.png){kind=icon}
.png){kind=icon}
Return
Dynamic-Parameterized Reconstruction Model for Resource-Aware Spatial Intelligence
.png){kind=icon}
OA
AI
DOI：10.3390/s26082355.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Spatial intelligence in autonomous driving requires object-level 3D geometry, yet existing monocular mesh reconstruction methods usually operate with a fixed inference path and a single mesh parameterization, which limits their flexibility under heterogeneous resource constraints. To address this issue, we propose DyPRSI, a dynamic-parameterized framework for monocular vehicle 3D reconstruction that provides multiple predefined accuracy–latency operating points within a single model. DyPRSI inserts two early exits into a shared Res2Net–BiFPN trunk and associates each exit with an exit-specific mesh specification, forming a coarse-to-fine reconstruction hierarchy across network depth. To better match the efficiency requirements of shallow branches, DyPRSI adopts lightweight coordinate-classification keypoint decoding for EE1 and EE2, while retaining a heatmap-regression keypoint head in the Main branch to preserve the upper bound of reconstruction accuracy. Experiments on ApolloCar3D show that DyPRSI-Main achieves competitive reconstruction performance, whereas EE1 and EE2 substantially reduce end-to-end inference latency and provide useful alternatives under different resource requirements. Ablation studies further show that the speedup mainly comes from the lightweight branch-specific keypoint heads, while the exit-specific mesh settings help organize stable coarse-to-fine reconstruction behavior across branches. These results indicate that DyPRSI is a practical monocular vehicle reconstruction framework for resource-aware spatial intelligence.
Keywords:
monocular 3D reconstruction
early exit
resource-aware inference
spatial intelligence
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
3.5
Papers:
7.1W
Citations:
20.9W
View more organizations