# Stereo Matching on KITTI Stereo deterministic held-out 2015 (train) Source: [Stereo Matching on KITTI Stereo deterministic held-out 2015 (train)]() Collection index: [llms.txt]() Data updated: 2026-03-31T10:31:07.625Z Evaluation of Stereo Matching performance on the specific 'deterministic held-out' training split of the KITTI 2015 dataset, measured using Top-N accuracy and Ground Truth EPE metrics (WTA and SGM). 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 | Stereo Matching | | Dataset (including any stated split) | KITTI Stereo deterministic held-out 2015 (train) | | Metric | Top-1 Accuracy | | Unit | PERCENT | | Direction | Higher is better | | Results loaded | 6 of 6 | | 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 - [Top-1 Accuracy](): Higher is better; unit: PERCENT. - [Top-5 Accuracy](): Higher is better; unit: PERCENT. - [EPE (WTA)](): Lower is better; unit: SCALAR. - [EPE (SGM)](): Lower is better; unit: SCALAR. ## Recorded results | Method | Top-1 Accuracy | Result date | Report paper | | --- | --- | --- | --- | | OURS | 70 | Not recorded | 69cb55340636e5bf4afca07c | | CroCo-v2 | 68.3 | Not recorded | 69cb55340636e5bf4afca07c | | DINOv3-style | 55 | Not recorded | 69cb55340636e5bf4afca07c | | CroCo-v1 | 35 | Not recorded | 69cb55340636e5bf4afca07c | | iBOT-style | 18.3 | Not recorded | 69cb55340636e5bf4afca07c | | DINOv2-style | 16.7 | Not recorded | 69cb55340636e5bf4afca07c | ### OURS Top-1 Accuracy: 70. Result ID: 69cba1d547f34ce924b48e3d. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pretraining recipe":"low-resource"}. This record does not assert independent reproduction. ### CroCo-v2 Top-1 Accuracy: 68.3. Result ID: 69cba1d547f34ce924b48e3f. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Positional Encoding":"RoPE","Pretraining recipe":"low-resource"}. This record does not assert independent reproduction. ### DINOv3-style Top-1 Accuracy: 55. Result ID: 69cba1d547f34ce924b48e42. [Reporting paper]() [Method origin paper]() Recorded evaluation configuration: {"Pretraining recipe":"low-resource"}. This record does not assert independent reproduction. ### CroCo-v1 Top-1 Accuracy: 35. Result ID: 69cba1d547f34ce924b48e3e. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Positional Encoding":"sincos","Pretraining recipe":"low-resource"}. This record does not assert independent reproduction. ### iBOT-style Top-1 Accuracy: 18.3. Result ID: 69cba1d547f34ce924b48e40. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining recipe":"low-resource"}. This record does not assert independent reproduction. ### DINOv2-style Top-1 Accuracy: 16.7. Result ID: 69cba1d547f34ce924b48e41. [Reporting paper]() [Method origin paper]() [Implementation]() Recorded evaluation configuration: {"Pretraining recipe":"low-resource"}. This record does not assert independent reproduction. Page 1 of 1. This is an index page, not the full collection.