Research map / 3D vision / NeRF and radiance fields
Deep 3D Mask Volume for View Synthesis of Dynamic Scenes
Kai-En Lin, Lei Xiao, Feng Liu, Guowei Yang, Ravi Ramamoorthi
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 |
|---|---|---|---|
| use 3D mask volume instead of per-frame MPI/LLFF | MPI/LLFF · Multi-view video dataset eval (14 clips, 2-view input) | STRRED: 0.2917 -> 0.1683 | Improved |
| use 3D mask volume instead of per-frame MPI/LLFF | MPI/LLFF · Multi-view video dataset eval (14 clips, 2-view input) | PSNR: 25.52 -> 26.22 | Improved |
| use 3D mask volume instead of 2D mask (ablation) | MPI blending · Multi-view video dataset eval (14 clips, 2-view input) | STRRED: 0.2892 -> 0.1683 | Improved |
| add 2D mask blending to MPI/LLFF | MPI/LLFF · Multi-view video dataset eval (14 clips, 2-view input) | STRRED: 0.2917 -> 0.2892 | No clear effect |
| add 2D mask blending to MPI/LLFF | MPI/LLFF · Multi-view video dataset eval (14 clips, 2-view input) | PSNR: 25.52 -> 25.50 | Hurt |
| use 3D mask volume instead of 2D mask (ablation) | MPI blending · Multi-view video dataset eval (14 clips, 2-view input) | PSNR: 25.50 -> 26.22 | Improved |
| add mask sparsity loss Ls (ablation) | 3D mask volume · Loss function ablation (our eval set) | STRRED: 0.1683 -> 0.1745 | Hurt |
| add mask sparsity loss Ls and mask supervision loss Lm (ablation) | 3D mask volume · Loss function ablation (our eval set) | STRRED: 0.1683 -> 0.1900 | Hurt |
| add mask sparsity loss Ls (ablation) | 3D mask volume · Loss function ablation (our eval set) | PSNR: 26.22 -> 26.18 | Hurt |
| add Ls and Lm losses (ablation) | 3D mask volume · Loss function ablation (our eval set) | SSIM: 0.8390 -> 0.8374 | Hurt |
Closest papers by meaning
- MVSplat360: Feed-Forward 360 Scene Synthesis from Sparse Views (NeurIPS 2024 · similarity 0.87)
- Geometry-guided Online 3D Video Synthesis with Multi-View Temporal Consistency (CVPR 2025 · similarity 0.86)
- DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision (CVPR 2024 · similarity 0.86)
- Video Perception Models for 3D Scene Synthesis (NeurIPS 2025 · similarity 0.86)
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos (NeurIPS 2025 · similarity 0.86)
- Pseudo-Generalized Dynamic View Synthesis from a Video (ICLR 2024 · 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.
