Research map / 3D vision / Depth and stereo
RGBD Based Dimensional Decomposition Residual Network for 3D Semantic Scene Completion
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 |
|---|---|---|---|
| Fuse RGB and depth inputs instead of using depth alone (ablation) | DDRNet · NYU | SSC-IoU: 28.9 -> 30.4 | Helped |
| Fuse RGB and depth inputs instead of using RGB alone (ablation) | DDRNet · NYU | SSC-IoU: 27.2 -> 30.4 | Helped |
| Add LW-ASPP (ablation) | DDRNet without ASPP · NYU | SC-IoU: 56.8 -> 61.0 | Helped |
| Add LW-ASPP (ablation) | DDRNet without ASPP · NYU | SSC-IoU: 26.8 -> 30.4 | Helped |
| Replace LW-ASPP with full 3D-ASPP (ablation) | DDRNet · NYU | SSC-IoU: 30.4 -> 30.8; 195.0 -> 431.0 Params/k; 27.22 -> 63.28 FLOPs/G | Mixed |
| Replace DDR blocks with 3D-ResNet blocks (ablation) | RGBD SSC network · NYU | SSC-IoU: 30.4 -> 30.8 | Helped |
| Use DDR blocks instead of 3D-ResNet blocks (ablation) | RGBD SSC network · NYU | Params (k): 1540.5 -> 195.0 | Helped |
Closest papers by meaning
- Attention-Based Multi-Modal Fusion Network for Semantic Scene Completion (AAAI 2020 · similarity 0.91)
- Unleashing Network Potentials for Semantic Scene Completion (CVPR 2024 · similarity 0.87)
- Memory-Augmented Re-Completion for 3D Semantic Scene Completion (AAAI 2025 · similarity 0.87)
- Completion as Enhancement: A Degradation-Aware Selective Image Guided Network for Depth Completion (CVPR 2025 · similarity 0.87)
- DFormerv2: Geometry Self-Attention for RGBD Semantic Segmentation (CVPR 2025 · similarity 0.87)
- Context and Geometry Aware Voxel Transformer for Semantic Scene Completion (NeurIPS 2024 · 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.