DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble

• URL: http://arxiv.org/abs/2607.00416v1
• Date: Wed, 01 Jul 2026 04:17:02 GMT
• Title: DroneIQA-VLE: Multi-Task Drone Image Quality Assessment via Vision-Language Ensemble
• Abstract summary: We present DroneIQA-VLE, our solution to the ICME 2026 Drone-IQA Grand Challenge on Target-aware Image Quality Assessment for Low-altitude UAV Images.<n>The framework jointly predicts global, target, and background quality scores by ensembling two complementary pipelines.<n>Our method achieves 2nd place in the challenge, demonstrating its effectiveness.
• Score: 53.12112874571972
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present DroneIQA-VLE, our solution to the ICME 2026 Drone-IQA Grand Challenge on Target-aware Image Quality Assessment for Low-altitude UAV Images. The framework jointly predicts global, target, and background quality scores by ensembling two complementary pipelines: (1) SigLIP2 vision encoders with multi-task regression heads, and (2) a LoRA-adapted Qwen3.5-9B multimodal large language model for quality score regression. The final global quality prediction is obtained by arithmetically averaging the outputs of both pipelines. Our method achieves 2nd place in the challenge, demonstrating its effectiveness. The code is available at https://github.com/sunwei925/DroneIQA-VLE.

Related papers

• Viewport-Unaware Blind Omnidirectional Image Quality Assessment: A Unified and Generalized Approach [48.016614649045586]
  Blind omnidirectional image quality assessment (BOIQA) presents a great challenge to the visual quality assessment community.<n>Main paradigm of BOIQA models includes two steps, ie, viewport generation and quality prediction.<n>We present a new BOIQA approach, which has three merits: ie, viewport-unaware.
  arXiv  Detail & Related papers  (2026-04-27T01:58:37Z)
• NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1) [115.35873876159131]
  We present an overview of the NTIRE 2026 challenge on the 3rd Restore Any Image Model in the Wild, specifically focusing on Track 1.<n>In total, the challenge attracted nearly 200 registrations and over 2,500 submissions.<n>The top-performing methods significantly advanced the state of the art in professional IQA.
  arXiv  Detail & Related papers  (2026-04-14T09:44:35Z)
• iDETEX: Empowering MLLMs for Intelligent DETailed EXplainable IQA [10.857047397246598]
  iDETEX is a unified multimodal large language model (MLLM) capable of simultaneously performing three key tasks: quality grounding, perception, and description.<n>We validate our approach on the large-scale ViDA-UGC benchmark, where iDETEX achieves state-of-the-art performance across all subtasks.
  arXiv  Detail & Related papers  (2025-10-20T09:26:12Z)
• Image Quality Assessment for Embodied AI [103.66095742463195]
  Embodied AI has developed rapidly in recent years, but it is still mainly deployed in laboratories.<n>There is no IQA method to assess the usability of an image in embodied tasks, namely, the perceptual quality for robots.
  arXiv  Detail & Related papers  (2025-05-22T15:51:07Z)
• DP-IQA: Utilizing Diffusion Prior for Blind Image Quality Assessment in the Wild [73.6767681305851]
  Blind image quality assessment (IQA) in the wild presents significant challenges.<n>Given the difficulty in collecting large-scale training data, leveraging limited data to develop a model with strong generalization remains an open problem.<n>Motivated by the robust image perception capabilities of pre-trained text-to-image (T2I) diffusion models, we propose a novel IQA method, diffusion priors-based IQA.
  arXiv  Detail & Related papers  (2024-05-30T12:32:35Z)
• Target-Grounded Graph-Aware Transformer for Aerial Vision-and-Dialog Navigation [10.25089706534778]
  This report details the methods of the winning entry of the AVDN Challenge in ICCV CLVL 2023. It addresses the Aerial Navigation from Dialog History (andH) task, which requires a drone agent to associate dialog history with aerial observations to reach the destination. For better cross-modal grounding abilities of the drone agent, we propose a Target-Grounded Graph-Aware Transformer (TG-GAT) framework.
  arXiv  Detail & Related papers  (2023-08-22T16:45:35Z)
• Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment [50.82681686110528]
  Blind Omnidirectional Image Quality Assessment (BOIQA) aims to objectively assess the human perceptual quality of omnidirectional images (ODIs) The quality assessment of ODIs is severely hampered by the fact that the existing BOIQA pipeline lacks the modeling of the observer's browsing process. We propose a novel multi-sequence network for BOIQA called Assessor360, which is derived from the realistic multi-assessor ODI quality assessment procedure.
  arXiv  Detail & Related papers  (2023-05-18T13:55:28Z)
• End-to-end deep multi-score model for No-reference stereoscopic image quality assessment [6.254148286968409]
  We use a deep multi-score Convolutional Neural Network (CNN) to estimate stereoscopic image quality without reference. Our model has been trained to perform four tasks: First, predict the left view's quality. Second, predict the quality of the left view. Third and fourth, predict the quality of the stereo view and global quality, respectively, with the global score serving as the ultimate quality.
  arXiv  Detail & Related papers  (2022-11-02T16:45:35Z)
• MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment [18.637040004248796]
  No-Reference Image Quality Assessment (NR-IQA) aims to assess the perceptual quality of images in accordance with human subjective perception. Existing NR-IQA methods are far from meeting the needs of predicting accurate quality scores on GAN-based distortion images. We propose Multi-dimension Attention Network for no-reference Image Quality Assessment (MANIQA) to improve the performance on GAN-based distortion.
  arXiv  Detail & Related papers  (2022-04-19T15:56:43Z)

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.