Novel View Extrapolation Eval

---
name: novel-view-extrapolation-eval
description: Evaluates a neural radiance field's ability to synthesize high-quality, artifact-free images of solid objects from viewpoints significantly outside the training camera distribution (novel view extrapolation). Use when the user wants to benchmark on Synthetic-NeRF*, MobileObject, or asks about evaluating this task. Reports PSNR.
metadata:
  skill_kind: dataset_eval
  source_arxiv: 2205.05922
  bibtex_key: [REDACTED]
  confidence: high
---

# novel-view-extrapolation-eval

> Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation — Zhang et al. (2022) (CVPR 2022, 2022)

## What this evaluates

Evaluates a neural radiance field's ability to synthesize high-quality, artifact-free images of solid objects from viewpoints significantly outside the training camera distribution (novel view extrapolation).

## Datasets

- **Synthetic-NeRF*** — total 300; splits: train (100), test (200)
- **MobileObject** — total ?; splits: train (100), test (-1)

## Metrics

- `PSNR` **(primary)** — range: other (dB)
  - Peak Signal-to-Noise Ratio computed in decibels (dB) between the rendered and ground truth images.
- `SSIM` — range: [0, 1]
  - Structural Similarity Index measuring perceived structural similarity between the rendered and ground truth images.
- `LPIPS` — range: [0, 1]
  - Learned Perceptual Image Patch Similarity measuring perceptual difference using a pre-trained network.

## Input / output format

**Input**: A set of training images with corresponding camera poses (intrinsics and extrinsics) for a single object.

**Output**: Rendered RGB images for each test camera pose.

## Scoring recipe

```python
def evaluate(rendered_imgs, gt_imgs):
    psnr_scores = [compute_psnr(r, g) for r, g in zip(rendered_imgs, gt_imgs)]
    ssim_scores = [compute_ssim(r, g) for r, g in zip(rendered_imgs, gt_imgs)]
    lpips_scores = [compute_lpips(r, g) for r, g in zip(rendered_imgs, gt_imgs)]
    return {
        'PSNR': np.mean(psnr_scores),
        'SSIM': np.mean(ssim_scores),
        'LPIPS': np.mean(lpips_scores)
    }
```

## Common pitfalls

- Novel view extrapolation requires testing on viewpoints far from the training distribution, not just interpolation.
- Camera pose errors significantly degrade performance for some baselines (e.g., NSVF), so accurate COLMAP reconstruction is critical.
- Metrics should be averaged per object and then across objects, as dataset sizes vary.

## Evidence (verbatim from paper)

> We use PSNR, SSIM [[43]], and LPIPS [[54]] to measure the rendering quality. As reported in Table 1, RapNeRF obtains the best performance on all metrics for novel view extrapolation.

## Citation

```bibtex
@misc{zhang2022raypriors,
  title={Ray Priors through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation},
  author={Zhang et al. (2022)},
  year={2022},
  note={CVPR 2022}
}
```

- arXiv: 2205.05922