Monocular Depth Estimation on MVSEC Depth
5.554RMSEScaleEvent
Evaluation results
| Method | Links | ||||||
|---|---|---|---|---|---|---|---|
| ScaleEventPresent at=-, Backbone=ViT-L/16, Initialization/Pre-training strategy=Event Pretraining + Fully-Supervised2026.03 | 5.554 | 62.5 | 83.4 | 93.4 | 26.8 | 0.343 | |
| ScaleEventPresent at=-, Backbone=ViT-B/16, Initialization/Pre-training strategy=Event Pretraining + Fully-Supervised2026.03 | 5.891 | 59.4 | 81.1 | 92.2 | 28 | 0.364 | |
| ScaleEventBackbone=ViT-S/16, Learning configuration=Full2026.03 | 6.145 | — | — | — | — | — | |
| ScaleEventPresent at=-, Backbone=ViT-S/16, Initialization/Pre-training strategy=Event Pretraining + Fully-Supervised2026.03 | 6.145 | 57.7 | 80 | 91.4 | 28.9 | 0.378 | |
| ScaleEventBackbone=ViT-S/16, Learning configuration=20%2026.03 | 6.352 | — | — | — | — | — | |
| DepthAnyEvent-RBackbone=ViT-S/16, Learning configuration=Full2026.03 | 6.465 | — | — | — | — | — | |
| DepthAnyEvent-RPresent at=ICCV’25, Backbone=ViT-S/16, Initialization/Pre-training strategy=Event Pretraining + Fully-Supervised2026.03 | 6.465 | 48.9 | 75.1 | 87.8 | 36.5 | 0.483 | |
| ScaleEventBackbone=ViT-S/16, Learning configuration=10%2026.03 | 6.477 | — | — | — | — | — | |
| DepthAnyEvent-RBackbone=ViT-S/16, Learning configuration=20%2026.03 | 6.637 | — | — | — | — | — | |
| ScaleEventBackbone=ViT-S/16, Learning configuration=5%2026.03 | 6.712 | — | — | — | — | — | |
| ScaleEventBackbone=ViT-S/16, Learning configuration=LP2026.03 | 6.756 | — | — | — | — | — | |
| DepthAnyEvent-RBackbone=ViT-S/16, Learning configuration=10%2026.03 | 6.794 | — | — | — | — | — | |
| ScaleEventBackbone=ViT-S/16, Learning configuration=1%2026.03 | 6.93 | — | — | — | — | — | |
| ECDDPPresent at=ECCV’24, Backbone=ViT-S/16, Initialization/Pre-training strategy=Event Pretraining + Fully-Supervised2026.03 | 6.957 | 51.3 | 76.2 | 87.1 | 42.8 | 0.469 | |
| DepthAnyEvent-RBackbone=ViT-S/16, Learning configuration=5%2026.03 | 7.261 | — | — | — | — | — | |
| E2DepthPresent at=3DV’20, Backbone=ResNet-18, Initialization/Pre-training strategy=RGB initialization + Fully-Supervised2026.03 | 7.268 | 43.2 | 71.7 | 86.8 | 42 | 0.455 | |
| DepthAnyEvent-RBackbone=ViT-S/16, Learning configuration=LP2026.03 | 7.473 | — | — | — | — | — | |
| DepthAnyEvent-RBackbone=ViT-S/16, Learning configuration=1%2026.03 | 7.542 | — | — | — | — | — | |
| ECDPPresent at=ICCV’23, Backbone=ViT-S/16, Initialization/Pre-training strategy=Event Pretraining + Fully-Supervised2026.03 | 7.68 | 47.6 | 77.2 | 86.3 | 49.6 | 0.506 | |
| EReFormerPresent at=TVSVT’24, Backbone=Swin-T, Initialization/Pre-training strategy=RGB initialization + Fully-Supervised2026.03 | 8.373 | 39.1 | 65.2 | 81 | 55.1 | 0.523 |