Research map / 3D vision / NeRF and radiance fields
MINE: Towards Continuous Depth MPI With NeRF for Novel View Synthesis
Jiaxin Li, Zijian Feng, Qi She, Henghui Ding, Changhu Wang, Gim Hee Lee
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 ImageNet pre-training of the encoder (ablation) | MINE N=32 · KITTI | PSNR: 21.4 -> 21.6 | Improved |
| add ImageNet pre-training of the encoder (ablation) | MINE N=32 · KITTI | LPIPS: 0.129 -> 0.122 | Improved |
| add edge-aware depth smoothness loss (ablation) | MINE N=32 · KITTI | PSNR: 21.6 -> 21.6 | No clear effect |
| add edge-aware depth smoothness loss (ablation) | MINE N=32 · KITTI | LPIPS: 0.123 -> 0.122 | Improved |
| increase number of planes N from 32 to 256 (ablation) | MINE (train 384x128) · KITTI | SSIM: 0.815 -> 0.828 | Improved |
| increase number of planes N from 32 to 256 (ablation) | MINE (train 384x128) · KITTI | LPIPS: 0.122 -> 0.112 | Improved |
| increase number of planes N from 32 to 256 (ablation) | MINE (train 384x128) · KITTI | PSNR: 21.6 -> 21.9 | Improved |
| increase number of planes N from 32 to 64 (ablation) | MINE (train 768x256) · KITTI | PSNR: 21.4 -> 21.3 | No clear effect |
| increase number of planes N from 32 to 64 (ablation) | MINE · RealEstate10K (random target) | LPIPS: 0.1674 -> 0.1562 | Improved |
| increase number of planes N from 32 to 64 (ablation) | MINE · RealEstate10K (random target) | PSNR: 24.56 -> 24.50 | No clear effect |
| increase number of planes N from 32 to 64 (ablation) | MINE · Flowers Light Fields | PSNR: 30.2 -> 30.3 | Improved |
| replace discrete-plane MPI with continuous-depth MINE | MPI · RealEstate10K (random target) | PSNR: 23.52 -> 24.56 | 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.
- SynSin — SynSin: End-to-End View Synthesis From a Single Image (CVPR 2020) · better on 1 of 1 shared result
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
- Dense Depth Priors for Neural Radiance Fields From Sparse Input Views (CVPR 2022 · similarity 0.90)
- Depth-Guided Optimization of Neural Radiance Fields for Indoor Multi-View Stereo (TPAMI 2023 · similarity 0.90)
- NerfingMVS: Guided Optimization of Neural Radiance Fields for Indoor Multi-View Stereo (ICCV 2021 · similarity 0.90)
- SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis (ICCV 2023 · similarity 0.89)
- DäRF: Boosting Radiance Fields from Sparse Input Views with Monocular Depth Adaptation (NeurIPS 2023 · similarity 0.89)
- NeRFPrior: Learning Neural Radiance Field as a Prior for Indoor Scene Reconstruction (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.
