Research map / 3D vision / 3D generation
Diffusion-based dual-view reflection removal
Tianyi Xu, Zifeng Wang, Boyang Lyu, Shuchen Weng, Boxin Shi
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 |
|---|---|---|---|
| add camera pose encoding (ablation) | dual-view diffusion · DualRef-V | PSNR: 23.53 -> 24.17 | Improved |
| add camera pose encoding (ablation) | dual-view diffusion · DualRef-R | PSNR: 27.47 -> 28.19 | Improved |
| use two distinct views instead of one view (ablation) | dual-view diffusion w/o pose · DualRef-V | PSNR: 21.59 -> 23.53 | Improved |
| use two distinct views instead of identical inputs (ablation) | dual-view diffusion w/o pose · DualRef-R | PSNR: 26.12 -> 27.47 | Improved |
| use frame-aware spatial attention instead of RAFT flow warping (ablation) | SD2.1 dual-view · DualRef-V | PSNR: 21.60 -> 24.17 | Improved |
| use frame-aware spatial attention instead of Cat3D-style joint attention (ablation) | dual-view diffusion · DualRef-V | PSNR: 22.09 -> 24.17 | Improved |
| use frame-aware spatial attention instead of 3D ResNet (SIR-style) (ablation) | dual-view diffusion · DualRef-V | PSNR: 20.87 -> 24.17 | Improved |
| use channel-wise fusion with attention instead of width concatenation (ablation) | dual-view diffusion · DualRef-R | PSNR: 25.83 -> 28.19 | Improved |
| use frame-aware spatial attention instead of Cat3D-style joint attention (ablation) | dual-view diffusion · DualRef-R | LPIPS: 0.1244 -> 0.0983 | Improved |
| fine-tune DSIT on DualRef training data | DSIT · DualRef-V | PSNR: 19.54 -> 20.55 | Improved |
| fine-tune ZF24 on DualRef training data | ZF24 · DualRef-V | PSNR: 19.80 -> 20.17 | Improved |
| increase number of input views beyond two (ablation) | dual-view diffusion · DualRef-V | quality | No clear effect |
Closest papers by meaning
- Revisiting Single Image Reflection Removal In the Wild (CVPR 2024 · similarity 0.89)
- Benchmarking Single-Image Reflection Removal Algorithms (ICCV 2017 · similarity 0.87)
- Removing Reflections from RAW Photos (CVPR 2025 · similarity 0.87)
- FIRM: Flexible Interactive Reflection ReMoval (AAAI 2025 · similarity 0.86)
- Flash-Split: 2D Reflection Removal with Flash Cues and Latent Diffusion Separation (CVPR 2025 · similarity 0.86)
- SIR-DIFF: Sparse Image Sets Restoration with Multi-View Diffusion Model (CVPR 2025 · similarity 0.86)
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.
