Related papers: Dynamic PlenOctree for Adaptive Sampling Refinemen…
Neural Radiance Fields (NeRF) have demonstrated superior novel view synthesis performance but are slow at rendering. To speed up the volume rendering process, many acceleration methods have been proposed at the cost of large memory…
Text-to-image generation powered by Diffusion Transformers (DiTs) has made remarkable strides, yet remote sensing (RS) synthesis lags behind due to two barriers: the absence of a domain-specialized DiT prior and the prohibitive cost of…
Deep learning has achieved tremendous success by training increasingly large models, which are then compressed for practical deployment. We propose a drastically different approach to compact and optimal deep learning: We decouple the…
While category-level 9DoF object pose estimation has emerged recently, previous correspondence-based or direct regression methods are both limited in accuracy due to the huge intra-category variances in object shape and color, etc.…
Diffractive optical neural networks (DONNs) have demonstrated unparalleled energy efficiency and parallelism by processing information directly in the optical domain. However, their computational expressivity is constrained by static,…
Neural Radiance Fields (NeRF) show impressive performance for the photorealistic free-view rendering of scenes. However, NeRFs require dense sampling of images in the given scene, and their performance degrades significantly when only a…
Parameter Efficient Fine-Tuning (PEFT) techniques have drawn significant attention due to their ability to yield competitive results while updating only a small portion of the adjustable parameters. However, existing PEFT methods pose…
Neural Radiance Fields (NeRF) have transformed novel view synthesis by modeling scene-specific volumetric representations directly from images. While generalizable NeRF models can generate novel views across unknown scenes by learning…
Human pose transfer (HPT) is an emerging research topic with huge potential in fashion design, media production, online advertising and virtual reality. For these applications, the visual realism of fine-grained appearance details is…
In this work, we propose a novel deep online correction (DOC) framework for monocular visual odometry. The whole pipeline has two stages: First, depth maps and initial poses are obtained from convolutional neural networks (CNNs) trained in…
Neural Radiance Field (NeRF) has broken new ground in the novel view synthesis due to its simple concept and state-of-the-art quality. However, it suffers from severe performance degradation unless trained with a dense set of images with…
Omnidirectional images (ODIs) have obtained lots of research interest for immersive experiences. Although ODIs require extremely high resolution to capture details of the entire scene, the resolutions of most ODIs are insufficient. Previous…
Dimensionality reduction (DR) plays a crucial role in various fields, including data engineering and visualization, by simplifying complex datasets while retaining essential information. However, achieving both high DR accuracy and strong…
Accurate reconstruction of plant phenotypes plays a key role in optimising sustainable farming practices in the field of Precision Agriculture (PA). Currently, optical sensor-based approaches dominate the field, but the need for…
The conventional mesh-based Level of Detail (LoD) technique, exemplified by applications such as Google Earth and many game engines, exhibits the capability to holistically represent a large scene even the Earth, and achieves rendering with…
Neural radiance fields (NeRFs) have exhibited potential in synthesizing high-fidelity views of 3D scenes but the standard training paradigm of NeRF presupposes an equal importance for each image in the training set. This assumption poses a…
Deep learning has triggered explosive growth in the demand for specialized hardware processors, thus motivating the development of scalable and reconfigurable computing substrates. Optical processors offer a fundamentally different…
This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…
Traditional full-field optical coherence tomography (FF-OCT) is effective for rapid cross-sectional imaging but often suffers from incoherent signals due to imbalanced light intensities between the sample and reference arms. While the…
Diffuse optical tomography (DOT) utilises near-infrared light for imaging spatially distributed optical parameters, typically the absorption and scattering coefficients. The image reconstruction problem of DOT is an ill-posed inverse…