AI Paper Atlas

Research map / Benchmarks / KITTI Eigen

KITTI Eigen leaderboard

11 papers at ICML, NeurIPS, ICLR, CVPR, AAAI, ICCV and ECCV, and the journals TPAMI, IJCV and JMLR report results on KITTI Eigen. Best Abs Rel: 0.015 (PackNet-SAN (RGB+D), CVPR 2021).

Numbers are as each paper reports them, read by AI from its results tables and not checked by hand. Papers can differ in setting (training data, model size, extra data); the topic column shows what each paper is about. Open the paper before you compare or quote a number.

KITTI Eigen · Abs Rel

11 papers, each with its best reported number for its own method; lower is better.

#Abs Rel ↓MethodPaperTopic
10.015PackNet-SAN (RGB+D)
PackNet
Sparse Auxiliary Networks for Unified Monocular Depth Prediction and Completion
CVPR 2021 · Table: Depth estimation result
Depth and stereo
20.037DeepV2DDeepV2D: Video to Depth with Differentiable Structure from Motion
ICLR 2020 · KITTI results table
Video segmentation and tracking
30.041FutureDepth
Dinov2 (ViT-L)
FutureDepth: Learning to Predict the Future Improves Video Depth Estimation
ECCV 2024 · Table 2
Video segmentation and tracking
40.05Ours
Swin-L
Single Image Depth Prediction Made Better: A Multivariate Gaussian Take
CVPR 2023 · Table: KITTI Eigen test
Depth and stereo
50.09DepthFormerMulti-Frame Self-Supervised Depth With Transformers
CVPR 2022 · Table 1
Self-supervised and contrastive
60.096Ours-MD2-Mono
Monodepth2
GeoRefine: Self-Supervised Online Depth Refinement for Accurate Dense Mapping
ECCV 2022 · Appendix KITTI table
Depth and stereo
70.1MonoViT + SCAT
MonoViT
Improving Domain Generalization in Self-Supervised Monocular Depth Estimation via Stabilized Adversarial Training
ECCV 2024 · Table 2
Depth and stereo
80.1SD-SSMDE
ResNet-50
Exploiting Pseudo Labels in a Self-Supervised Learning Framework for Improved Monocular Depth Estimation
CVPR 2022 · Table 6
Self-supervised and contrastive
90.104MonoFormer
ResNet50 + ViT-B/16
Deep Digging into the Generalization of Self-Supervised Monocular Depth Estimation
AAAI 2023 · Table 1
Self-supervised and contrastive
100.105KDBTS
BTS
Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation
CVPR 2024 · Table 2
Depth and stereo
1 more papers on this leaderboard, the baselines reported on it and a CSV download are free with a scime account.
Sign in free to see all

Not affiliated with any conference, journal or the benchmark's authors. Corrections: contact@latenticlabs.com.