Related papers: Fast projections of two-dimensional light patterns…
Visual-inertial odometry (VIO) is widely used in various fields, such as robots, drones, and autonomous vehicles. However, real-world scenes often feature dynamic objects, compromising the accuracy of VIO. The diversity and partial…
Unsupervised Camoflaged Object Detection (UCOD) has gained attention since it doesn't need to rely on extensive pixel-level labels. Existing UCOD methods typically generate pseudo-labels using fixed strategies and train 1 x1 convolutional…
Ensuring safety in autonomous driving is a complex challenge requiring handling unknown objects and unforeseen driving scenarios. We develop multiscale video transformers capable of detecting unknown objects using only motion cues. Video…
The efficiency of object detectors depends on factors like detection accuracy, processing time, and computational resources. Processing time is crucial for real-time applications, particularly for autonomous vehicles (AVs), where…
Omnidirectional images (ODIs) are commonly used in real-world visual tasks, and high-resolution ODIs help improve the performance of related visual tasks. Most existing super-resolution methods for ODIs use end-to-end learning strategies,…
Trajectory prediction is central to the safe and seamless operation of autonomous vehicles (AVs). In deployment, however, prediction models inevitably face distribution shifts between training data and real-world conditions, where rare or…
Recent years have seen object detection robotic systems deployed in several personal devices (e.g., home robots and appliances). This has highlighted a challenge in their design, i.e., they cannot efficiently update their knowledge to…
Scene Text Image Super-Resolution (STISR) aims to restore high-resolution details in low-resolution text images, which is crucial for both human readability and machine recognition. Existing methods, however, often depend on external…
Out-of-distribution (OOD) detection is essential in autonomous driving, to determine when learning-based components encounter unexpected inputs. Traditional detectors typically use encoder models with fixed settings, thus lacking effective…
Accurately controlling object count in text-to-image generation remains a key challenge. Supervised methods often fail, as training data rarely covers all count variations. Methods that manipulate the denoising process to add or remove…
Forecasting over graph-structured sensor networks demands models that capture both deterministic spatial trends and stochastic variability, while remaining efficient enough for repeated inference as new observations arrive. We propose…
LiDAR-based 3D object detection plays a critical role for reliable and safe autonomous driving systems. However, existing detectors often produce overly confident predictions for objects not belonging to known categories, posing significant…
Out-of-distribution (OOD) detection is essential for deploying deep learning models in open-world environments. Existing approaches, such as energy-based scoring and gradient-projection methods, typically rely on high-dimensional…
We propose DeepASA, a multi-purpose model for auditory scene analysis that performs multi-input multi-output (MIMO) source separation, dereverberation, sound event detection (SED), audio classification, and direction-of-arrival estimation…
Unmanned aerial vehicles (UAVs), commonly known as drones, are increasingly used across diverse domains, including logistics, agriculture, surveillance, and defense. While these systems provide numerous benefits, their misuse raises safety…
I propose a spatial-mode demultiplexing (SPADE) measurement scheme for the far-field imaging of spatially incoherent optical sources. For any object too small to be resolved by direct imaging under the diffraction limit, I show that SPADE…
Adaptive optics in combination with multi-photon techniques is a powerful approach to image deep into a specimen. Remarkably, virtually all adaptive optics schemes today rely on wavefront modulators which are reflective, diffractive, or…
We demonstrate a high performance AOM based bi-frequency interferometer, which can realize either beating or beating free interference for single photon level quantum state. Visibility and optical efficiency of the interferometer are (99.5…
Autoregressive Transformer models have demonstrated impressive performance in video generation, but their sequential token-by-token decoding process poses a major bottleneck, particularly for long videos represented by tens of thousands of…
Anomaly segmentation aims to identify Out-of-Distribution (OoD) anomalous objects within images. Existing pixel-wise methods typically assign anomaly scores individually and employ a global thresholding strategy to segment anomalies.…