Monocular Depth Estimation On Kitti Eigen
Metrics
absolute relative error
Results
Performance results of various models on this benchmark
Comparison Table
| Model Name | absolute relative error |
|---|---|
| competitive-collaboration-joint-unsupervised | 0.140 |
| adaptive-fusion-of-single-view-and-multi-view | 0.044 |
| signet-semantic-instance-aided-unsupervised | 0.133 |
| primedepth-efficient-monocular-depth | 0.079 |
| vision-transformers-for-dense-prediction | 0.062 |
| enforcing-geometric-constraints-of-virtual | 0.072 |
| unik3d-universal-camera-monocular-3d | 0.037 |
| dinov2-learning-robust-visual-features | 0.0652 |
| mamo-leveraging-memory-and-attention-for | 0.049 |
| d-net-a-generalised-and-optimised-deep | 0.056 |
| ecodepth-effective-conditioning-of-diffusion | 0.048 |
| evp-enhanced-visual-perception-using-inverse | 0.048 |
| global-local-path-networks-for-monocular | 0.057 |
| scaledepth-decomposing-metric-depth | 0.048 |
| learning-monocular-depth-estimation-with | 0.126 |
| dipe-deeper-into-photometric-errors-for | 0.112 |
| adabins-depth-estimation-using-adaptive-bins | 0.058 |
| geometry-aware-symmetric-domain-adaptation | 0.149 |
| repurposing-diffusion-based-image-generators | 0.099 |
| mgdepth-motion-guided-cost-volume-for-self | 0.091 |
| attention-attention-everywhere-monocular | 0.051 |
| deep-ordinal-regression-network-for-monocular | 0.072 |
| depth-prediction-without-the-sensors | 0.135 |
| unsupervised-scale-consistent-depth-and-ego | 0.137 |
| iebins-iterative-elastic-bins-for-monocular-1 | 0.050 |
| unsupervised-scale-consistent-depth-learning | 0.119 |
| revealing-the-dark-secrets-of-masked-image | 0.052 |
| single-image-depth-estimation-trained-via-1 | 0.110 |
| learning-to-recover-3d-scene-shape-from-a | 0.149 |
| learn-stereo-infer-mono-siamese-networks-for | 0.113 |
| depth-anything-unleashing-the-power-of-large | 0.046 |
| metric3d-v2-a-versatile-monocular-geometric-1 | 0.039 |
| monocular-depth-estimation-using-laplacian | 0.059 |
| on-deep-learning-techniques-to-boost | 0.075 |
| nddepth-normal-distance-assisted-monocular | 0.050 |
| the-devil-is-in-the-labels-semantic | 0.14 |
| idisc-internal-discretization-for-monocular | 0.050 |
| lighteddepth-video-depth-estimation-in-light | 0.041 |
| deep-two-view-structure-from-motion-revisited | 0.055 |
| revealing-the-dark-secrets-of-masked-image | 0.050 |
| high-quality-monocular-depth-estimation-via | 0.093 |
| analysis-of-nan-divergence-in-training | 0.0508 |
| unidepthv2-universal-monocular-metric-depth | 0.037 |
| harnessing-diffusion-models-for-visual | 0.047 |
| unidepth-universal-monocular-metric-depth | 0.042 |
| unsupervised-scale-consistent-depth-and-ego | 0.128 |
| semi-supervised-monocular-depth-estimation | 0.096 |
| monocular-depth-estimation-through-virtual | 0.053 |
| urcdc-depth-uncertainty-rectified-cross | 0.050 |
| depthformer-exploiting-long-range-correlation | 0.052 |
| structure-attentioned-memory-network-for | 0.097 |
| monocular-depth-estimation-by-learning-from | 0.096 |
| depthformer-multiscale-vision-transformer-for | 0.058 |
| learning-monocular-depth-estimation-infusing | 0.096 |
| metric3d-towards-zero-shot-metric-3d | 0.058 |
| enhancing-self-supervised-monocular-depth | 0.091 |
| focal-wnet-an-architecture-unifying | 0.082 |
| self-supervised-learning-for-single-view | 0.133 |
| toward-hierarchical-self-supervised-monocular | 0.113 |
| spidepth-strengthened-pose-information-for | 0.029 |
| primedepth-efficient-monocular-depth | 0.073 |
| digging-into-self-supervised-monocular-depth | 0.106 |
| nvs-monodepth-improving-monocular-depth | 0.057 |
| binsformer-revisiting-adaptive-bins-for | 0.052 |
| gcndepth-self-supervised-monocular-depth | 0.104 |
| sqldepth-generalizable-self-supervised-fine | 0.043 |
| veritatem-dies-aperit-temporally-consistent | 0.193 |
| lightdepth-a-resource-efficient-depth | 0.070 |
| from-big-to-small-multi-scale-local-planar | 0.064 |
| new-crfs-neural-window-fully-connected-crfs-1 | 0.052 |
| towards-scene-understanding-unsupervised | 0.118 |
| ddp-diffusion-model-for-dense-visual | 0.050 |
| unsupervised-scale-consistent-depth-learning | 0.114 |
| depthmaster-taming-diffusion-models-for | 0.082 |
| gedepth-ground-embedding-for-monocular-depth | 0.048 |
| single-view-stereo-matching | 0.094 |
| futuredepth-learning-to-predict-the-future | 0.041 |
| packnet-sfm-3d-packing-for-self-supervised | 0.12 |
| self-supervised-monocular-depth-hints | 0.096 |