Suchergebnisse - "Computing methodologies— Computer graphics—Image manipulation—Image processing"

Rain Wiper: An Incremental Randomly Wired Network for Single Image Deraining von Liang, X., Qiu, B., Su, Z., Gao, C., Shi, X., Wang, R.

“… Single image rain removal is a challenging ill‐posed problem due to various shapes and densities of rain streaks. We present a novel incremental randomly wired …”
Volltext

Extended Depth-of-Field Projector using Learned Diffractive Optics von Li, Yuqi, Fu, Qiang, Heidrich, Wolfgang

“… Projector Depth-of-Field (DOF) refers to the projection range of projector images in focus. It is a crucial property of projectors in spatial augmented reality …”
Volltext

Deep360Up: A Deep Learning-Based Approach for Automatic VR Image Upright Adjustment von Jung, Raehyuk, Lee, Aiden Seung Joon, Ashtari, Amirsaman, Bazin, Jean-Charles

“… Spherical VR cameras can capture high-quality immersive VR images with a 360° field of view. However, in practice, when the camera orientation is not straight, …”
Volltext

MHDiff: Memory- and Hardware-Efficient Diffusion Acceleration via Focal Pixel Aware Quantization von Qi, Chunyu, Wang, Xuhang, Chen, Ruiyang, Yao, Yuanzheng, Jing, Naifeng, Zhang, Chen, Wang, Jun, Fu, Zhihui, Liang, Xiaoyao, Song, Zhuoran

“… Diffusion models have demonstrated superior performance in image generation tasks, thus becoming the mainstream model for generative visual tasks. Diffusion …”
Volltext

SynGPU: Synergizing CUDA and Bit-Serial Tensor Cores for Vision Transformer Acceleration on GPU von Yao, Yuanzheng, Zhang, Chen, Qi, Chunyu, Chen, Ruiyang, Wang, Jun, Fu, Zhihui, Jing, Naifeng, Liang, Xiaoyao, Song, Zhuoran

“… Vision Transformers (ViTs) have demonstrated remarkable performance in computer vision tasks by effectively extracting global features. However, their …”
Volltext

SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity von Fan, Zichen, Dai, Steve, Venkatesan, Rangharajan, Sylvester, Dennis, Khailany, Brucek

“… Diffusion models have gained significant popularity in image generation tasks. However, generating high-quality content remains notably slow because it …”
Volltext

DM-Tune: Quantizing Diffusion Models with Mixture-of-Gaussian Guided Noise Tuning von Haghi, Pouya, Falahati, Ali, Azad, Zahra, Wu, Chunshu, Song, Ruibing, Liu, Chuan, Li, Ang, Geng, Tong

“… Diffusion models have become essential generative tools for tasks such as image generation, video creation, and inpainting, but their high computational and …”
Volltext

DCDiff: Enhancing JPEG Compression via Diffusion-based DC Coefficients Estimation von Zhang, Ziyuan, Qiu, Han, Zhang, Tianwei, Chen, Bin, Zhang, Chao

“… JPEG is the most widely-used image compression method on low-cost cameras which cannot support learning-based compressors. One promising approach to enhance …”
Volltext

Privacy-Preserving Medical Image Segmentation via Hybrid Trusted Execution Environment von Bian, Song, Jiang, Weiwen, Sato, Takashi

“… Recently, it is reported that the-state-of-the-art secure protocol is able to segment a three-dimensional heart CT scan in roughly 3,000 seconds, without …”
Volltext

On Large Visual Language Models for Medical Imaging Analysis: An Empirical Study von Van, Minh-Hao, Verma, Prateek, Wu, Xintao

“… Recently, large language models (LLMs) have taken the spotlight in natural language processing. Further, integrating LLMs with vision enables the users to …”
Volltext

Degraded Reality: Using VR/AR to simulate visual impairments von Jones, Pete R., Ometto, Giovanni

“… The effects of eye disease cannot be depicted accurately using traditional media. Consequently, public understanding of eye disease is often poor. We present a …”
Volltext

Adaptive Patching for High-resolution Image Segmentation with Transformers von Zhang, Enzhi, Lyngaas, Isaac, Chen, Peng, Wang, Xiao, Igarashi, Jun, Huo, Yuankai, Munetomo, Masaharu, Wahib, Mohamed

“… Attention-based models are proliferating in the space of image analytics, including segmentation. The standard method of feeding images to transformer encoders …”
Volltext

Propagation as Data (PaD): Neural Phase Hologram Generation with Variable Distance Support von Cha, Jun Yeong, Ban, Hyunmin, Choi, Seongmi, Kim, Hui Yong

“… Most of the neural network models for generating phase holograms developed so far are trained and validated only for a single distance. Consequently, if a …”
Volltext

Distribution-Shifting: Novel Phase-distortion Metrics for Hologram Processing von Choi, Seungmi, Cha, Jun Yeong, Ban, Hyunmin, Oh, Kwan-Jung, Ko, Hyunsuk, Kim, Hui Yong

“… Due to the lack of suitable phase distortion metrics, the optimization and evaluation of phase-holograms have relied on numerical reconstruction (NR) domain …”
Volltext

DeclutterAR: Mobile Diminished Reality and Augmented Reality to Address Hoarding by Motivating Decluttering and Selling on Online Marketplace von Chan, Samantha W. T., Ryskeldiev, Bektur, Nanayakkara, Suranga

“… Hoarding behaviour is a widespread issue in which people have difficulty discarding or parting with their possessions. We present our work to address hoarding …”
Volltext

Discovering Image Usage Online: A Case Study with "Flatten the Curve" von Jones, Shawn M., Oyen, Diane

“… Understanding the spread of images across the web helps us understand the reuse of scientific visualizations and their relationship with the public. The …”
Volltext

Enhancing Electron Microscopy Image Classification Using Data Augmentation von Welsman, Jordan A., Weber, Gunther H., Amusat, Oluwamayowa O., Giannakou, Anna, Ramakrishnan, Lavanya

“… Manual labeling for machine learning tasks such as image classification is tedious and labor-intensive; as a result, scientific datasets suitable for deep …”
Volltext

Real-time Hand-object Occlusion for Augmented Reality Using Hand Segmentation and Depth Correction von Wu, Yuhui, Liu, Yue, Wang, Jiajun

“… Hand-object occlusion is crucial to enhance the realism of Aug-mented Reality, especially for egocentric hand-object interaction scenes. In this paper, a hand …”
Volltext

Scalable FBP Decomposition for Cone-Beam CT Reconstruction von Chen, Peng, Wahib, Mohamed, Wang, Xiao, Hirofuchi, Takahiro, Ogawa, Hirotaka, Biguri, Ander, Boardman, Richard, Blumensath, Thomas, Matsuoka, Satoshi

“… Filtered Back-Projection (FBP) is a fundamental compute intense algorithm used in tomographic image reconstruction. Cone-Beam Computed Tomography (CBCT) …”
Volltext

Toward Fair and Efficient Hyperdimensional Computing von Sheng, Yi, Yang, Junhuan, Jiang, Weiwen, Yang, Lei

“… We are witnessing the evolution that Machine Learning (ML) is applied to varied applications, such as intelligent security systems, medical diagnoses, etc …”
Volltext