Research map / Detection and segmentation / CNN features
RDFNet: RGB-D Multi-Level Residual Feature Fusion for Indoor Semantic Segmentation
Seong-Jin Park, Ki-Sang Hong, Seungyong Lee
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 depth (HHA) via multi-modal fusion to RefineNet-152 | RefineNet Res-152 · NYUDv2 | mean IoU: 46.5 -> 50.1 | Improved |
| replace multi-level concatenation fusion with MMFNet fusion (ablation) | RDF-101 · NYUDv2 | mean IoU: 47.0 -> 49.1 | Improved |
| add residual pooling (ablation) | RDF-101 · NYUDv2 | mean IoU: 48.7 -> 49.1 | Improved |
| add adaptive-weight convolution in fusion (ablation) | RDF-101 · NYUDv2 | mean IoU: 47.7 -> 49.1 | Improved |
| add skip connection in RCUs (ablation) | RDF-101 · NYUDv2 | mean IoU: 45.8 -> 49.1 | Improved |
| deeper backbone ResNet-50 to ResNet-101 | RDFNet · NYUDv2 | mean IoU: 47.7 -> 49.1 | Improved |
| deeper backbone ResNet-101 to ResNet-152 | RDFNet · NYUDv2 | mean IoU: 49.1 -> 50.1 | Improved |
| use raw scaled depth instead of HHA encoding | RDF-101 · NYUDv2 | mean IoU: 49.1 -> 48.2 | Hurt |
| use RefineNet instead of FCN32 for HHA-only input | depth-only network · NYUDv2 | mean IoU: 25.2 -> 36.3 | Improved |
Closest papers by meaning
- Locality-Sensitive Deconvolution Networks With Gated Fusion for RGB-D Indoor Semantic Segmentation (CVPR 2017 · similarity 0.92)
- Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks (ECCV 2016 · similarity 0.92)
- Discriminative Multi-Modal Feature Fusion for RGBD Indoor Scene Recognition (CVPR 2016 · similarity 0.92)
- DF2Net: Discriminative Feature Learning and Fusion Network for RGB-D Indoor Scene Classification (AAAI 2018 · similarity 0.90)
- PDDM: Pseudo Depth Diffusion Model for RGB-PD Semantic Segmentation Based in Complex Indoor Scenes (AAAI 2025 · similarity 0.87)
- DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation (ICLR 2024 · similarity 0.86)
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.
