Research map / Architectures and efficiency / RNNs and normalization
The Domain Transform Solver
Akash Bapat, Jan-Michael Frahm
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 |
|---|---|---|---|
| Replace BL-Solver refinement with DTS | MC-CNN stereo refinement · Middlebury training | time/MP (s): 42.7 (126) -> 5.9 (89.2) | Improved |
| Replace BL-Solver refinement with DTS | MC-CNN stereo refinement · Middlebury training | MAE (px), non-occluded: 2.60 -> 3.02 | Hurt |
| Replace BL-Solver refinement with DTS | MC-CNN stereo refinement · Middlebury testing | time/MP (s): 28 (140) -> 10 (122) | Improved |
| Replace BL-Solver refinement with DTS | MC-CNN stereo refinement · Middlebury testing | MAE (px), non-occluded: 2.67 -> 3.78 | Hurt |
| Use DTS instead of bicubic upsampling alone | Depth super-resolution · Art/Books/Moebius average | Avg. error (px): 5.94 -> 3.43 | Improved |
| Replace BL-Solver with DTS | Depth super-resolution · Art/Books/Moebius average | Avg. error (px): 2.75 -> 3.43 | Hurt |
| Replace BL-Solver with DTS | Depth super-resolution · Art/Books/Moebius average | time (s): 0.234 -> 0.0215 | Improved |
| Increase gradient-descent iterations | DTS stereo optimization · Middlebury training | MAE and RMSE | Improved |
Closest papers by meaning
- The Fast Bilateral Solver (ECCV 2016 · similarity 0.87)
- Edge-aware Image Smoothing with Relative Wavelet Domain Representation (ICLR 2025 · similarity 0.87)
- Pixel-Perfect Depth with Semantics-Prompted Diffusion Transformers (NeurIPS 2025 · similarity 0.85)
- $\alpha$Depth: Learning Single-Pass Soft Boundary Decomposition for Stereo Conversion (NeurIPS 2026 · similarity 0.85)
- Diff-Shadow: Global-guided Diffusion Model for Shadow Removal (AAAI 2025 · similarity 0.85)
- Intrinsic Phase-Preserving Networks for Depth Super Resolution (AAAI 2024 · 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.
