VOIC decouples monocular 3D scene completion into visible semantic perception and occluded reasoning via VRLE and a dual-decoder architecture, achieving state-of-the-art results on SemanticKITTI and SSCBench-KITTI360.
Symphonize 3d semantic scene completion with contextual instance queries,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
VOIC: Visible-Occluded Integrated Guidance for 3D Semantic Scene Completion
VOIC decouples monocular 3D scene completion into visible semantic perception and occluded reasoning via VRLE and a dual-decoder architecture, achieving state-of-the-art results on SemanticKITTI and SSCBench-KITTI360.