Research map / 3D vision / 3D generation
Image-to-Voxel Model Translation for 3D Scene Reconstruction and Segmentation
Vladimir V. Kniaz, Vladimir A. Knyaz, Fabio Remondino, Artem Bordodymov, Petr Moshkantsev
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| add Pose6DoF discriminator (ablation) | SSZ · ShapeNet | mean 3D IoU: 0.455 -> 0.614 | Improved |
| add Pose6DoF discriminator (ablation) | SSZ · SemanticVoxels | mean 3D IoU: 0.461 -> 0.620 | Improved |
| add 2D inverted residual blocks (ablation) | SSZ · ShapeNet | mean 3D IoU: 0.506 -> 0.614 | Improved |
| add 2D inverted residual blocks (ablation) | SSZ · SemanticVoxels | mean 3D IoU: 0.462 -> 0.620 | Improved |
| add 2D and 3D inverted residual blocks (ablation) | SSZ · ShapeNet | mean 3D IoU: 0.469 -> 0.614 | Improved |
| add 2D and 3D inverted residual blocks (ablation) | SSZ · SemanticVoxels | mean 3D IoU: 0.435 -> 0.620 | Improved |
| add 2D inverted residual blocks (bicycle class) (ablation) | SSZ · SemanticVoxels | mean 3D IoU: 0.000 -> 0.531 | Improved |
| use SSZ instead of Pix2Vox | SSZ · ShapeNet | mean 3D IoU: 0.562 -> 0.614 | Improved |
| use SSZ instead of Pix2Vox | SSZ · SemanticVoxels | mean 3D IoU: 0.254 -> 0.620 | Improved |
| use SSZ instead of Pix2Vox (plane class) | SSZ · ShapeNet | mean 3D IoU: 0.598 -> 0.558 | Hurt |
Closest papers by meaning
- VoxFormer: Sparse Voxel Transformer for Camera-Based 3D Semantic Scene Completion (CVPR 2023 · similarity 0.90)
- Atlas: End-to-End 3D Scene Reconstruction from Posed Images (ECCV 2020 · similarity 0.89)
- Structured Prediction of Unobserved Voxels From a Single Depth Image (CVPR 2016 · similarity 0.89)
- SDFormer: Vision-based 3D Semantic Scene Completion via SAM-assisted Dual-channel Voxel Transformer (ICCV 2025 · similarity 0.88)
- Large Spatial Model: End-to-end Unposed Images to Semantic 3D (NeurIPS 2024 · similarity 0.88)
- Know Your Neighbors: Improving Single-View Reconstruction via Spatial Vision-Language Reasoning (CVPR 2024 · similarity 0.88)
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.
