UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry

• URL: http://arxiv.org/abs/2509.13713v1
• Date: Wed, 17 Sep 2025 05:51:07 GMT
• Title: UM-Depth : Uncertainty Masked Self-Supervised Monocular Depth Estimation with Visual Odometry
• Authors: Tae-Wook Um, Ki-Hyeon Kim, Hyun-Duck Choi, Hyo-Sung Ahn,
• Abstract summary: We introduce UM-Depth, a framework that combines motion- and uncertainty-aware refinement to enhance depth accuracy.<n>We develop a teacher training strategy that embeds uncertainty estimation into both the training pipeline and network architecture.<n> UM-Depth achieves state-of-the-art results in both self-supervised depth and pose estimation on the KITTI datasets.
• Score: 3.8323580808203785
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Monocular depth estimation has been increasingly adopted in robotics and autonomous driving for its ability to infer scene geometry from a single camera. In self-supervised monocular depth estimation frameworks, the network jointly generates and exploits depth and pose estimates during training, thereby eliminating the need for depth labels. However, these methods remain challenged by uncertainty in the input data, such as low-texture or dynamic regions, which can cause reduced depth accuracy. To address this, we introduce UM-Depth, a framework that combines motion- and uncertainty-aware refinement to enhance depth accuracy at dynamic object boundaries and in textureless regions. Specifically, we develop a teacherstudent training strategy that embeds uncertainty estimation into both the training pipeline and network architecture, thereby strengthening supervision where photometric signals are weak. Unlike prior motion-aware approaches that incur inference-time overhead and rely on additional labels or auxiliary networks for real-time generation, our method uses optical flow exclusively within the teacher network during training, which eliminating extra labeling demands and any runtime cost. Extensive experiments on the KITTI and Cityscapes datasets demonstrate the effectiveness of our uncertainty-aware refinement. Overall, UM-Depth achieves state-of-the-art results in both self-supervised depth and pose estimation on the KITTI datasets.

Related papers

• CurriFlow: Curriculum-Guided Depth Fusion with Optical Flow-Based Temporal Alignment for 3D Semantic Scene Completion [47.47320142811049]
  CurriFlow is a novel semantic occupancy prediction framework that integrates optical flow-based temporal alignment with curriculum-guided depth fusion.<n>We show that CurriFlow achieves state-of-the-art performance with a mean IoU of 16.9, validating the effectiveness of our motion-guided and curriculum-aware design for camera-based 3D semantic scene completion.
  arXiv  Detail & Related papers  (2025-10-14T10:25:26Z)
• Mining Supervision for Dynamic Regions in Self-Supervised Monocular Depth Estimation [23.93080319283679]
  Existing methods jointly estimate pixel-wise depth and motion, relying mainly on an image reconstruction loss. Dynamic regions1 remain a critical challenge for these methods due to the inherent ambiguity in depth and motion estimation. This paper proposes a self-supervised training framework exploiting pseudo depth labels for dynamic regions from training data.
  arXiv  Detail & Related papers  (2024-04-23T10:51:15Z)
• ADU-Depth: Attention-based Distillation with Uncertainty Modeling for Depth Estimation [11.92011909884167]
  We introduce spatial cues by training a teacher network that leverages left-right image pairs as inputs. We apply both attention-adapted feature distillation and focal-depth-adapted response distillation in the training stage. Our experiments on the real depth estimation datasets KITTI and DrivingStereo demonstrate the effectiveness of the proposed method.
  arXiv  Detail & Related papers  (2023-09-26T08:12:37Z)
• SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes [58.89295356901823]
  Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions. We introduce an external pretrained monocular depth estimation model for generating single-image depth prior. Our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes.
  arXiv  Detail & Related papers  (2022-11-07T16:17:47Z)
• Towards Scale-Aware, Robust, and Generalizable Unsupervised Monocular Depth Estimation by Integrating IMU Motion Dynamics [74.1720528573331]
  Unsupervised monocular depth and ego-motion estimation has drawn extensive research attention in recent years. We propose DynaDepth, a novel scale-aware framework that integrates information from vision and IMU motion dynamics. We validate the effectiveness of DynaDepth by conducting extensive experiments and simulations on the KITTI and Make3D datasets.
  arXiv  Detail & Related papers  (2022-07-11T07:50:22Z)
• SelfTune: Metrically Scaled Monocular Depth Estimation through Self-Supervised Learning [53.78813049373321]
  We propose a self-supervised learning method for the pre-trained supervised monocular depth networks to enable metrically scaled depth estimation. Our approach is useful for various applications such as mobile robot navigation and is applicable to diverse environments.
  arXiv  Detail & Related papers  (2022-03-10T12:28:42Z)
• Unsupervised Scale-consistent Depth Learning from Video [131.3074342883371]
  We propose a monocular depth estimator SC-Depth, which requires only unlabelled videos for training. Thanks to the capability of scale-consistent prediction, we show that our monocular-trained deep networks are readily integrated into the ORB-SLAM2 system. The proposed hybrid Pseudo-RGBD SLAM shows compelling results in KITTI, and it generalizes well to the KAIST dataset without additional training.
  arXiv  Detail & Related papers  (2021-05-25T02:17:56Z)
• Unsupervised Monocular Depth Learning with Integrated Intrinsics and Spatio-Temporal Constraints [61.46323213702369]
  This work presents an unsupervised learning framework that is able to predict at-scale depth maps and egomotion. Our results demonstrate strong performance when compared to the current state-of-the-art on multiple sequences of the KITTI driving dataset.
  arXiv  Detail & Related papers  (2020-11-02T22:26:58Z)
• Self-Supervised Joint Learning Framework of Depth Estimation via Implicit Cues [24.743099160992937]
  We propose a novel self-supervised joint learning framework for depth estimation. The proposed framework outperforms the state-of-the-art(SOTA) on KITTI and Make3D datasets.
  arXiv  Detail & Related papers  (2020-06-17T13:56:59Z)
• DeFeat-Net: General Monocular Depth via Simultaneous Unsupervised Representation Learning [65.94499390875046]
  DeFeat-Net is an approach to simultaneously learn a cross-domain dense feature representation. Our technique is able to outperform the current state-of-the-art with around 10% reduction in all error measures.
  arXiv  Detail & Related papers  (2020-03-30T13:10:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.