Research map / 3D vision / NeRF and radiance fields
AligNeRF: High-Fidelity Neural Radiance Fields via Alignment-Aware Training
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 convolution-augmented rendering (ablation) | mip-NeRF 360 · Bicycle 2560×1680, standard and warped test sets | PSNR: 24.17/24.96 -> 24.41/25.20 | Helped |
| Add alignment-aware loss to the convolution-augmented model (ablation) | mip-NeRF 360 · Bicycle 2560×1680, standard and warped test sets | PSNR: 24.41/25.20 -> 24.51/25.45 | Helped |
| Add the first-block VGG high-frequency loss (ablation) | Mip-NeRF 360 + convolution + alignment · Bicycle 2560×1680, standard and warped test sets | PSNR: 24.51/25.45 -> 24.55/25.51 | Helped |
| Use iterative optical-flow warping of training images (ablation) | mip-NeRF 360, 4096 channels · Flowers 2560×1680, warped test set | PSNR: +0.62dB | Helped |
| Use iterative optical-flow warping of training images (ablation) | mip-NeRF 360, 1024 channels · Flowers 2560×1680, warped test set | PSNR: +0.23dB | Helped |
| Increase the NeRF MLP from 1024 to 4096 channels without correcting alignment (ablation) | mip-NeRF 360 · Flowers 2560×1680, standard test set | PSNR: 20.83 -> 21.23 | Helped |
| Apply AligNeRF | mip-NeRF 360 · Outdoor 2560×1680, 1×, standard test set | PSNR: 23.71 -> 23.84 | Helped |
| Apply AligNeRF | mip-NeRF 360 · Outdoor 2560×1680, 4×, warped test set | PSNR: 24.83 -> 25.22 | Helped |
| Apply AligNeRF | mip-NeRF 360 · Outdoor 1280×840 | PSNR: 24.36 -> 24.55 | Helped |
Closest papers by meaning
- Aug-NeRF: Training Stronger Neural Radiance Fields With Triple-Level Physically-Grounded Augmentations (CVPR 2022 · similarity 0.93)
- PyNeRF: Pyramidal Neural Radiance Fields (NeurIPS 2023 · similarity 0.92)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (AAAI 2024 · similarity 0.91)
- Rad-NeRF: Ray-decoupled Training of Neural Radiance Field (NeurIPS 2024 · similarity 0.91)
- InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules (ICLR 2024 · similarity 0.90)
- Joint Optimization of Neural Radiance Fields and Continuous Camera Motion from a Monocular Video (CVPR 2025 · similarity 0.90)
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.