SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation

• URL: http://arxiv.org/abs/2605.28477v1
• Date: Wed, 27 May 2026 13:38:25 GMT
• Title: SA4Depth: Consistent Pose-Depth Scale Alignment for Self-Supervised Monocular Depth Estimation
• Abstract summary: Self-supervised depth estimation from monocular sequences relies on the joint learning of a depth and a pose network.<n>We introduce SA4Depth, an approach to improve the alignment between the scene scales estimated by the pose and depth nets.<n>Our proposed method uses the depth estimated during training to reproject learnable visual features across consecutive frames.
• Score: 76.82232244682113
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Self-supervised depth estimation from monocular sequences relies on the joint learning of a depth and a pose network. Despite abundant research done to improve the depth network, efforts on the pose remain limited. In this context, even when depth is estimated up to scale, we highlight the importance of the alignment between the scene scales estimated by the pose and depth nets. Then, we introduce SA4Depth, an approach to improve this alignment and boost the depth predictions while keeping the inference time unchanged. Our proposed method uses the depth estimated during training to reproject learnable visual features across consecutive frames and refine the pose estimates by reducing feature alignment residuals. With our method, the estimated scene scales by the separate depth and pose networks are aligned, and the prediction scale consistency is improved across different sequences. Our differentiable refinement integrates seamlessly into existing self-supervised pipelines and substantially improves their depth estimates. We demonstrate this with extensive experiments both outdoors and indoors on KITTI, Cityscapes, and NYUv2. Additionally, results on KITTI Odometry confirm the effectiveness of our pose refinement. Our code is available at https://github.com/Runningchauncey/SA4Depth .

Related papers

• PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistency [5.854654986365097]
  Existing approaches often struggle to maintain temporal consistency in depth estimation across consecutive frames.<n>This paper proposes a consistency-aware monocular depth estimation framework that leverages wheel odometry from a mobile robot to achieve stable and coherent depth predictions over time.<n>The proposed method is evaluated on the KITTI, TartanAir, and our own dataset, demonstrating robust and accurate depth estimation performance.
  arXiv  Detail & Related papers  (2026-04-02T09:03:02Z)
• Metric-Solver: Sliding Anchored Metric Depth Estimation from a Single Image [51.689871870692194]
  Metric-r is a novel sliding anchor-based metric depth estimation method.<n>Our design enables a unified and adaptive depth representation across diverse environments.
  arXiv  Detail & Related papers  (2025-04-16T14:12:25Z)
• Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion [57.08169927189237]
  Existing methods for depth completion operate in tightly constrained settings.<n>Inspired by advances in monocular depth estimation, we reframe depth completion as an image-conditional depth map generation.<n>Marigold-DC builds on a pretrained latent diffusion model for monocular depth estimation and injects the depth observations as test-time guidance.
  arXiv  Detail & Related papers  (2024-12-18T00:06:41Z)
• ScaleDepth: Decomposing Metric Depth Estimation into Scale Prediction and Relative Depth Estimation [62.600382533322325]
  We propose a novel monocular depth estimation method called ScaleDepth. Our method decomposes metric depth into scene scale and relative depth, and predicts them through a semantic-aware scale prediction module. Our method achieves metric depth estimation for both indoor and outdoor scenes in a unified framework.
  arXiv  Detail & Related papers  (2024-07-11T05:11:56Z)
• Self-Supervised Learning based Depth Estimation from Monocular Images [0.0]
  The goal of Monocular Depth Estimation is to predict the depth map, given a 2D monocular RGB image as input. We plan to do intrinsic camera parameters during training and apply weather augmentations to further generalize our model.
  arXiv  Detail & Related papers  (2023-04-14T07:14:08Z)
• DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium [11.78276690882616]
  Self-supervised multi-frame depth estimation achieves high accuracy by computing matching costs of pixel correspondences between adjacent frames. We propose the Dual model, which tightly couples depth and pose estimation through a feedback loop. Our novel update pipeline uses a deep equilibrium model framework to iteratively refine depth estimates and a hidden state of feature maps.
  arXiv  Detail & Related papers  (2023-04-07T09:46:29Z)
• 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)
• Towards 3D Scene Reconstruction from Locally Scale-Aligned Monocular Video Depth [90.33296913575818]
  In some video-based scenarios such as video depth estimation and 3D scene reconstruction from a video, the unknown scale and shift residing in per-frame prediction may cause the depth inconsistency. We propose a locally weighted linear regression method to recover the scale and shift with very sparse anchor points. Our method can boost the performance of existing state-of-the-art approaches by 50% at most over several zero-shot benchmarks.
  arXiv  Detail & Related papers  (2022-02-03T08:52:54Z)
• Adaptive confidence thresholding for monocular depth estimation [83.06265443599521]
  We propose a new approach to leverage pseudo ground truth depth maps of stereo images generated from self-supervised stereo matching methods. The confidence map of the pseudo ground truth depth map is estimated to mitigate performance degeneration by inaccurate pseudo depth maps. Experimental results demonstrate superior performance to state-of-the-art monocular depth estimation methods.
  arXiv  Detail & Related papers  (2020-09-27T13:26:16Z)
• Monocular Depth Estimation Based On Deep Learning: An Overview [16.2543991384566]
  Inferring depth information from a single image (monocular depth estimation) is an ill-posed problem. Deep learning has been widely studied recently and achieved promising performance in accuracy. In order to improve the accuracy of depth estimation, different kinds of network frameworks, loss functions and training strategies are proposed.
  arXiv  Detail & Related papers  (2020-03-14T12:35:34Z)

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.