mlsanityData to 14 Oct 2026

Towards Sharper Object Boundaries in Self-Supervised Depth Estimation

arXiv 2509.15987 ↗First posted 19 Sep 2025cs.CV cs.AI cs.ROcited by 1

Not on the map. Why?

Abstract (arXiv)

Accurate monocular depth estimation is crucial for 3D scene understanding, but existing methods often blur depth at object boundaries, introducing spurious intermediate 3D points. While achieving sharp edges usually requires very fine-grained supervision, our method produces crisp depth discontinuities using only self-supervision. Specifically, we model per-pixel depth as a mixture distribution, capturing multiple plausible depths and shifting uncertainty from direct regression to the mixture weights. This formulation integrates seamlessly into existing pipelines via variance-aware loss functions and uncertainty propagation. Extensive evaluations on KITTI and VKITTIv2 show that our method achieves up to 35% higher boundary sharpness and improves point cloud quality compared to state-of-the-art baselines.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 19 Sep 2025.

Builds on

29 of 40 references.

References · 29

  1. 2022A ConvNet for the 2020scited by 3,579
  2. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  3. 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,274
  4. 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 820
  5. 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 782
  6. 2020AdaBins: Depth Estimation using Adaptive Binscited by 601
  7. 20193D Packing for Self-Supervised Monocular Depth Estimationcited by 439
  8. 2024Depth Pro: Sharp Monocular Metric Depth in Less Than a Secondcited by 404
  9. 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
  10. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 341
  11. 2017Sparsity Invariant CNNscited by 326
  12. 2020On the uncertainty of self-supervised monocular depth estimationcited by 182
17 more
  1. 2018Unsupervised Learning of Monocular Depth Estimation and Visual Odometry with Deep Feature Reconstructioncited by 159
  2. 2020Feature-metric Loss for Self-supervised Learning of Depth and Egomotioncited by 140
  3. 2022MonoViT: Self-Supervised Monocular Depth Estimation with a Vision Transformercited by 136
  4. 2021SMD-Nets: Stereo Mixture Density Networkscited by 120
  5. 2020Self-supervised Monocular Trained Depth Estimation using Self-attention and Discrete Disparity Volumecited by 116
  6. 2020HR-Depth: High Resolution Self-Supervised Monocular Depth Estimationcited by 115
  7. 2022Lite-Mono: A Lightweight CNN and Transformer Architecture for Self-Supervised Monocular Depth Estimationcited by 100
  8. 2018Layer-structured 3D Scene Inference via View Synthesiscited by 82
  9. 2021Self-Supervised Monocular Depth Estimation with Internal Feature Fusioncited by 67
  10. 2018SuperDepth: Self-Supervised, Super-Resolved Monocular Depth Estimationcited by 64
  11. 2019Reliable training and estimation of variance networkscited by 63
  12. 2021Channel-Wise Attention-Based Network for Self-Supervised Monocular Depth Estimationcited by 63
  13. 2022PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planescited by 32
  14. 2022Self-Supervised Monocular Depth Estimation: Solving the Edge-Fattening Problemcited by 20
  15. 2022Deconstructing Self-Supervised Monocular Reconstruction: The Design Decisions that Mattercited by 18
  16. 2022MonoDVPS: A Self-Supervised Monocular Depth Estimation Approach to Depth-aware Video Panoptic Segmentationcited by 7
  17. 2024GroCo: Ground Constraint for Metric Self-Supervised Monocular Depthcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026MoE3D: A Mixture-of-Experts Module for 3D Reconstructioncited by 4