Research map / Label-efficient and robust learning / Domain adaptation and generalization
Unsupervised Domain Adaptation for ToF Data Denoising With Adversarial Learning
Gianluca Agresti, Henrik Schaefer, Piergiorgio Sartor, Pietro Zanuttigh
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 |
|---|---|---|---|
| add adversarial domain adaptation to the synthetic-supervised Coarse-Fine CNN | Coarse-Fine CNN ToF denoiser · S4 | MAE (cm): 2.74 cm -> 2.36 cm | Improved |
| use the proposed noisy-depth/error-map discriminator instead of feature-based domain adaptation | ToF denoiser · S4 | MAE (cm): 2.6 -> 2.36 | Improved |
| use the proposed noisy-depth/error-map discriminator instead of feature-based domain adaptation | ToF denoiser · S5 | MAE (cm): 1.71 -> 1.66 | Improved |
| add adversarial domain adaptation to supervised synthetic-data training (ablation) | Coarse-Fine CNN ToF denoiser · S4 real-world validation scenes | MAE | Improved |
| add the history buffer to adversarial training (ablation) | Coarse-Fine CNN and discriminator · S4 real-world validation scenes | MAE | Improved |
| add noise data augmentation to discriminator training (ablation) | Coarse-Fine CNN and discriminator · S4 real-world validation scenes | MAE | Improved |
| add both the history buffer and noise data augmentation (ablation) | Coarse-Fine CNN and discriminator · S4 real-world validation scenes | MAE | Improved |
| remove both the history buffer and noise data augmentation (ablation) | Coarse-Fine CNN and discriminator · S4 real-world validation scenes | MAE | Hurt |
Closest papers by meaning
- Unsupervised Domain Adaptation of Deep Networks for ToF Depth Refinement (TPAMI 2021 · similarity 0.91)
- RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising (CVPR 2022 · similarity 0.87)
- Unsupervised Pixel-Level Domain Adaptation With Generative Adversarial Networks (CVPR 2017 · similarity 0.86)
- Adversarial Discriminative Domain Adaptation (CVPR 2017 · similarity 0.84)
- Real-Time Neural Denoising with Render-Aware Knowledge Distillation (AAAI 2025 · similarity 0.84)
- Denoising as Adaptation: Noise-Space Domain Adaptation for Image Restoration (ICLR 2025 · similarity 0.83)
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.
