Research map / 3D vision / Depth and stereo
A Lightweight Neural Network for Monocular View Generation With Occlusion Handling
Simon Evain, Christine M. Guillemot
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 phase III (refiner and confidence blending) after phases I-II (ablation) | Monocular view synthesis network · KITTI | PSNR disoccluded: 14.85 -> 15.32 | Improved |
| add phase III after phases I-II (ablation) | Monocular view synthesis network · KITTI | PSNR: 18.87 -> 19.24 | Improved |
| add phase II (structure refinement) before phase III (ablation) | Monocular view synthesis network · KITTI | LPIPS: 0.206 -> 0.139 | Improved |
| add phase II to phase I (ablation) | Monocular view synthesis network · KITTI | PSNR disoccluded: 14.84 -> 14.85 | No clear effect |
| use staged training schedule instead of end-to-end training (ablation) | Monocular view synthesis network · KITTI | LPIPS: 0.345 -> 0.139 | Improved |
| use staged training schedule instead of end-to-end training (ablation) | Monocular view synthesis network · KITTI | PSNR: 19.23 -> 19.24 | No clear effect |
| add forward-backward confidence constraint on blending weights (ablation) | Monocular view synthesis network · KITTI | LPIPS: 0.190 -> 0.139 | Improved |
| add forward-backward confidence constraint on blending weights (ablation) | Monocular view synthesis network · KITTI | PSNR: 19.40 -> 19.24 | Hurt |
| add forward-backward confidence constraint on blending weights (ablation) | Monocular view synthesis network · KITTI | SSIM: 0.75 -> 0.74 | Hurt |
| add phase I-II-III schedule with refiner to disparity-only prediction (ablation) | Monocular view synthesis network · KITTI | PSNR: 18.76 -> 19.24 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- Deep3D — Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks (ECCV 2016) · better on 3 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Unsupervised Monocular Depth Estimation With Left-Right Consistency (CVPR 2017 · similarity 0.89)
- Single View Stereo Matching (CVPR 2018 · similarity 0.89)
- Learning Stereo from Single Images (ECCV 2020 · similarity 0.88)
- DeepMVS: Learning Multi-View Stereopsis (CVPR 2018 · similarity 0.88)
- MVS2D: Efficient Multi-View Stereo via Attention-Driven 2D Convolutions (CVPR 2022 · similarity 0.88)
- One View Is Enough: In-the-Wild Monocular Pretraining for Novel View Generation (NeurIPS 2026 · similarity 0.87)
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.
