Research map / Image generation / Autoregressive and latent generation
PieAPP: Perceptual Image-Error Assessment Through Pairwise Preference
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 |
|---|---|---|---|
| Use PieAPP's pairwise-preference-trained error estimator instead of Bosse et al. (FR) | Full-reference image-error assessment · PieAPP test set | KRCC (˜pAB /∈ [0.35,0.65]): 0.503 -> 0.815 | Helped |
| Replace PieAPP's error-estimation network with Kim et al.'s architecture (ablation) | Pairwise-learning framework · PieAPP test set | KRCC (˜pAB ∈ [0,1]): 0.668 -> 0.491 | Hurt |
| Replace PieAPP's error-estimation network with Bosse et al.'s no-reference architecture (ablation) | Pairwise-learning framework · PieAPP test set | KRCC (˜pAB ∈ [0,1]): 0.668 -> 0.470 | Hurt |
| Replace PieAPP's error-estimation network with Bosse et al.'s full-reference architecture (ablation) | Pairwise-learning framework · PieAPP test set | KRCC (˜pAB ∈ [0,1]): 0.668 -> 0.588 | Hurt |
| Train the error-estimation network on MOS labels rather than pairwise preferences (ablation) | Error-estimation f · CSIQ | KRCC | No clear effect |
Closest papers by meaning
- Perception Encoder: The best visual embeddings are not at the output of the network (NeurIPS 2025 · similarity 0.87)
- Multidimensional Observer Model and Perceptual Dimensions of Human Image Quality Assessment (NeurIPS 2026 · similarity 0.87)
- The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric (ICLR 2024 · similarity 0.86)
- Human and AI Perceptual Differences in Image Classification Errors (AAAI 2025 · similarity 0.86)
- Evaluating Multiview Object Consistency in Humans and Image Models (NeurIPS 2024 · similarity 0.86)
- When does perceptual alignment benefit vision representations? (NeurIPS 2024 · similarity 0.86)
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.