UAV Video Deblurring via Motion-Aware Diffusion: A Path to Robust Target Detection

Zhiqiang Hu; Shouren Huang; Masatoshi Ishikawa

cs.CVAug 15, 2026

UAV Video Deblurring via Motion-Aware Diffusion: A Path to Robust Target Detection

Authors: Zhiqiang Hu, Shouren Huang, Masatoshi Ishikawa

Organizations: Research Institute for Science & Technology, Tokyo University of Science

Abstract

Unmanned Aerial Vehicles (UAVs) play a crucial role in various scenarios ranging from disaster response to traffic surveillance. However, aerial video footage often suffers from severe motion blur due to rapid flight maneuvers, vibrations, and camera panning, which can significantly degrade downstream tasks such as target detection. Our goal is to explore a computationally-efficient and effective video deblurring approach to enhance UAV target detection performance. To reduce computational cost, we first propose an Adaptive Latent Scale Selector that dynamically adjusts the latent space resolution according to the intensity of UAV motion, thus balancing detail preservation with inference efficiency. To ensure temporal consistency, we introduce a Multi-Frame Alignment and Learnable Gating module to warp and gate the preceding frames, allowing the model to fuse only relevant temporal information and suppress misaligned or uninformative features. Our method can effectively recover sharp details from the UAV video stream. Extensive experiments on real UAV benchmarks demonstrate that our method not only yields superior deblurring performance but also significantly boosts target detection accuracy, making it highly applicable to robust aerial vision tasks.

Figures & tables

Fig. 1: Impact of Video Deblurring on UAV-Based Object Detection. The left section shows a UAV capturing a blurry scene. The middle section represents the deblurring process, restoring sharp frames. The right section compares object detection results on both blurry and restored frames, demonstrating improved object detection performance with deblurring.

Fig. 2: Inference Process with Adaptive Latent Feature Sizes: For frames with smooth motion (top), the Optical Flow Estimator calculates a lower motion intensity, leading the Adaptive Latent Scale Selector to choose a smaller latent feature size for encoding, which results in a shorter inference time; conversely, for frames with intense motion, a larger latent feature size is selected, leading to a longer inference time.

Fig. 3: Overview of Our Motion-Aware Dynamic Latent Diffusion Framework (a) for UAV Video Deblurring. First, each blurry frame is encoded at multiple scales. Then, an Adaptive Latent Scale Selector (Sec. III-C) dynamically determines the appropriate latent feature size based on the estimated motion intensity from optical flow, balancing fine detail preservation and computational efficiency. Next, our Multi-Frame Alignment and Learnable Gating (b) and Latent Fusion with MFCA (c) (Sec. III-E) warps preceding frames and filters out misaligned or uninformative regions, ensuring robust temporal fusion. Finally, we perform diffusion-based denoising (Sec. III-E) conditioned on these fused latent and decode them back to the spatial domain to obtain deblurred frames.

Fig. 4: Visual Comparisons Between our Method and SOTA Methods on GoPro [ 20 ] Dataset.

Fig. 5: Visual Comparisons Between Our Method and SOTA Methods on DVD [ 23 ] Dataset.

Fig. 6: Temporal Consistency Comparison on DVD [ 23 ] dataset. We analyze the temporal profile along a fixed row in consecutive frames to assess temporal consistency. The temporal profiles generated by existing methods, including VRT [ 16 ] , RVRT [ 17 ] , and Shift-Net+ [ 12 ] , reveal noticeable distortions and discontinuities, indicating flickering artifacts across frames. In contrast, Ours maintains a smooth and coherent profile over time, showcasing improved temporal consistency.

Method	GoPro		DVD
Method	PSNR	SSIM	PSNR	SSIM
STFAN [ 32 ]	28.69	0.8610	31.24	0.9340
STDA [ 28 ]	32.62	0.9375	33.05	0.9374
NAFNet [ 2 ]	33.69	0.9670	-	-
ARVo [ 13 ]	-	-	32.80	0.9352
VRT [ 16 ]	34.81	0.9724	34.27	0.9651

TABLE I: Quantitative comparisons on the GoPro and DVD datasets. The best results are highlighted in bold.

Fig. 7: Object Detection Performance on the VisDrone-VID2019 Dataset [ 33 ] . From left to right: (1) Detection results on blurred input frames using RTDETR [ 31 ] , (2) RVRT [ 17 ] deblurred frames + RTDETR detection [ 31 ] , (3) Our method deblurred frames + RTDETR detection, and (4) Detection results on original clear frames using RTDETR [ 31 ] . Our approach ( Ours + RTDETR [ 31 ] ) achieves the best detection performance, effectively recovering motion-degraded objects while preserving fine details. The zoomed-in patches further highlight that our deblurring algorithm restores sharper textures and more accurate object structures compared to RVRT [ 17 ] .

Fig. 8: Precision-recall Curves on the VisDrone-VID2019 [ 33 ] Dataset. The proposed method ( F: Ours + RTDETR [ 31 ] ) achieves the best precision-recall performance, consistently outperforming previous methods including STFAN [ 32 ] , VRT [ 16 ] , RVRT [ 17 ] , and Shift-Net [ 12 ] . This demonstrates its superior capability in handling degraded UAV imagery and improving object detection accuracy.

