Research map / 3D vision / Depth and stereo
Spatio-Focal Bidirectional Disparity Estimation From a Dual-Pixel Image
Donggun Kim, Hyeonjoong Jang, Inchul Kim, Min H. Kim
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 |
|---|---|---|---|
| use the proposed self-supervised bidirectional disparity method instead of Wadhwa et al. | Dual-pixel disparity estimation · Dataset by [23] | RMSE: 4.1113 -> 3.7943 | Improved |
| use the proposed self-supervised bidirectional disparity method instead of Wadhwa et al. | Dual-pixel disparity estimation · Dataset by [2] | RMSE: 6.7384 -> 5.5075 | Improved |
| use the proposed method instead of the best baseline | Dual-pixel depth estimation · Punnappurath et al. dataset | AI(1): 0.0449 -> 0.0391 | Improved |
| use the proposed method instead of the best baseline | Dual-pixel depth estimation · Punnappurath et al. dataset | AI(2): 0.0724 -> 0.0682 | Improved |
| use the proposed method instead of the best baseline | Dual-pixel depth estimation · Punnappurath et al. dataset | 1 − |ρs|: 0.2703 -> 0.2619 | Improved |
| add the kernel-split symmetry loss (ablation) | Pretrained stereo network with photometric and smoothness losses · Punnappurath et al. dataset | AI(1): 0.0502 -> 0.0391 | Improved |
| add the photometric loss (ablation) | Pretrained stereo network with kernel-split symmetry and smoothness losses · Punnappurath et al. dataset | AI(1): 0.0689 -> 0.0391 | Improved |
| add the smoothness loss (ablation) | Pretrained stereo network with kernel-split symmetry and photometric losses · Punnappurath et al. dataset | AI(1): 0.0398 -> 0.0391 | Improved |
| use only the kernel-split symmetry loss (ablation) | Pretrained stereo network · Punnappurath et al. dataset | AI(1): 0.0826 -> 0.0660 | Improved |
| use only the photometric loss (ablation) | Pretrained stereo network · Punnappurath et al. dataset | AI(1): 0.0826 -> 0.0656 | Improved |
| use only the smoothness loss (ablation) | Pretrained stereo network · Punnappurath et al. dataset | AI(1): 0.0826 -> 0.1122 | Hurt |
Closest papers by meaning
- Learning Single Camera Depth Estimation Using Dual-Pixels (ICCV 2019 · similarity 0.91)
- Weakly-Supervised Depth Estimation and Image Deblurring via Dual-Pixel Sensors (TPAMI 2024 · similarity 0.88)
- K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring (CVPR 2023 · similarity 0.88)
- Du²Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels (ECCV 2020 · similarity 0.88)
- DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints (NeurIPS 2025 · similarity 0.87)
- LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network (CVPR 2024 · similarity 0.85)
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.
