# HDR on ImageNet 256

Source: [HDR on ImageNet 256](<https://www.sota2.com/research/sota/hdr-on-imagenet-256>)

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

Data updated: 2026-05-22T06:55:52.266Z

Evaluation of High Dynamic Range (HDR) processing performance on the ImageNet 256 subset, measured using latency (Time (s)), LPIPS, and FID.

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 | HDR |
| Dataset (including any stated split) | ImageNet 256 |
| Metric | Latency (s) |
| Unit | TIME |
| Direction | Lower is better |
| Results loaded | 7 of 7 |
| 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

- [Latency (s)](<https://www.sota2.com/research/sota/hdr-on-imagenet-256.md?metric=Latency%20(s)>): Lower is better; unit: TIME.

- [LPIPS](<https://www.sota2.com/research/sota/hdr-on-imagenet-256.md?metric=LPIPS>): Lower is better; unit: SCALAR.

- [FID](<https://www.sota2.com/research/sota/hdr-on-imagenet-256.md?metric=FID>): Lower is better; unit: SCALAR.

## Recorded results

| Method | Latency (s) | Result date | Report paper |
| --- | --- | --- | --- |
| RED-Diff | 0.7 | Not recorded | 6a0fe2ebf984739ed6739c1c |
| HyperNoise | 1.3 | Not recorded | 6a0fe2ebf984739ed6739c1c |
| AHVP | 1.3 | Not recorded | 6a0fe2ebf984739ed6739c1c |
| NDTM | 5.8 | Not recorded | 6a0fe2ebf984739ed6739c1c |
| SHVP | 5.8 | Not recorded | 6a0fe2ebf984739ed6739c1c |
| DAPS | 30.9 | Not recorded | 6a0fe2ebf984739ed6739c1c |
| DPS | 46.7 | Not recorded | 6a0fe2ebf984739ed6739c1c |

### RED-Diff

Latency (s): 0.7. Result ID: 6a0ffda5fbc373592c085b03.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2ebf984739ed6739c1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa5af61e209131ce9c4296.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### HyperNoise

Latency (s): 1.3. Result ID: 6a0ffda5fbc373592c085b05.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2ebf984739ed6739c1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7a911e209131cea83f31.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### AHVP

Latency (s): 1.3. Result ID: 6a0ffda5fbc373592c085b06.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2ebf984739ed6739c1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe2ebf984739ed6739c1c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### NDTM

Latency (s): 5.8. Result ID: 6a0ffda5fbc373592c085b02.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2ebf984739ed6739c1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa78c51e209131cea7a67e.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### SHVP

Latency (s): 5.8. Result ID: 6a0ffda5fbc373592c085b07.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2ebf984739ed6739c1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/6a0fe2ebf984739ed6739c1c.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DAPS

Latency (s): 30.9. Result ID: 6a0ffda5fbc373592c085b01.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2ebf984739ed6739c1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7aa31e209131cea84481.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

### DPS

Latency (s): 46.7. Result ID: 6a0ffda5fbc373592c085b04.

[Reporting paper](<https://www.sota2.com/research/paper/6a0fe2ebf984739ed6739c1c.md>)

[Method origin paper](<https://www.sota2.com/research/paper/68fa7bdd1e209131cea8adbc.md>)

Recorded evaluation configuration: Not recorded. This record does not assert independent reproduction.

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