Research map / 3D vision / Depth and stereo
Augmenting Colonoscopy Using Extended and Directional CycleGAN for Lossy Image Translation
Shawn Mathew, Saad Nadeem, Sruti Kumari, Arie Kaufman
Check 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 XDCycleGAN instead of Ma et al.'s method for depth inference | Scale-consistent depth inference · Textured VC video, 2000 frames | SSIM: 0.637 -> 0.918 | Improved |
| Use XDCycleGAN instead of Ma et al.'s method for depth inference | Scale-consistent depth inference · Textured VC video, 2000 frames | RMSE: 92.67$\pm$10.32 -> 31.25$\pm$6.76 | Improved |
| Add extended cycle consistency loss (ablation) | CycleGAN · VC → OC → VC | cycle consistency accuracy for depth: 7.74$\pm$6.07 -> 6.84$\pm$5.39 | Improved |
| Add the Directional Discriminator to extended CycleGAN (ablation) | XCycleGAN · VC → OC → VC | cycle consistency accuracy for depth: 6.84$\pm$5.39 -> 6.34$\pm$3.73 | Improved |
| Add the Directional Discriminator (ablation) | XCycleGAN · OC to VC image translation | removal of textures and specular highlights | Improved |
| Add the Directional Discriminator (ablation) | XCycleGAN · VC to OC image translation | structural fidelity | Improved |
| Replace standard cycle consistency with extended cycle consistency (ablation) | CycleGAN · OC to VC image translation | texture and specular-highlight removal | Mixed |
Closest papers by meaning
- An Embedding-Unleashing Video Polyp Segmentation Framework via Region Linking and Scale Alignment (AAAI 2024 · similarity 0.86)
- VPSentry: Semi-supervised Video Polyp Segmentation via Sentry-guided Long-term Prototype Fusion with Correlation Dynamic Propagation (AAAI 2026 · similarity 0.86)
- Generative Adversarial Networks for Video-to-Video Domain Adaptation (AAAI 2020 · similarity 0.85)
- HFSTI-Net: Hierarchical Frequency-spatial-temporal Interactions for Video Polyp Segmentation (ICLR 2026 · similarity 0.85)
- Unsupervised Photometric-Consistent Depth Estimation from Endoscopic Monocular Video (AAAI 2025 · similarity 0.82)
- EffiDec3D: An Optimized Decoder for High-Performance and Efficient 3D Medical Image Segmentation (CVPR 2025 · similarity 0.81)
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.
