Related papers: Semantic See-Through Rendering on Light Fields
Single-frame Infrared Small Target Detection (ISTD) aims to localize weak targets under heavy background clutter, yet dense pixel-wise annotations are expensive. Point supervision with online label evolution reduces annotation cost;…
Gloss-free Sign Language Translation (SLT) has advanced rapidly, achieving strong performances without relying on gloss annotations. However, these gains have often come with increased model complexity and high computational demands,…
Semantic segmentation has made encouraging progress due to the success of deep convolutional networks in recent years. Meanwhile, depth sensors become prevalent nowadays, so depth maps can be acquired more easily. However, there are few…
Deep convolutional neural networks (CNNs) are the backbone of state-of-art semantic image segmentation systems. Recent work has shown that complementing CNNs with fully-connected conditional random fields (CRFs) can significantly enhance…
Sign language translation (SLT), which generates text in a spoken language from visual content in a sign language, is important to assist the hard-of-hearing community for their communications. Inspired by neural machine translation (NMT),…
Unsupervised semantic segmentation aims to discover and localize semantically meaningful categories within image corpora without any form of annotation. To solve this task, algorithms must produce features for every pixel that are both…
We present a simple algorithm for differentiable rendering of surfaces represented by Signed Distance Fields (SDF), which makes it easy to integrate rendering into gradient-based optimization pipelines. To tackle visibility-related…
Light field (LF) imaging captures both angular and spatial light distributions, enabling advanced photographic techniques. However, micro-lens array (MLA)- based cameras face a spatial-angular resolution tradeoff due to a single shared…
The bundle of geometry and appearance in computer vision has proven to be a promising solution for robots across a wide variety of applications. Stereo cameras and RGB-D sensors are widely used to realise fast 3D reconstruction and…
Semantic mapping based on the supervised object detectors is sensitive to image distribution. In real-world environments, the object detection and segmentation performance can lead to a major drop, preventing the use of semantic mapping in…
Most prior semantic segmentation methods have been developed for day-time scenes, while typically underperforming in night-time scenes due to insufficient and complicated lighting conditions. In this work, we tackle this challenge by…
Future advancements in robot autonomy and sophistication of robotics tasks rest on robust, efficient, and task-dependent semantic understanding of the environment. Semantic segmentation is the problem of simultaneous segmentation and…
Recent studies on semantic communication commonly rely on neural network (NN) based transceivers such as deep joint source and channel coding (DeepJSCC). Unlike traditional transceivers, these neural transceivers are trainable using actual…
Neural Radiance Fields (NeRF) achieves photo-realistic image rendering from novel views, and the Neural Scene Graphs (NSG) \cite{ost2021neural} extends it to dynamic scenes (video) with multiple objects. Nevertheless, computationally heavy…
Most modern computational approaches to lexical semantic change detection (LSC) rely on embedding-based distributional word representations with neural networks. Despite the strong performance on LSC benchmarks, they are often opaque. We…
X-ray computed tomography (CT) is a widely used imaging technique that provides detailed examinations into the internal structure of an object with synchrotron CT (SR-CT) enabling improved data quality by using higher energy, monochromatic…
Visual transfer learning for unseen categories presents an active research topic yet a challenging task, due to the inherent conflict between preserving category-specific representations and acquiring transferable knowledge. Vision-Language…
Synthesizing a densely sampled light field from a single image is highly beneficial for many applications. The conventional method reconstructs a depth map and relies on physical-based rendering and a secondary network to improve the…
Light field (LF) cameras record both intensity and directions of light rays, and encode 3D scenes into 4D LF images. Recently, many convolutional neural networks (CNNs) have been proposed for various LF image processing tasks. However, it…
Owe to the powerful generative priors, the pre-trained text-to-image (T2I) diffusion models have become increasingly popular in solving the real-world image super-resolution problem. However, as a consequence of the heavy quality…