Research map / 3D vision / NeRF and radiance fields
SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image
Xiaoyu Zhou, Zhiwei Lin, Xiaojun Shan, Yongtao Wang, Deqing Sun, Ming-Hsuan Yang
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 |
|---|---|---|---|
| replace Uniform-Fix MPI plane placement with adaptive bins (ablation) | SAMPLING · KITTI city | PSNR: 21.98 -> 23.67 | Improved |
| replace Log-Fix MPI with adaptive bins (ablation) | SAMPLING · KITTI city | PSNR: 22.53 -> 23.67 | Improved |
| add Hierarchical Refinement Branch (ablation) | SAMPLING · KITTI city | PSNR: 22.87 -> 23.67 | Improved |
| add adaptive-bins loss L_ada (ablation) | SAMPLING · KITTI city | PSNR: 22.25 -> 23.67 | Improved |
| increase number of MPI planes from 8 to 64 (ablation) | SAMPLING · KITTI city | PSNR: 20.02 -> 23.67 | Improved |
| increase number of MPI planes from 64 to 128 (ablation) | SAMPLING · KITTI city | PSNR: 23.67 -> 23.68 | No clear effect |
| replace MINE with SAMPLING (single-image MPI baseline) | single-image NVS · KITTI city (N=64) | SSIM: 0.818 -> 0.883 | Improved |
| train on KITTI and test on T&T instead of staying in-domain | SAMPLING vs MINE · Tanks and Temples | PSNR: 21.04 -> 23.56 | Improved |
| SAMPLING vs 3D-Photo (trained on T&T) on cross-dataset PSNR | SAMPLING · Tanks and Temples | PSNR: 23.63 vs 23.56 | No clear effect |
Closest papers by meaning
- WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild (NeurIPS 2025 · similarity 0.86)
- Novel View Synthesis with Pixel-Space Diffusion Models (CVPR 2025 · similarity 0.86)
- Zero-Shot Novel View and Depth Synthesis with Multi-View Geometric Diffusion (CVPR 2025 · similarity 0.86)
- ZeroNVS: Zero-Shot 360-Degree View Synthesis from a Single Image (CVPR 2024 · similarity 0.85)
- MultiDiff: Consistent Novel View Synthesis from a Single Image (CVPR 2024 · similarity 0.85)
- Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day (ICLR 2024 · similarity 0.85)
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.
