RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908310810132480 |
|---|---|
| author | Monteagudo, Henrique Piñeiro Taccari, Leonardo Pjetri, Aurel Sambo, Francesco Salti, Samuele |
| author_facet | Monteagudo, Henrique Piñeiro Taccari, Leonardo Pjetri, Aurel Sambo, Francesco Salti, Samuele |
| contents | Bird's Eye View (BEV) semantic maps have recently garnered a lot of attention as a useful representation of the environment to tackle assisted and autonomous driving tasks. However, most of the existing work focuses on the fully supervised setting, training networks on large annotated datasets. In this work, we present RendBEV, a new method for the self-supervised training of BEV semantic segmentation networks, leveraging differentiable volumetric rendering to receive supervision from semantic perspective views computed by a 2D semantic segmentation model. Our method enables zero-shot BEV semantic segmentation, and already delivers competitive results in this challenging setting. When used as pretraining to then fine-tune on labeled BEV ground-truth, our method significantly boosts performance in low-annotation regimes, and sets a new state of the art when fine-tuning on all available labels. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_14792 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation Monteagudo, Henrique Piñeiro Taccari, Leonardo Pjetri, Aurel Sambo, Francesco Salti, Samuele Computer Vision and Pattern Recognition Bird's Eye View (BEV) semantic maps have recently garnered a lot of attention as a useful representation of the environment to tackle assisted and autonomous driving tasks. However, most of the existing work focuses on the fully supervised setting, training networks on large annotated datasets. In this work, we present RendBEV, a new method for the self-supervised training of BEV semantic segmentation networks, leveraging differentiable volumetric rendering to receive supervision from semantic perspective views computed by a 2D semantic segmentation model. Our method enables zero-shot BEV semantic segmentation, and already delivers competitive results in this challenging setting. When used as pretraining to then fine-tune on labeled BEV ground-truth, our method significantly boosts performance in low-annotation regimes, and sets a new state of the art when fine-tuning on all available labels. |
| title | RendBEV: Semantic Novel View Synthesis for Self-Supervised Bird's Eye View Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.14792 |