Research map / 3D vision / 3D generation
SceneCode: Monocular Dense Semantic Reconstruction Using Learned Encoded Scene Representations
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| optimise compact semantic codes jointly across views instead of using multiplication-based element-wise fusion | SceneCode · SceneNet RGB-D (validation), 2 views | mIoU: 42.326 -> 43.842 | Helped |
| optimise compact semantic codes jointly across views instead of averaging element-wise probabilities | SceneCode · SceneNet RGB-D (validation), 2 views | mIoU: 42.220 -> 43.842 | Helped |
| optimise compact semantic codes jointly across views instead of using multiplication-based element-wise fusion | SceneCode · SceneNet RGB-D (validation), 3 views | mIoU: 42.692 -> 44.231 | Helped |
| optimise compact semantic codes jointly across views instead of averaging element-wise probabilities | SceneCode · SceneNet RGB-D (validation), 3 views | mIoU: 42.213 -> 44.231 | Helped |
| optimise compact semantic codes jointly across views instead of using multiplication-based element-wise fusion | SceneCode · SceneNet RGB-D (validation), 4 views | mIoU: 42.795 -> 44.263 | Helped |
| optimise compact semantic codes jointly across views instead of averaging element-wise probabilities | SceneCode · SceneNet RGB-D (validation), 4 views | mIoU: 42.102 -> 44.263 | Helped |
| add a zero-code prior during semantic optimisation (ablation) | SceneCode semantic fusion · SceneNet RGB-D (validation), 2 views | mIoU: 39.600 -> 43.842 | Helped |
Closest papers by meaning
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.90)
- Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning (CVPR 2024 · similarity 0.88)
- Bi-SSC: Geometric-Semantic Bidirectional Fusion for Camera-based 3D Semantic Scene Completion (CVPR 2024 · similarity 0.88)
- H2GFormer: Horizontal-to-Global Voxel Transformer for 3D Semantic Scene Completion (AAAI 2024 · similarity 0.88)
- MESC-3D:Mining Effective Semantic Cues for 3D Reconstruction from a Single Image (CVPR 2025 · similarity 0.88)
- Geometry-Guided Semantic Reconstruction for 3D Instance Segmentation (NeurIPS 2026 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.