XiDepth: a Lightweight and Efficient Network for Self-supervised Monocular Depth Estimation

• URL: http://arxiv.org/abs/2608.03666v1
• Date: Tue, 04 Aug 2026 13:42:41 GMT
• Title: XiDepth: a Lightweight and Efficient Network for Self-supervised Monocular Depth Estimation
• Abstract summary: Self-supervised monocular depth estimation has emerged as an appealing solution to design lightweight and effective models for deployment on computationally constrained devices.<n>A critical challenge is achieving resource-efficient neural networks without compromising the overall performance.<n>We propose XiDepth, a lightweight architecture based on the XiNet operator block, to enhance feature extraction while maintaining low computational complexity and energy demand.
• Score: 6.07094468381517
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Self-supervised monocular depth estimation has emerged as an appealing solution to design lightweight and effective models for deployment on computationally constrained devices due to its reduced reliance on expensive depth sensors. By eliminating the need for ground-truth annotations and leveraging the simplicity of monocular camera setups, this approach facilitates cost-effective data collection and broad applicability across fields such as computer vision and robotics. A critical challenge is achieving resource-efficient neural networks without compromising the overall performance. State-of-the-art models generally adopt depth-wise convolutions and attention mechanisms; however, these functions often incur high energy costs and face compatibility issues in embedded environments. To address this, we propose XiDepth, a lightweight architecture based on the XiNet operator block, designed to enhance feature extraction while maintaining low computational complexity and energy demand. On the KITTI dataset, XiDepth achieves state-of-the-art performance with only 0.8M parameters. Tests on a Raspberry Pi 4 further confirm its suitability for real-world embedded applications, reducing FLOPs by 40% and energy consumption by 35% compared to leading methods.

Related papers

• LiteEvent-AE: Lightweight Autoencoder for Event-Based Vision on Low-Latency Energy-Constrained Edge Devices [0.3957768262206625]
  Event-based vision has emerged as a promising paradigm for energy-aware artificial intelligence (AI)<n>This work presents a compact and event-driven autoencoder that efficiently compresses neuromorphic data.<n>The architecture integrates lightweight encoding with robust performance under adaptive event thresholding.
  arXiv  Detail & Related papers  (2026-08-22T04:13:47Z)
• Seeing Through WiFi: Lightweight Human Pose Estimation with Dynamic Kernel Attention [55.570606479386434]
  WiFi-based human pose estimation (HPE) enables the detection and interpretation of human body positions and movements without the need for wearable devices.<n>This paper introduces a novel framework, WiLHPE, for lightweight and efficient human pose estimation using WiFi CSI signals.
  arXiv  Detail & Related papers  (2026-07-03T11:04:05Z)
• $D^3$-RSMDE: 40$\times$ Faster and High-Fidelity Remote Sensing Monocular Depth Estimation [72.9912717963138]
  Real-time, high-fidelity monocular depth estimation from remote sensing imagery is crucial for numerous applications.<n>Although using Vision Transformer (ViT) backbones for dense prediction is fast, they often exhibit poor perceptual quality.<n>We propose Depth Detail Diffusion for Remote Sensing Monocular Depth Estimation ($D3$-RSMDE) to overcome these limitations.<n>$D3$-RSMDE achieves a notable 11.85% reduction in the Learned Perceptual Image Patch Similarity (LPIPS) perceptual metric.
  arXiv  Detail & Related papers  (2026-03-17T10:50:36Z)
• PuriLight: A Lightweight Shuffle and Purification Framework for Monocular Depth Estimation [15.413017422345545]
  PuriLight is a framework for self-supervised monocular depth estimation.<n>It addresses the dual challenges of computational efficiency and detail preservation.<n>PuriLight achieves state-of-the-art performance with minimal training parameters.
  arXiv  Detail & Related papers  (2026-02-11T17:35:21Z)
• ECORE: Energy-Conscious Optimized Routing for Deep Learning Models at the Edge [17.74343318260183]
  ECORE is a framework that integrates multiple dynamic routing strategies.<n>ECORE balances energy efficiency and detection performance based on object characteristics.<n>Results demonstrate that our proposed context-aware routing strategies can reduce energy consumption and latency by 35% and 49%, respectively.
  arXiv  Detail & Related papers  (2025-07-08T14:16:14Z)
• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Lightweight Deep Learning Framework for Accurate Particle Flow Energy Reconstruction [8.598010350935596]
  This paper systematically evaluates a deep learning reconstruction framework.<n>We design a hybrid loss function combining weighted mean squared with error structural similarity index.<n>We enhance the model's capability to capture cross-modaltemporal correlations and energy-displacement nonlinearities.
  arXiv  Detail & Related papers  (2024-10-08T11:49:18Z)
• HW-SW Optimization of DNNs for Privacy-preserving People Counting on Low-resolution Infrared Arrays [9.806742394395322]
  Low-resolution infrared (IR) array sensors enable people counting applications such as monitoring the occupancy of spaces and people flows. Deep Neural Networks (DNNs) have been shown to be well-suited to process these sensor data in an accurate and efficient manner. We propose a highly automated full-stack optimization flow for DNNs that goes from neural architecture search, mixed-precision quantization, and post-processing.
  arXiv  Detail & Related papers  (2024-02-02T08:45:38Z)
• Computation-efficient Deep Learning for Computer Vision: A Survey [121.84121397440337]
  Deep learning models have reached or even exceeded human-level performance in a range of visual perception tasks. Deep learning models usually demand significant computational resources, leading to impractical power consumption, latency, or carbon emissions in real-world scenarios. New research focus is computationally efficient deep learning, which strives to achieve satisfactory performance while minimizing the computational cost during inference.
  arXiv  Detail & Related papers  (2023-08-27T03:55:28Z)
• Deep Learning for Real Time Satellite Pose Estimation on Low Power Edge TPU [58.720142291102135]
  In this paper we propose a pose estimation software exploiting neural network architectures. We show how low power machine learning accelerators could enable Artificial Intelligence exploitation in space.
  arXiv  Detail & Related papers  (2022-04-07T08:53:18Z)
• DepthNet Nano: A Highly Compact Self-Normalizing Neural Network for Monocular Depth Estimation [76.90627702089357]
  DepthNet Nano is a compact deep neural network for monocular depth estimation designed using a human machine collaborative design strategy. The proposed DepthNet Nano possesses a highly efficient network architecture, while still achieving comparable performance with state-of-the-art networks.
  arXiv  Detail & Related papers  (2020-04-17T00:41:35Z)

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.