Search Results for author: Lingzhi Zhang

Found 11 papers, 5 papers with code

Amodal Completion via Progressive Mixed Context Diffusion

no code implementations24 Dec 2023 Katherine Xu, Lingzhi Zhang, Jianbo Shi

We propose to sidestep many of the difficulties of existing approaches, which typically involve a two-step process of predicting amodal masks and then generating pixels.

Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation

no code implementations6 Aug 2022 Lingzhi Zhang, Connelly Barnes, Kevin Wampler, Sohrab Amirghodsi, Eli Shechtman, Zhe Lin, Jianbo Shi

Recently, deep models have established SOTA performance for low-resolution image inpainting, but they lack fidelity at resolutions associated with modern cameras such as 4K or more, and for large holes.

Image Inpainting

Perceptual Artifacts Localization for Inpainting

1 code implementation5 Aug 2022 Lingzhi Zhang, Yuqian Zhou, Connelly Barnes, Sohrab Amirghodsi, Zhe Lin, Eli Shechtman, Jianbo Shi

Inspired by this workflow, we propose a new learning task of automatic segmentation of inpainting perceptual artifacts, and apply the model for inpainting model evaluation and iterative refinement.

Image Inpainting

Deep Image Blending

2 code implementations25 Oct 2019 Lingzhi Zhang, Tarmily Wen, Jianbo Shi

In addition, we jointly optimize the proposed Poisson blending loss as well as the style and content loss computed from a deep network, and reconstruct the blending region by iteratively updating the pixels using the L-BFGS solver.

Object

Multimodal Image Outpainting With Regularized Normalized Diversification

1 code implementation25 Oct 2019 Lingzhi Zhang, Jiancong Wang, Jianbo Shi

In this paper, we study the problem of generating a set ofrealistic and diverse backgrounds when given only a smallforeground region.

Image Outpainting

Neural Embedding for Physical Manipulations

no code implementations13 Jul 2019 Lingzhi Zhang, Andong Cao, Rui Li, Jianbo Shi

In common real-world robotic operations, action and state spaces can be vast and sometimes unknown, and observations are often relatively sparse.

Cannot find the paper you are looking for? You can Submit a new open access paper.