Method	AP	AP 50	AP 75	AR 1	AR 10	AR 100	AR 500
(A) Blur Video + RTDETR [ 31 ]	21.53	45.22	16.34	10.45	28.74	42.66	44.12
(B) STFAN [ 32 ] + RTDETR [ 31 ]	29.22	58.00	25.34	14.30	35.58	50.75	53.67
(C) VRT [ 16 ] + RTDETR [ 31 ]	31.50	60.20	27.80	15.20	37.44	52.20	55.10
(D) RVRT [ 17 ] + RTDETR [ 31 ]	32.60	62.80	28.60	16.10	38.05	53.60	56.00
(E) Shift-Net+ [ 12 ] + RTDETR [ 31 ]	33.80	63.20	29.25	16.60	38.90	54.40	57.50
(F) Ours + RTDETR [ 31 ]	35.12	64.70	30.80	17.75	40.10	55.90	59.20

TABLE II: Comparison results (AP, AR %) on the VisDrone-VID2019 [ 33 ] dataset. All entries use the same RTDETR [ 31 ] detection framework. We report AP, AP 50 , AP 75 , and AR under different candidate limits (1, 10, 100, 500).

Method	ALSS	MAlign	Gating	GoPro		VisDrone-VID2019
Method	ALSS	MAlign	Gating	PSNR	SSIM	AP	AP 50	AP 75	AR 1	AR 10	AR 100	AR 500
(1) Baseline	–	–	–	34.20	0.9680	31.00	60.30	27.00	15.20	36.10	51.20	53.50
(2) + ALSS	✓	–	–	34.80	0.9710	31.90	61.20	28.00	15.80	37.00	52.10	54.60
(3) + MAlign	–	✓	–	35.00	0.9730	32.50	62.10	28.90	16.00	38.00	53.80	55.90
(4) + Gating	–	–	✓	35.10	0.9745	33.00	62.70	29.10	16.20	38.40	54.10	56.10
(5) + MAlign + Gating	–	✓	✓	35.50	0.9770	34.00	63.50	29.70	16.50	39.00	55.20	57.30

TABLE III: Ablation Study on the GoPro Dataset (PSNR/SSIM) and the VisDrone-VID2019 Dataset. ALSS = Adaptive Latent Scale Selector, MAlign = Multi-Frame Alignment, Gating = Learnable Gating. The best results are in bold .

Experiment	PSNR	SSIM	AP	Time (ms)
Latent Scale Ablation
Fixed size $16\times 16$	33.50	0.9590	30.10	20
Fixed size $32\times 32$	34.00	0.9660	31.50	30
Fixed size $64\times 64$	34.50	0.9700	32.40	45
+ Adaptive Scale (ALSS)	34.20	0.9671	32.80	35
Cached Latent Frames Ablation

TABLE IV: Combined Ablation Study on Latent Scale and Cached Latent Frames on VisDrone-VID2019. Best results in each block are in bold .

Image Deblurring

Image deblurring restores sharp images from motion, defocus, and other blur by estimating lost detail and modeling image formation.

See all 62 papers

Decoupling Ego-Motion from Target Dynamics via Dual-Interval Motion Cues for UAV Detection
May 21, 2026Liuyang Wang, Feitian ZhangVideo Object Detection Object Detection
Robotics and Control Laboratory, Department of Robotics, School of Advanced Manufacturing and Robotics, and the State Key Laboratory of Turbulence and Complex Systems, Peking University, Beijing, 100871, China · Great Bay University, Guangdong 523808, China
UAV-DETR: DETR for Anti-Drone Target Detection
Mar 24, 2026Jun Yang, Dong Wang, Hongxu Yin +2Aerial Object Detection Small Object Detection
School of Automation, NPU, Xian, ShaanXi
UFO-DETR: Frequency-Guided End-to-End Detector for UAV Tiny Objects
Feb 26, 2026Yuankai Chen, Kai Lin, Qihong Wu +6Small Object Detection Aerial Object Detection
Easy Lab, College of Mathematics and Informatics, South China Agricultural University, Guangzhou, China · School of Computer Science and Engineering, Southeast University, Nanjing, China · School of Mathematics, Foshan University, Foshan, China

May 21, 2026J/K move · Enter open · S save

Decoupling Ego-Motion from Target Dynamics via Dual-Interval Motion Cues for UAV Detection

Liuyang Wang, Feitian Zhang

Robotics and Control Laboratory, Department of Robotics, School of Advanced Manufacturing and Robotics, and the State Key Laboratory of Turbulence and Complex Systems, Peking University, Beijing, 100871, China · Great Bay University, Guangdong 523808, China

Video Object Detection Object Detection Aerial Object Detection UAV Detection

Open paper AskPDF arXiv

Object detection from Unmanned Aerial Vehicles (UAVs) is challenged by severe ego-motion, camera jitter, and large scale variations. While modern detectors perform well on static images, their direct application to UAV video often fails, particularly for small objects in dynamic scenes. Existing motion-based methods either rely on computationally expensive optical flow or use single-interval differencing, which is sensitive to jitter and limited in capturing diverse motion patterns. We propose a vision-only motion-guided detection framework that decouples target motion from camera-induced disturbances. A homography-based Global Motion Compensation (GMC) first aligns adjacent frames. We then introduce a Dual-Interval Motion Extraction strategy that captures both short-term and long-term motion cues. To integrate these cues, a lightweight Motion-Guided Attention (MGA) module enhances feature representations within a Feature Pyramid Network. Experiments on the VisDrone-VID dataset demonstrate consistent improvements over a strong YOLOv8 baseline under severe ego-motion. Ablation studies further confirm the effectiveness of the dual-interval design and the proposed motion-guided attention mechanism.

Abstract

Image Deblurring

Explore similar work

Decoupling Ego-Motion from Target Dynamics via Dual-Interval Motion Cues for UAV Detection

UAV-DETR: DETR for Anti-Drone Target Detection

UFO-DETR: Frequency-Guided End-to-End Detector for UAV Tiny Objects