Research map / Vision-language and multimodal / Human and embodied modeling
Bridging the Gap Between Computational Photography and Visual Recognition
Rosaura G. VidalMata, Sreya Banerjee, Brandon RichardWebster, Michael Albright, Pedro Davalos, Scott McCloskey, Ben Miller, Asongu L. Tambo, Sushobhan Ghosh, Sudarshan Nagesh, Ye Yuan, Yueyu Hu and 12 more
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 |
|---|---|---|---|
| apply CCRE enhancement | UG2 frames · UG2 Task 1 | images judged improved by humans: 126 images improved; 144 images rated 3 to 3.25 | Improved |
| apply MA-CNN enhancement | UG2 frames · UG2 Task 1 | images judged improved by humans: 59 improved; almost 25% rated 3.5 to 3.75 | Mixed |
| apply CCRE enhancement | ResNet · UG2 UAV Collection | M2: 0.20% improvement over baseline | Improved |
| apply MA-CNN enhancement | VGG16 and VGG19 · UG2 Glider Collection | M2: 2.23% and 3.10% improvement | Improved |
| apply CDRM enhancement | Inception · UG2 Ground Collection | M1 and M2: 5.30% and 5.21% improvement | Improved |
| apply participant enhancement algorithms | VGG19 · UG2 Ground Collection | M1 vs M2: 0.03% for M1, 2.95% for M2 | Mixed |
| apply Sharma et al. classification-driven enhancement filters | ImageNet-trained classifiers · UG2 | classification rate at rank 5 | No clear effect |
| use higher LPIPS change (stronger enhancement) | enhancement algorithms · UG2 Task 1 | human rating: LPIPS extremes of 0.36 and rating 2.35 | Hurt |
Closest papers by meaning
- UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement (CVPR 2026 · similarity 0.88)
- ClearAIR: A Human-Visual-Perception-Inspired All-in-One Image Restoration (AAAI 2026 · similarity 0.86)
- Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration (NeurIPS 2023 · similarity 0.86)
- Evaluation of Visual Processing Should Be Human-Centered, Not Metric-Centered (NeurIPS 2026 · similarity 0.86)
- VQCNIR: Clearer Night Image Restoration with Vector-Quantized Codebook (AAAI 2024 · similarity 0.85)
- BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model (NeurIPS 2024 · 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.
