# Depth Map Super-Resolution on Middlebury Teddy v1 (test) Source: [Depth Map Super-Resolution on Middlebury Teddy v1 (test)]() Collection index: [llms.txt]() Data updated: 2026-02-26T05:57:46.589Z Evaluation of Depth Map Super-Resolution performance using the Middlebury Teddy v1 test set, typically measured by metrics like Percentage of bad pixels. 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 | Depth Map Super-Resolution | | Dataset (including any stated split) | Middlebury Teddy v1 (test) | | Metric | Percentage Bad Pixels (delta=1) | | Unit | PERCENT | | Direction | Lower is better | | Results loaded | 13 of 13 | | 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 - [Percentage Bad Pixels (delta=1)](): Lower is better; unit: PERCENT. ## Recorded results | Method | Percentage Bad Pixels (delta=1) | Result date | Report paper | | --- | --- | --- | --- | | bimodal co-sparse analysis model | 1.41 | Not recorded | 68fa60dc1e209131ce9f191e | | Yang et al. | 2.43 | Not recorded | 68fa60dc1e209131ce9f191e | | Hawe et al. | 2.95 | Not recorded | 68fa60dc1e209131ce9f191e | | bimodal co-sparse analysis model | 3.54 | Not recorded | 68fa60dc1e209131ce9f191e | | Hawe et al. | 4.8 | Not recorded | 68fa60dc1e209131ce9f191e | | nearest-neighbor | 4.97 | Not recorded | 68fa60dc1e209131ce9f191e | | Yang et al. | 5.95 | Not recorded | 68fa60dc1e209131ce9f191e | | bimodal co-sparse analysis model | 6.49 | Not recorded | 68fa60dc1e209131ce9f191e | | nearest-neighbor | 6.71 | Not recorded | 68fa60dc1e209131ce9f191e | | Lu et al. | 9.87 | Not recorded | 68fa60dc1e209131ce9f191e | | nearest-neighbor | 10.9 | Not recorded | 68fa60dc1e209131ce9f191e | | Hawe et al. | 11.4 | Not recorded | 68fa60dc1e209131ce9f191e | | Yang et al. | 11.5 | Not recorded | 68fa60dc1e209131ce9f191e | ### bimodal co-sparse analysis model Percentage Bad Pixels (delta=1): 1.41. Result ID: 698bcaff7a967eddb771646d. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Upscaling factor (d)":"2x"}. This record does not assert independent reproduction. ### Yang et al. Percentage Bad Pixels (delta=1): 2.43. Result ID: 698bcaff7a967eddb771646b. [Reporting paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"2x"}. This record does not assert independent reproduction. ### Hawe et al. Percentage Bad Pixels (delta=1): 2.95. Result ID: 698bcaff7a967eddb771646c. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"2x"}. This record does not assert independent reproduction. ### bimodal co-sparse analysis model Percentage Bad Pixels (delta=1): 3.54. Result ID: 698bcaff7a967eddb7716471. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Upscaling factor (d)":"4x"}. This record does not assert independent reproduction. ### Hawe et al. Percentage Bad Pixels (delta=1): 4.8. Result ID: 698bcaff7a967eddb7716470. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"4x"}. This record does not assert independent reproduction. ### nearest-neighbor Percentage Bad Pixels (delta=1): 4.97. Result ID: 698bcaff7a967eddb771646a. [Reporting paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"2x"}. This record does not assert independent reproduction. ### Yang et al. Percentage Bad Pixels (delta=1): 5.95. Result ID: 698bcaff7a967eddb771646f. [Reporting paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"4x"}. This record does not assert independent reproduction. ### bimodal co-sparse analysis model Percentage Bad Pixels (delta=1): 6.49. Result ID: 698bcaff7a967eddb7716476. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Upscaling factor (d)":"8x"}. This record does not assert independent reproduction. ### nearest-neighbor Percentage Bad Pixels (delta=1): 6.71. Result ID: 698bcaff7a967eddb771646e. [Reporting paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"4x"}. This record does not assert independent reproduction. ### Lu et al. Percentage Bad Pixels (delta=1): 9.87. Result ID: 698bcaff7a967eddb7716474. [Reporting paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"8x"}. This record does not assert independent reproduction. ### nearest-neighbor Percentage Bad Pixels (delta=1): 10.9. Result ID: 698bcaff7a967eddb7716472. [Reporting paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"8x"}. This record does not assert independent reproduction. ### Hawe et al. Percentage Bad Pixels (delta=1): 11.4. Result ID: 698bcaff7a967eddb7716475. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"8x"}. This record does not assert independent reproduction. ### Yang et al. Percentage Bad Pixels (delta=1): 11.5. Result ID: 698bcaff7a967eddb7716473. [Reporting paper]() Recorded evaluation configuration: {"Upscaling factor (d)":"8x"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.