Related papers: DaDiff: Domain-aware Diffusion Model for Nighttime…

Unmanned aerial vehicle (UAV) tracking is critical for applications like surveillance, search-and-rescue, and autonomous navigation. However, the high-speed movement of UAVs and targets introduces unique challenges, including real-time…

Good 3D object detection performance from LiDAR-Camera sensors demands seamless feature alignment and fusion strategies. We propose the 3DifFusionDet framework in this paper, which structures 3D object detection as a denoising diffusion…

In this paper, we look into the problem of estimating per-pixel depth maps from unconstrained RGB monocular night-time images which is a difficult task that has not been addressed adequately in the literature. The state-of-the-art day-time…

Deploying autonomous robots in crowded indoor environments usually requires them to have accurate dynamic obstacle perception. Although plenty of previous works in the autonomous driving field have investigated the 3D object detection…

Accurate relative positioning is crucial for swarm aerial robotics, enabling coordinated flight and collision avoidance. Although vision-based tracking has been extensively studied, 3D LiDAR-based methods remain underutilized despite their…

Time-of-Flight (ToF) sensors efficiently capture scene depth, but the nonlinear depth construction procedure often results in extremely large noise variance or even invalid areas. Recent methods based on deep neural networks (DNNs) achieve…

Although learning-based image restoration methods have made significant progress, they still struggle with limited generalization to real-world scenarios due to the substantial domain gap caused by training on synthetic data. Existing…

Current video deblurring methods have limitations in recovering high-frequency information since the regression losses are conservative with high-frequency details. Since Diffusion Models (DMs) have strong capabilities in generating…

With the rapid advancement of diffusion models, a variety of fine-tuning methods have been developed, enabling high-fidelity image generation with high similarity to the target content using only 3 to 5 training images. More recently,…

We propose an approach for unsupervised adaptation of object detectors from label-rich to label-poor domains which can significantly reduce annotation costs associated with detection. Recently, approaches that align distributions of source…

Domain adaptation methods face performance degradation in object detection, as the complexity of tasks require more about the transferability of the model. We propose a new perspective on how CNN models gain the transferability, viewing the…

A good feature representation is the key to image classification. In practice, image classifiers may be applied in scenarios different from what they have been trained on. This so-called domain shift leads to a significant performance drop…

Recent deep learning methods for object detection rely on a large amount of bounding box annotations. Collecting these annotations is laborious and costly, yet supervised models do not generalize well when testing on images from a different…

Deep neural networks (DNNs) are increasingly integrated into LiDAR (Light Detection and Ranging)-based perception systems for autonomous vehicles (AVs), requiring robust performance under adversarial conditions. We aim to address the…

We investigate a challenging task of nighttime optical flow, which suffers from weakened texture and amplified noise. These degradations weaken discriminative visual features, thus causing invalid motion feature matching. Typically,…

Diffusion models have recently shown promise in time series forecasting, particularly for probabilistic predictions. However, they often fail to achieve state-of-the-art point estimation performance compared to regression-based methods.…

We introduce a novel unsupervised domain adaptation approach for object detection. We aim to alleviate the imperfect translation problem of pixel-level adaptations, and the source-biased discriminativity problem of feature-level adaptations…

With the proliferation of location-tracking technologies, massive volumes of trajectory data are continuously being collected. As a fundamental task in trajectory data mining, trajectory similarity computation plays a critical role in a…

Diffusion policies are becoming mainstream in robotic manipulation but suffer from hard negative class imbalance due to uniform sampling and lack of sample difficulty awareness, leading to slow training convergence and frequent inference…

Camera and LiDAR serve as informative sensors for accurate and robust autonomous driving systems. However, these sensors often exhibit heterogeneous natures, resulting in distributional modality gaps that present significant challenges for…