Research map / Detection and segmentation / 3D detection and driving

VoxDet: Rethinking 3D Semantic Scene Completion as Dense Object Detection

NeurIPS 2025 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 0 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Reframes 3D semantic scene completion from dense voxel segmentation to dense object detection, aiming to add instance-centric discriminability to fix instance-level incompleteness and adjacent-object ambiguity.

Problem

3D semantic scene completion (SSC) is typically treated as independent per-voxel classification, which ignores instance-level structure and causes instance incompleteness and ambiguity between adjacent objects.

Approach

Recasts SSC as a dense object detection problem so that voxels are reasoned about in an instance-centric way rather than as independent segmentation labels; details beyond the abstract are not available.

Closest papers by meaning

• Sparsity-Aware Voxel Attention and Foreground Modulation for 3D Semantic Scene Completion (CVPR 2026 · similarity 0.92)
• Not All Voxels Are Equal: Semantic Scene Completion from the Point-Voxel Perspective (AAAI 2022 · similarity 0.91)
• H2GFormer: Horizontal-to-Global Voxel Transformer for 3D Semantic Scene Completion (AAAI 2024 · similarity 0.90)
• Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation (CVPR 2024 · similarity 0.90)
• Context and Geometry Aware Voxel Transformer for Semantic Scene Completion (NeurIPS 2024 · similarity 0.90)
• Three Cars Approaching within 100m! Enhancing Distant Geometry by Tri-Axis Voxel Scanning for Camera-based Semantic Scene Completion (CVPR 2025 · similarity 0.89)