activity
20162023
most citedAccurate Light Field Depth Estimation with Superpixel Regularization over Partially Occluded Regions

129 citations · 511 across the 26 of their papers we have counts for

collaborators
Showing 2021Show all

6 papers · 1 filter

cs.CV2021

Temporal-MPI: Enabling Multi-Plane Images for Dynamic Scene Modelling via Temporal Basis Learning

Wenpeng Xing, Jie Chen

Novel view synthesis of static scenes has achieved remarkable advancements in producing photo-realistic results. However, key challenges remain for immersive rendering of dynamic s…

eess.IV2021★ 62 cited

Attention-Guided Progressive Neural Texture Fusion for High Dynamic Range Image Restoration

Jie Chen, Zaifeng Yang, Tsz Nam Chan +3

High Dynamic Range (HDR) imaging via multi-exposure fusion is an important task for most modern imaging platforms. In spite of recent developments in both hardware and algorithm in…

cs.CV2021★ 4 cited

Attention-Guided NIR Image Colorization via Adaptive Fusion of Semantic and Texture Clues

Xingxing Yang, Jie Chen, Zaifeng Yang +1

Near infrared (NIR) imaging has been widely applied in low-light imaging scenarios; however, it is difficult for human and algorithms to perceive the real scene in the colorless NI…

cs.CV2021★ 4 cited

Scale-Consistent Fusion: from Heterogeneous Local Sampling to Global Immersive Rendering

Wenpeng Xing, Jie Chen, Zaifeng Yang +1

Image-based geometric modeling and novel view synthesis based on sparse, large-baseline samplings are challenging but important tasks for emerging multimedia applications such as v…

cs.CV2021★ 2 cited

Image-based Virtual Fitting Room

Zhiling Huang, Junwen Bu, Jie Chen

Virtual fitting room is a challenging task yet useful feature for e-commerce platforms and fashion designers. Existing works can only detect very few types of fashion items. Beside…

eess.IV2021

Learning Structral coherence Via Generative Adversarial Network for Single Image Super-Resolution

Yuanzhuo Li, Yunan Zheng, Jie Chen +2

Among the major remaining challenges for single image super resolution (SISR) is the capacity to recover coherent images with global shapes and local details conforming to human vi…