mlsanityData to 14 Oct 2026

Leveraging Metric Depth for Relative Depth Prediction

arXiv 2606.10628 ↗First posted 9 Jun 2026cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

We present our solution to the 2025 SoccerNet Monocular Depth Estimation Competition Challenge. Predicting the relative depth in football scenarios is challenging, especially with only thousands of training samples available. To address this issue, our method leverages the powerful zero-shot capabilities of models pretrained on large-scale datasets to learn metric depth for effective relative depth prediction, achieving a score of 2.68 × 10-3 on the challenge set.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 15 of its 21 references that are in the map. First posted on arXiv 9 Jun 2026.

Builds on

15 of 21 references.

References · 15

  1. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  2. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,360
  3. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 657
  4. 2022LocalBins: Improving Depth Estimation by Learning Local Distributionscited by 94
  5. 2024T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Drivingcited by 35
  6. 2023Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Featurecited by 22
  7. 2025Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regressioncited by 21
  8. 2025Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoningcited by 20
  9. 2023Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embeddingcited by 19
  10. 2022RGB-Depth Fusion GAN for Indoor Depth Completioncited by 18
  11. 2025DC-SAM: In-Context Segment Anything in Images and Videos via Dual Consistencycited by 15
  12. 2025SafeDriveRAG: Towards Safe Autonomous Driving with Knowledge Graph-based Retrieval-Augmented Generationcited by 15
3 more
  1. 2025Explainable Action Form Assessment by Exploiting Multimodal Chain-of-Thoughts Reasoningcited by 14
  2. 2025Towards Balanced Multi-Modal Learning in 3D Human Pose Estimationcited by 12
  3. 2023RDFC-GAN: RGB-Depth Fusion CycleGAN for Indoor Depth Completioncited by 7

Built on by

Not cited yet.