Research map / 3D vision / Depth and stereo
Novel View Synthesis of Dynamic Scenes With Globally Coherent Depths From a Monocular Camera
Jae Shin Yoon, Kihwan Kim, Orazio Gallo, Hyun Soo Park, Jan Kautz
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 |
|---|---|---|---|
| Fuse single-view depth with multi-view stereo depth using DFNet | Dynamic scene depth estimation · Dynamic scene dataset, dynamic contents | RMSE: 1.17 m | Improved |
| Use DFNet depth with bidirectional 3D warping | Novel view synthesis · Dynamic scene dataset (average) | perceptual similarity: 0.15 | Improved |
| Use DFNet depth with bidirectional 3D warping | Novel view synthesis · Dynamic scene dataset (average) | optical flow magnitude: 5.3 pixels | Improved |
| Add the DeepBlender refinement after warping (ablation) | DFNet+B3W · Dynamic scene view synthesis | perceptual similarity | Improved |
| Use pixel-wise bidirectional 3D warping instead of grid-wise ASAP warping (ablation) | DFNet view synthesis · Dynamic scene view synthesis | perceptual similarity | Improved |
| Add the static-background depth consistency loss L_g (ablation) | DFNet · Dynamic scene depth estimation | depth accuracy | Improved |
| Add the relative-depth consistency loss L_l (ablation) | DFNet · Dynamic scene depth estimation | dynamic-content depth accuracy | Improved |
| Add the scene-flow loss L_s (ablation) | DFNet · Dynamic scene depth estimation | foreground depth quality | Improved |
| Add the spatial regularization loss L_e (ablation) | DFNet · Dynamic scene depth estimation | foreground depth quality | Improved |
Closest papers by meaning
- View Synthesis of Dynamic Scenes Based on Deep 3D Mask Volume (TPAMI 2023 · similarity 0.89)
- Dense Monocular Depth Estimation in Complex Dynamic Scenes (CVPR 2016 · similarity 0.89)
- Pseudo-Generalized Dynamic View Synthesis from a Video (ICLR 2024 · similarity 0.88)
- Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency (CVPR 2025 · similarity 0.88)
- Depth2Pose: A Pose-Based Benchmark for Monocular Depth Estimation without Ground-Truth Depth (NeurIPS 2026 · similarity 0.87)
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion (CVPR 2025 · 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.
