Research map / Image generation / Autoregressive and latent generation
ALRe: Outlier Detection for Guided Refinement
Mingzhu Zhu, Zhang Gao, Junzhi Yu, Bingwei He, Jiantao Liu
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 ALRe instead of weighted-median-filter change as outlier detector | outlier detection · Synthetic Middlebury 2014, M=50 | IoU: 0.814 -> 0.978 | Improved |
| use ALRe instead of weighted-median-filter change as outlier detector | outlier detection · Synthetic Middlebury 2014, M=100 | IoU: 0.727 -> 0.958 | Improved |
| use ALRe instead of weighted-median-filter change as outlier detector | outlier detection · Synthetic Middlebury 2014, M=200 | IoU: 0.556 -> 0.868 | Improved |
| increase number of outlier regions M from 50 to 200 (ablation) | ALRe · Synthetic Middlebury 2014 | IoU: 0.978 -> 0.868 | Hurt |
| increase number of outlier regions M from 50 to 200 (ablation) | WMF detection · Synthetic Middlebury 2014 | IoU: 0.814 -> 0.556 | Hurt |
| increase ALRe expectation (larger box-filter R) (ablation) | ALRe and WMF · Synthetic Middlebury 2014 | IoU | No clear effect |
| use ALRe weights in WMF for depth refinement | WMF · RGB-D depth map refinement (qualitative) | visual quality | Improved |
| use ALRe weights in GF for feathering | GF · guided feathering (qualitative) | visual quality | Improved |
| use ALRe weights instead of cross check for disparity refinement | WLS/JBF · Middlebury 2003 disparity (qualitative) | visual quality | No clear effect |
| use ALRe weights instead of model-based weights for transmission refinement | WLS · haze removal (qualitative) | visual quality | No clear effect |
Closest papers by meaning
- LaRE^2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection (CVPR 2024 · similarity 0.85)
- OID: Outlier Identifying and Discarding in Blind Image Deblurring (ECCV 2020 · similarity 0.84)
- Efficient Subpixel Refinement With Symbolic Linear Predictors (CVPR 2018 · similarity 0.84)
- A Likelihood Ratio-Based Approach to Segmenting Unknown Objects (IJCV 2025 · similarity 0.83)
- Learning Image Demoiréing from Unpaired Real Data (AAAI 2024 · similarity 0.83)
- RODEO: Robust Outlier Detection via Exposing Adaptive Out-of-Distribution Samples (ICML 2024 · similarity 0.82)
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.
