Research map / Detection and segmentation / CNN features
Calibrated RGB-D Salient Object Detection
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 |
|---|---|---|---|
| Replace raw depth with calibrated depth (ablation) | Depth Stream · NJU2K | MAE: .068 -> .059 | Helped |
| Add calibrated depth to the RGB stream (ablation) | DCF · NJU2K | MAE: .046 -> .043 | Helped |
| Use CRM instead of direct feature fusion (ablation) | DCF with RGB and calibrated depth · NJU2K | MAE: .043 -> .035 | Helped |
| Add triplet loss to CRM (ablation) | DCF · NJU2K | MAE: .038 -> .035 | Helped |
| Train D3Net using calibrated rather than raw depth (ablation) | D3Net · DUT-D | MAE: 0.097 -> 0.081 | Helped |
| Train D3Net using calibrated rather than raw depth (ablation) | D3Net · NJU2K | MAE: 0.047 -> 0.043 | Helped |
| Train DMRA using calibrated rather than raw depth (ablation) | DMRA · DUT-D | MAE: 0.048 -> 0.043 | Helped |
| Train DMRA using calibrated rather than raw depth (ablation) | DMRA · NJU2K | MAE: 0.051 -> 0.047 | Helped |
Closest papers by meaning
- Deep RGB-D Saliency Detection With Depth-Sensitive Attention and Automatic Multi-Modal Fusion (CVPR 2021 · similarity 0.92)
- RGB-D Salient Object Detection via 3D Convolutional Neural Networks (AAAI 2021 · similarity 0.92)
- Promoting Saliency From Depth: Deep Unsupervised RGB-D Saliency Detection (ICLR 2022 · similarity 0.91)
- DVSOD: RGB-D Video Salient Object Detection (NeurIPS 2023 · similarity 0.91)
- DiMSOD: A Diffusion-Based Framework for Multi-Modal Salient Object Detection (AAAI 2025 · similarity 0.89)
- Alignment-Free RGB-T Salient Object Detection: A Large-Scale Dataset and Progressive Correlation Network (AAAI 2025 · 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.