Related papers: EigeNet: Geometry-Informed Multi-Modal Learning fo…

Medical image segmentation requires large annotated datasets, creating a significant bottleneck for clinical applications. While few-shot segmentation methods can learn from minimal examples, existing approaches demonstrate suboptimal…

Room impulse response (RIR) functions capture how the surrounding physical environment transforms the sounds heard by a listener, with implications for various applications in AR, VR, and robotics. Whereas traditional methods to estimate…

The success of deep learning models is heavily tied to the use of massive amount of labeled data and excessively long training time. With the emergence of intelligent edge applications that use these models, the critical challenge is to…

Few-shot aerial image segmentation is a challenging task that involves precisely parsing objects in query aerial images with limited annotated support. Conventional matching methods without consideration of varying object orientations can…

Multimodal object detection leveraging RGB and Infrared (IR) images is pivotal for robust perception in all-weather scenarios. While recent adapter-based approaches efficiently transfer RGB-pretrained foundation models to this task, they…

We propose ImGeoNet, a multi-view image-based 3D object detection framework that models a 3D space by an image-induced geometry-aware voxel representation. Unlike previous methods which aggregate 2D features into 3D voxels without…

Accurate estimation of Room Impulse Response (RIR), which captures an environment's acoustic properties, is important for speech processing and AR/VR applications. We propose AV-RIR, a novel multi-modal multi-task learning approach to…

Referring Remote Sensing Image Segmentation (RRSIS) is a situated, task-driven cross-modal task related to the embodied perception paradigm, requiring models to align visual-spatial features with linguistic intentions for precise target…

In mixed reality applications, a realistic acoustic experience in spatial environments is as crucial as the visual experience for achieving true immersion. Despite recent advances in neural approaches for Room Impulse Response (RIR)…

The recent emergence of hybrid models has introduced a transformative approach to computer vision, gradually moving beyond conventional convolutional neural networks and vision transformers. However, efficiently combining these two…

Currently, single image inpainting has achieved promising results based on deep convolutional neural networks. However, inpainting on stereo images with missing regions has not been explored thoroughly, which is also a significant but…

Geometric knowledge has been shown to be beneficial for the stereo matching task. However, prior attempts to integrate geometric insights into stereo matching algorithms have largely focused on geometric knowledge from single images while…

Room geometry inference (RGI) aims at estimating room shapes from measured room impulse responses (RIRs) and has received lots of attention for its importance in environment-aware audio rendering and virtual acoustic representation of a…

Existing few-shot segmentation methods are based on the meta-learning strategy and extract instance knowledge from a support set and then apply the knowledge to segment target objects in a query set. However, the extracted knowledge is…

Room geometry is important prior information for implementing realistic 3D audio rendering. For this reason, various room geometry inference (RGI) methods have been developed by utilizing the time-of-arrival (TOA) or…

Recent research has made significant progress in designing fusion modules for audio-visual speech separation. However, they predominantly focus on multi-modal fusion at a single temporal scale of auditory and visual features without…

In this work, we present Multimodal Equivariant Inverse Design Network (MEIDNet), a framework that jointly learns structural information and materials properties through contrastive learning, while encoding structures via an equivariant…

We present a method that synthesizes novel views of complex scenes by interpolating a sparse set of nearby views. The core of our method is a network architecture that includes a multilayer perceptron and a ray transformer that estimates…

With the growing demand for real-time video enhancement in live applications, existing methods often struggle to balance speed and effective exposure control, particularly under uneven lighting. We introduce RRNet (Rendering Relighting…

Humans naturally perceive a 3D scene in front of them through accumulation of information obtained from multiple interconnected projections of the scene and by interpreting their correspondence. This phenomenon has inspired artificial…