments under various weather conditions demonstrate that MonoWAD achieves weather-robust monocular 3D object detection. The code and dataset are released at https://github.com/VisualAIKHU/MonoWAD. |
| title | MonoWAD: Weather-Adaptive Diffusion Model for Robust Monocular 3D Object Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2407.16448 |