MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection
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_ | 1866915235571433472 |
|---|---|
| author | Parihar, Rishubh Sarkar, Srinjay Vora, Sarthak Kundu, Jogendra Babu, R. Venkatesh |
| author_facet | Parihar, Rishubh Sarkar, Srinjay Vora, Sarthak Kundu, Jogendra Babu, R. Venkatesh |
| contents | Current monocular 3D detectors are held back by the limited diversity and scale of real-world datasets. While data augmentation certainly helps, it's particularly difficult to generate realistic scene-aware augmented data for outdoor settings. Most current approaches to synthetic data generation focus on realistic object appearance through improved rendering techniques. However, we show that where and how objects are positioned is just as crucial for training effective 3D monocular detectors. The key obstacle lies in automatically determining realistic object placement parameters - including position, dimensions, and directional alignment when introducing synthetic objects into actual scenes. To address this, we introduce MonoPlace3D, a novel system that considers the 3D scene content to create realistic augmentations. Specifically, given a background scene, MonoPlace3D learns a distribution over plausible 3D bounding boxes. Subsequently, we render realistic objects and place them according to the locations sampled from the learned distribution. Our comprehensive evaluation on two standard datasets KITTI and NuScenes, demonstrates that MonoPlace3D significantly improves the accuracy of multiple existing monocular 3D detectors while being highly data efficient. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_06801 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection Parihar, Rishubh Sarkar, Srinjay Vora, Sarthak Kundu, Jogendra Babu, R. Venkatesh Computer Vision and Pattern Recognition Current monocular 3D detectors are held back by the limited diversity and scale of real-world datasets. While data augmentation certainly helps, it's particularly difficult to generate realistic scene-aware augmented data for outdoor settings. Most current approaches to synthetic data generation focus on realistic object appearance through improved rendering techniques. However, we show that where and how objects are positioned is just as crucial for training effective 3D monocular detectors. The key obstacle lies in automatically determining realistic object placement parameters - including position, dimensions, and directional alignment when introducing synthetic objects into actual scenes. To address this, we introduce MonoPlace3D, a novel system that considers the 3D scene content to create realistic augmentations. Specifically, given a background scene, MonoPlace3D learns a distribution over plausible 3D bounding boxes. Subsequently, we render realistic objects and place them according to the locations sampled from the learned distribution. Our comprehensive evaluation on two standard datasets KITTI and NuScenes, demonstrates that MonoPlace3D significantly improves the accuracy of multiple existing monocular 3D detectors while being highly data efficient. |
| title | MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2504.06801 |