• Corpus ID: 244478759

Bridging Global Context Interactions for High-Fidelity Image Completion

@inproceedings{Zheng2021BridgingGC,
  title={Bridging Global Context Interactions for High-Fidelity Image Completion},
  author={Chuanxia Zheng and T. Cham and Jianfei Cai and Dinh Q. Phung},
  year={2021}
}
Bridging global context interactions correctly is important for high-fidelity image completion with large masks. Previous methods attempting this via deep or large receptive field (RF) convolutions cannot escape from the dominance of nearby interactions, which may be inferior. In this paper, we propose to treat image completion as a directionless sequence-to-sequence prediction task, and deploy a transformer to directly capture long-range dependence in the encoder. Crucially, we employ a… 
High-Quality Pluralistic Image Completion via Code Shared VQGAN
TLDR
The richness of the representation helps the subsequent deploy- ment of a transformer to effectively learn how to composite and complete a masked image at the discrete code domain, resulting in much better image reconstruction quality.

References

SHOWING 1-10 OF 64 REFERENCES
High-Fidelity Pluralistic Image Completion with Transformers
TLDR
The proposed method vastly outperforms state-of-the-art methods in terms of large performance boost on image fidelity even compared to deterministic completion methods; better diversity and higher fidelity for pluralistic completion; and exceptional generalization ability on large masks and generic dataset, like ImageNet.
Globally and locally consistent image completion
We present a novel approach for image completion that results in images that are both locally and globally consistent. With a fully-convolutional neural network, we can complete images of arbitrary
Contextual Residual Aggregation for Ultra High-Resolution Image Inpainting
TLDR
A Contextual Residual Aggregation mechanism that can produce high-frequency residuals for missing contents by weighted aggregating residuals from contextual patches, thus only requiring a low-resolution prediction from the network.
Taming Transformers for High-Resolution Image Synthesis
TLDR
It is demonstrated how combining the effectiveness of the inductive bias of CNNs with the expressivity of transformers enables them to model and thereby synthesize high-resolution images.
Contextual-Based Image Inpainting: Infer, Match, and Translate
TLDR
This work proposes a learning-based approach to generate visually coherent completion given a high-resolution image with missing components and shows that it generates results of better visual quality than previous state-of-the-art methods.
EdgeConnect: Structure Guided Image Inpainting using Edge Prediction
TLDR
This work proposes a two-stage model that separates the inpainting problem into structure prediction and image completion, similar to sketch art, and demonstrates that this approach outperforms current state-of-the-art techniques quantitatively and qualitatively.
Image Inpainting Guided by Coherence Priors of Semantics and Textures
TLDR
A multi-scale joint optimization framework is adopted to first model the coherence priors and then accordingly interleaving optimize image inpainting and semantic segmentation in a coarse-to-fine manner and two coherence losses are proposed to constrain the consistency between the semantics and the inpainted image in terms of the overall structure and detailed textures.
High-Resolution Image Inpainting with Iterative Confidence Feedback and Guided Upsampling
TLDR
A deep generative model which not only outputs an inpainting result but also a corresponding confidence map is introduced, which progressively fills the hole by trusting only high-confidence pixels inside the hole at each iteration and focuses on the remaining pixels in the next iteration.
SPG-Net: Segmentation Prediction and Guidance Network for Image Inpainting
TLDR
This paper proposes to introduce the semantic segmentation information, which disentangles the inter-class difference and intra-class variation for image inpainting, which leads to much clearer recovered boundary between semantically different regions and better texture within semantically consistent segments.
Pluralistic Free-Form Image Completion
TLDR
This paper proposes a novel and probabilistically principled framework with two parallel paths for pluralistic image completion, a reconstructive path that utilizes the only one ground truth to get prior distribution of missing patches and rebuild the original image from this distribution.
...
...