Research map / 3D vision / Depth and stereo
Light Field Messaging With Deep Photographic Steganography
Check 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 |
|---|---|---|---|
| Add CDTF model T() to training (ablation) | LFM · tested camera-display pairs, frontal | BER: 49.961% -> 10.051%; 50.138% -> 6.5809%; 50.047% -> 10.333%; 50.108% -> 5.0732%; 50.042% -> 4.8305% | Helped |
| Add CDTF model T() to training (ablation) | LFM · new camera-display pairs, frontal | BER: 50.059% -> 9.1688%; 49.948% -> 7.313%; 50.0005% -> 20.454%; 49.997% -> 17.555% | Helped |
| Use CDTF-trained photographic embedding instead of Baluja steganography | camera-display messaging on new hardware · four unseen camera-display pairs, frontal | BER: 40.372% -> 9.1688%; 37.152% -> 7.313%; 48.497% -> 20.454%; 48.827% -> 17.555% | Helped |
| Increase camera-display angle from frontal to 45° | LFM with T() · tested camera-display pairs | BER: 10.051% -> 29.807%; 6.5809% -> 15.229%; 10.333% -> 10.217%; 5.0732% -> 5.1415%; 4.8305% -> 10.01% | Hurt |
| Increase perceptual loss weight λT (ablation) | LFM embedding · coded-image visual quality and message recovery | BER | Mixed |
| Change camera exposure to overexposed (ablation) | LFM with T() · Pixel 2 + Acer Predator XB271HU | BER: 0.78% -> 7.42% | Hurt |
| Change camera exposure to underexposed (ablation) | LFM with T() · Pixel 2 + Acer Predator XB271HU | BER: 0.78% -> 0.29% | Helped |
Closest papers by meaning
- Robust Message Embedding via Attention Flow-Based Steganography (CVPR 2025 · similarity 0.84)
- Time-Efficient Light-Field Acquisition Using Coded Aperture and Events (CVPR 2024 · similarity 0.83)
- StegoGAN: Leveraging Steganography for Non-Bijective Image-to-Image Translation (CVPR 2024 · similarity 0.82)
- Event Fields: Capturing Light Fields at High Speed, Resolution, and Dynamic Range (CVPR 2025 · similarity 0.82)
- NeLF-Pro: Neural Light Field Probes for Multi-Scale Novel View Synthesis (CVPR 2024 · similarity 0.81)
- S2D-LFE: Sparse-to-Dense Light Field Event Generation (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.