Research map / Image generation / Super-resolution
DIFFSSR: Stereo Image Super-resolution Using Differential Transformer
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes DIFFSSR, a stereo image super-resolution network built on a differential Transformer attention mechanism intended to suppress attention noise.
Problem
Stereo image super-resolution (StereoSR) for AR/VR and autonomous driving, where Transformer-based models suffer from attention noise that yields suboptimal reconstructions.
Approach
Applies a differential Transformer design to StereoSR so that attention noise is reduced, in contrast to standard Transformer-based stereo SR models.
Experimental setup
Builds on: differential transformer
Closest papers by meaning
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (AAAI 2024 · similarity 0.85)
- CFAT: Unleashing Triangular Windows for Image Super-resolution (CVPR 2024 · similarity 0.84)
- Recursive Generalization Transformer for Image Super-Resolution (ICLR 2024 · similarity 0.84)
- DEFOM-Stereo: Depth Foundation Model Based Stereo Matching (CVPR 2025 · similarity 0.84)
- RRT-MVS: Recurrent Regularization Transformer for Multi-View Stereo (AAAI 2025 · similarity 0.84)
- MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo (ICLR 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.