Research map / 3D vision / Depth and stereo
Invert to Learn to Invert
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 |
|---|---|---|---|
| Replace RIM with invertible i-RIM 2D | Iterative MRI reconstruction · fastMRI single-coil validation, 4x acceleration | NMSE: 0.0332 -> 0.0316 | Helped |
| Replace RIM with invertible i-RIM 2D | Iterative MRI reconstruction · fastMRI single-coil validation, 8x acceleration | NMSE: 0.0484 -> 0.0429 | Helped |
| Replace RIM with invertible i-RIM 2D | Iterative MRI reconstruction · fastMRI single-coil test, 4x acceleration | NMSE: 0.0270 -> 0.0255 | Helped |
| Replace RIM with invertible i-RIM 2D | Iterative MRI reconstruction · fastMRI single-coil test, 8x acceleration | NMSE: 0.0458 -> 0.0408 | Helped |
| Use i-RIM 3D instead of RIM | Iterative MRI reconstruction · fastMRI single-coil validation, 4x acceleration | NMSE: 0.0332 -> 0.0322 | Helped |
| Use i-RIM 3D instead of RIM | Iterative MRI reconstruction · fastMRI single-coil validation, 8x acceleration | NMSE: 0.0484 -> 0.0435 | Helped |
| Use i-RIM 3D instead of RIM | Iterative MRI reconstruction · fastMRI single-coil test, 4x acceleration | NMSE: 0.0270 -> 0.0261 | Helped |
| Use i-RIM 3D instead of RIM | Iterative MRI reconstruction · fastMRI single-coil test, 8x acceleration | NMSE: 0.0458 -> 0.0413 | Helped |
| Use invertible training for a 400-layer, 2D iterative model | Iterative MRI reconstruction · Training memory at 8 inference steps | memory (GB): 10.49 -> 2.51 | Helped |
| Use invertible training for a 400-layer, 3D iterative model | Iterative MRI reconstruction · Training memory at 8 inference steps | memory (GB): 11.89 | Helped |
Closest papers by meaning
- i-RevNet: Deep Invertible Networks (ICLR 2018 · similarity 0.88)
- Sparse Model Inversion: Efficient Inversion of Vision Transformers for Data-Free Applications (ICML 2024 · similarity 0.86)
- Model Inversion with Layer-Specific Modeling and Alignment for Data-Free Continual Learning (NeurIPS 2025 · similarity 0.85)
- Patch Rebirth: Fast and Transferable Model Inversion of Vision Transformers (NeurIPS 2026 · similarity 0.85)
- Network Inversion of Convolutional Neural Nets (Student Abstract) (AAAI 2025 · similarity 0.85)
- Self-diffusion for Solving Inverse Problems (NeurIPS 2025 · 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.