Related papers: Test-Time Dynamic Image Fusion
Major data protection regulations all mention the "right to be forgotten," and that's what pushed federated unlearning (FU) techniques forward. But one stubborn issue remains: catastrophic forgetting--you erase the target knowledge, yet…
Capturing and reconstructing high-speed dynamic 3D scenes has numerous applications in computer graphics, vision, and interdisciplinary fields such as robotics, aerodynamics, and evolutionary biology. However, achieving this using a single…
This paper presents a concept of image pixel fusion of visual and thermal faces, which can significantly improve the overall performance of a face recognition system. Several factors affect face recognition performance including pose…
Shadow removal is still a challenging task due to its inherent background-dependent and spatial-variant properties, leading to unknown and diverse shadow patterns. Even powerful state-of-the-art deep neural networks could hardly recover…
Image fusion is a technique to integrate information from multiple source images with complementary information to improve the richness of a single image. Due to insufficient task-specific training data and corresponding ground truth, most…
Radars, due to their robustness to adverse weather conditions and ability to measure object motions, have served in autonomous driving and intelligent agents for years. However, Radar-based perception suffers from its unintuitive sensing…
Current image fusion methods struggle to address the composite degradations encountered in real-world imaging scenarios and lack the flexibility to accommodate user-specific requirements. In response to these challenges, we propose a…
Composed image retrieval (CIR) aims to retrieve the target image based on a multimodal query, i.e., a reference image paired with corresponding modification text. Recent CIR studies leverage vision-language pre-trained (VLP) methods as the…
There are two critical sensors for 3D perception in autonomous driving, the camera and the LiDAR. The camera provides rich semantic information such as color, texture, and the LiDAR reflects the 3D shape and locations of surrounding…
The inherent challenge of multimodal fusion is to precisely capture the cross-modal correlation and flexibly conduct cross-modal interaction. To fully release the value of each modality and mitigate the influence of low-quality multimodal…
We propose a simple yet effective deep tree-structured fusion model based on feature aggregation for the deraining problem. We argue that by effectively aggregating features, a relatively simple network can still handle tough image…
With the rapid progression of deep learning technologies, multi-modality image fusion has become increasingly prevalent in object detection tasks. Despite its popularity, the inherent disparities in how different sources depict scene…
Sensor fusion has wide applications in many domains including health care and autonomous systems. While the advent of deep learning has enabled promising multi-modal fusion of high-level features and end-to-end sensor fusion solutions,…
LiDAR point clouds have become the most common data source in autonomous driving. However, due to the sparsity of point clouds, accurate and reliable detection cannot be achieved in specific scenarios. Because of their complementarity with…
In recent years, multi-modal fusion has attracted a lot of research interest, both in academia, and in industry. Multimodal fusion entails the combination of information from a set of different types of sensors. Exploiting complementary…
Autonomous vehicles were experiencing rapid development in the past few years. However, achieving full autonomy is not a trivial task, due to the nature of the complex and dynamic driving environment. Therefore, autonomous vehicles are…
Deep image embedding provides a way to measure the semantic similarity of two images. It plays a central role in many applications such as image search, face verification, and zero-shot learning. It is desirable to have a universal deep…
Compositing is one of the most common operations in photo editing. To generate realistic composites, the appearances of foreground and background need to be adjusted to make them compatible. Previous approaches to harmonize composites have…
Flow-based generative super-resolution (SR) models learn to produce a diverse set of feasible SR solutions, called the SR space. Diversity of SR solutions increases with the temperature ($\tau$) of latent variables, which introduces random…
The rapid progress of Deepfake technology has made face swapping highly realistic, raising concerns about the malicious use of fabricated facial content. Existing methods often struggle to generalize to unseen domains due to the diverse…