Research map / 3D vision / Depth and stereo
Attention-based Multi-Level Fusion Network for Light Field Depth Estimation
Read the paperCheck 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 |
|---|---|---|---|
| add intra-branch channel attention and inter-branch attention fusion (ablation) | AttMLFNet · HCI 4D Light Field scenes in Table 1 | Avg BadPix(0.07): 4.010 -> 2.801 | Helped |
| add intra-branch channel attention and inter-branch attention fusion (ablation) | AttMLFNet · HCI 4D Light Field scenes in Table 1 | Avg MSE: 1.926 -> 1.257 | Helped |
| add inter-branch attention fusion (ablation) | BaseNet · HCI 4D Light Field scenes in Table 1 | Avg BadPix(0.07): 4.010 -> 3.364 | Helped |
| add intra-branch channel attention to inter-branch fusion (ablation) | BattNet · HCI 4D Light Field scenes in Table 1 | Avg BadPix(0.07): 3.364 -> 2.801 | Helped |
| add intra-branch channel attention and inter-branch attention fusion (ablation) | AttMLFNet · HCI 4D Light Field scenes in Table 1 | Avg MSE: 1.561 -> 1.257 | Helped |
| use AttMLFNet instead of LFattNet | LF depth estimation · HCI 4D Light Field scenes in Table 1 | BadPix(0.07): 0.195 vs 0.271 (Cotton); 3.228 vs 3.126 (Backgammon) | Mixed |
Closest papers by meaning
- Attention-Based View Selection Networks for Light-Field Disparity Estimation (AAAI 2020 · similarity 0.91)
- Learning Fused Pixel and Feature-Based View Reconstructions for Light Fields (CVPR 2020 · similarity 0.88)
- Towards Multimodal Depth Estimation From Light Fields (CVPR 2022 · similarity 0.88)
- Occlusion-Aware Cost Constructor for Light Field Depth Estimation (CVPR 2022 · similarity 0.86)
- Structured Attention Guided Convolutional Neural Fields for Monocular Depth Estimation (CVPR 2018 · similarity 0.85)
- Multi-Focus Image Fusion via Explicit Defocus Blur Modelling (AAAI 2025 · similarity 0.84)
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.