DepthSSC: Monocular 3D Semantic Scene Completion via Depth-Spatial Alignment and Voxel Adaptation
This work improves 3D scene understanding for autonomous driving by enhancing monocular camera-based methods, though it appears incremental as it builds on existing approaches.
The paper tackled the problem of 3D semantic scene completion from monocular images, addressing challenges like inaccurate object shape prediction and boundary misclassification, and achieved state-of-the-art performance on datasets such as SemanticKITTI and SSCBench-KITTI-360.
The task of 3D semantic scene completion using monocular cameras is gaining significant attention in the field of autonomous driving. This task aims to predict the occupancy status and semantic labels of each voxel in a 3D scene from partial image inputs. Despite numerous existing methods, many face challenges such as inaccurately predicting object shapes and misclassifying object boundaries. To address these issues, we propose DepthSSC, an advanced method for semantic scene completion using only monocular cameras. DepthSSC integrates the Spatial Transformation Graph Fusion (ST-GF) module with Geometric-Aware Voxelization (GAV), enabling dynamic adjustment of voxel resolution to accommodate the geometric complexity of 3D space. This ensures precise alignment between spatial and depth information, effectively mitigating issues such as object boundary distortion and incorrect depth perception found in previous methods. Evaluations on the SemanticKITTI and SSCBench-KITTI-360 dataset demonstrate that DepthSSC not only captures intricate 3D structural details effectively but also achieves state-of-the-art performance.