Takeshi Ikenaga — accepted AI-conference papers

2024

Multi-Level Spatial-Temporal Feature Aggregation and Alignment-Based Selective Residual Dense Propagation Module for HDR Video Reconstruction

Yiyu Liu, Fengshan Zhao, Qin Liu, Takeshi Ikenaga

ICASSP 2024accepted

To reconstruct high dynamic range (HDR) video from alternating exposed low dynamic range (LDR) frames, the key is to address the misalignment and imprecise fusion caused by information loss and noise in ill-exposed regions. Following a coarse-to-fine manner, a Multi-level Spatial-Temporal feature ag…

Cited by 0 Source ↗Scholar ↗

2023

Pyramid Spatial Feature Transform and Shared-Offsets Deformable Alignment Based Convolutional Network for HDR Imaging

Junda Liao, Qin Liu, Takeshi Ikenaga

ICASSP 2023accepted

To generate ghost-free high dynamic range (HDR) images by merging multiple differently exposed low dynamic range (LDR) images, the key is to handle ill-exposed areas in the input LDR images and misalignment among them. In this paper, a Pyramid Spatial Feature Transform and shared-offsets Deformable…

Cited by 0 Source ↗Scholar ↗

2016

Anti-occlusion observation model and automatic recovery for multi-view ball tracking in sports analysis

Xina Cheng, Masaaki Honda, Norikazu Ikoma, Takeshi Ikenaga

ICASSP 2016accepted

The 3D position of the ball plays a crucial role in professional sport analysis. In ball sports, tracking of ball's precise position accurately is highly required, whose performance is affected by inaccurate 3D coordinates and occlusion problem. In this paper, we propose anti-occlusion observation m…

Cited by 0 Source ↗Scholar ↗