Related papers: Retrieval-Augmented Neural Field for HRTF Upsampli…
Sound field reconstruction (SFR) augments the information of a sound field captured by a microphone array. Conventional SFR methods using basis function decomposition are straightforward and computationally efficient, but may require more…
This paper introduces a novel paradigm for the generalizable neural radiance field (NeRF). Previous generic NeRF methods combine multiview stereo techniques with image-based neural rendering for generalization, yielding impressive results,…
As retrieval-augmented generation (RAG) becomes more widespread, the role of retrieval is shifting from retrieving information for human browsing to retrieving context for AI reasoning. This shift creates more complex search environments,…
While deep learning reshaped the classical motion capture pipeline with feed-forward networks, generative models are required to recover fine alignment via iterative refinement. Unfortunately, the existing models are usually hand-crafted or…
Neural Radiance Fields (NeRFs) can be dramatically accelerated by spatial grid representations. However, they do not explicitly reason about scale and so introduce aliasing artifacts when reconstructing scenes captured at different camera…
Magnetic resonance fingerprinting (MRF) provides a unique concept for simultaneous and fast acquisition of multiple quantitative MR parameters. Despite acquisition efficiency, adoption of MRF into the clinics is hindered by its dictionary…
Articulated objects pose a unique challenge for robotic perception and manipulation. Their increased number of degrees-of-freedom makes tasks such as localization computationally difficult, while also making the process of real-world…
Neural radiance field (NeRF) has shown remarkable performance in generating photo-realistic novel views. Among recent NeRF related research, the approaches that involve the utilization of explicit structures like grids to manage features…
Estimation of a speaker's direction and head orientation with binaural recordings can be a critical piece of information in many real-world applications with emerging `earable' devices, including smart headphones and AR/VR headsets.…
Radio frequency (RF)-based indoor localization offers significant promise for applications such as indoor navigation, augmented reality, and pervasive computing. While deep learning has greatly enhanced localization accuracy and robustness,…
Hyperspectral images are crucial for many research works. Spectral super-resolution (SSR) is a method used to obtain high spatial resolution (HR) hyperspectral images from HR multispectral images. Traditional SSR methods include…
Typical person re-identification (re-ID) methods train a deep CNN to extract deep features and combine them with a distance metric for the final evaluation. In this work, we focus on exploiting the full information encoded in the deep…
Magnetic Resonance Fingerprinting (MRF) is an imaging technique acquiring unique time signals for different tissues. Although the acquisition is highly accelerated, the reconstruction time remains a problem, as the state-of-the-art template…
Largely due to their implicit nature, neural fields lack a direct mechanism for filtering, as Fourier analysis from discrete signal processing is not directly applicable to these representations. Effective filtering of neural fields is…
Neural Radiance Fields (NeRF) with hybrid representations have shown impressive capabilities for novel view synthesis, delivering high efficiency. Nonetheless, their performance significantly drops with sparse input views. Various…
Instant on-device Neural Radiance Fields (NeRFs) are in growing demand for unleashing the promise of immersive AR/VR experiences, but are still limited by their prohibitive training time. Our profiling analysis reveals a memory-bound…
Relative impulse responses between microphones are usually long and dense due to the reverberant acoustic environment. Estimating them from short and noisy recordings poses a long-standing challenge of audio signal processing. In this paper…
Realistic sound simulation plays a critical role in many applications. A key element in sound simulation is the room impulse response (RIR), which characterizes how sound propagates from a source to a listener within a given space. Recent…
Modern deep neural networks (DNNs) are highly accurate on many recognition tasks for overhead (e.g., satellite) imagery. However, visual domain shifts (e.g., statistical changes due to geography, sensor, or atmospheric conditions) remain a…
This paper proposes a model that integrates sub-band processing and deep filtering to fully exploit information from the target time-frequency (TF) bin and its surrounding TF bins for single-channel speech enhancement. The sub-band module…