# Surface Normal Estimation on Omnidata pseudo ground truth v2

Source: [Surface Normal Estimation on Omnidata pseudo ground truth v2](<https://www.sota2.com/research/sota/surface-normal-estimation-on-omnidata-pseudo-ground-truth-v2>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-02-26T05:47:57.662Z

Evaluation of Surface Normal Estimation performance on the Omnidata pseudo ground truth v2 dataset, typically measured using L1 error and Angular Error.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Surface Normal Estimation |
| Dataset (including any stated split) | Omnidata pseudo ground truth v2 |
| Metric | L1 Error |
| Unit | SCALAR |
| Direction | Lower is better |
| Results loaded | 4 of 4 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [L1 Error](<https://www.sota2.com/research/sota/surface-normal-estimation-on-omnidata-pseudo-ground-truth-v2.md?metric=L1%20Error>): Lower is better; unit: SCALAR.

- [Angular Error](<https://www.sota2.com/research/sota/surface-normal-estimation-on-omnidata-pseudo-ground-truth-v2.md?metric=Angular%20Error>): Lower is better; unit: SCALAR.

## Recorded results

| Method | L1 Error | Result date | Report paper |
| --- | --- | --- | --- |
| Omnidata-v1 | 0.0501 | Not recorded | 68fa6f8e1e209131cea4636d |
| X-task consistency | 0.0502 | Not recorded | 68fa6f8e1e209131cea4636d |
| X-task baseline | 0.0511 | Not recorded | 68fa6f8e1e209131cea4636d |
| StyleGAN | 0.0834 | Not recorded | 68fa6f8e1e209131cea4636d |

### Omnidata-v1

L1 Error: 0.0501. Result ID: 6990c9f83a6c314849034b95.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea4636d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6afe1e209131cea2b9b2.md>)

Recorded evaluation configuration: {"#Parameters":"75.1M"}. This record does not assert independent reproduction.

### X-task consistency

L1 Error: 0.0502. Result ID: 6990c9f83a6c314849034b96.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea4636d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ab1e209131cea17a3d.md>)

Recorded evaluation configuration: {"#Parameters":"75.5M"}. This record does not assert independent reproduction.

### X-task baseline

L1 Error: 0.0511. Result ID: 6990c9f83a6c314849034b97.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea4636d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa67ab1e209131cea17a3d.md>)

Recorded evaluation configuration: {"#Parameters":"75.5M"}. This record does not assert independent reproduction.

### StyleGAN

L1 Error: 0.0834. Result ID: 6990c9f83a6c314849034b98.

[Reporting paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea4636d.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa6f8e1e209131cea4636d.md>)

Recorded evaluation configuration: {"#Parameters":"24.7M","zero-shot":true}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.