REVIEW 9 cited by
Free-Form Image Inpainting with Gated Convolution
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
We present a generative image inpainting system to complete images with free-form mask and guidance. The system is based on gated convolutions learned from millions of images without additional labelling efforts. The proposed gated convolution solves the issue of vanilla convolution that treats all input pixels as valid ones, generalizes partial convolution by providing a learnable dynamic feature selection mechanism for each channel at each spatial location across all layers. Moreover, as free-form masks may appear anywhere in images with any shape, global and local GANs designed for a single rectangular mask are not applicable. Thus, we also present a patch-based GAN loss, named SN-PatchGAN, by applying spectral-normalized discriminator on dense image patches. SN-PatchGAN is simple in formulation, fast and stable in training. Results on automatic image inpainting and user-guided extension demonstrate that our system generates higher-quality and more flexible results than previous methods. Our system helps user quickly remove distracting objects, modify image layouts, clear watermarks and edit faces. Code, demo and models are available at: https://github.com/JiahuiYu/generative_inpainting
Forward citations
Cited by 9 Pith papers
-
Image Inpainting with Learnable Bidirectional Attention Maps
A U-Net inpainting model with learnable forward and reverse attention maps improves irregular-hole filling over partial convolution and other state-of-the-art methods.
-
Copy-and-Paste Networks for Deep Video Inpainting
Copy-and-Paste Networks fill video holes using a self-supervised alignment network and masked softmax context matching, reaching quality similar to optimization-based methods at a fraction of the runtime.
-
Onion-Peel Networks for Deep Video Completion
Onion-Peel Networks fill video holes progressively from the boundary inward, using asymmetric attention to retrieve content from reference frames, and match or slightly trail an optimization-based method at much lower...
-
Indoor Depth Completion with Boundary Consistency and Self-Attention
A self-attention depth completion network with a Sobel-supervised boundary consistency loss reports state-of-the-art results on Matterport3D.
-
Boundless: Generative Adversarial Networks for Image Extension
Semantic conditioning of a GAN discriminator with pretrained InceptionV3 features improves generated image extensions, especially for large masks.
-
StructureFlow: Image Inpainting via Structure-aware Appearance Flow
StructureFlow splits inpainting into structure reconstruction on edge-preserved smooth images and texture generation via appearance flow, reporting competitive results on Places2, CelebA, and Paris StreetView.
-
DRRNet: Macro-Micro Feature Fusion and Dual Reverse Refinement for Camouflaged Object Detection
DRRNet is a four-stage camouflaged object detection network that fuses global and local features and then applies two rounds of reverse refinement to sharpen object boundaries.
-
Inpainting Insights: Elevating Visual XAI with Photorealistic Perturbations
LILI uses LaMa inpainting and mask expansion to make LIME's perturbations photorealistic, improving FID and saliency scores on ImageNet explanations.
-
SSDD-GAN: Single-Step Denoising Diffusion GAN for Cochlear Implant Surgical Scene Completion
A single-step denoising diffusion GAN with a Patch-GAN discriminator completes surgical microscope scenes, reporting higher SSIM than several inpainting baselines on a small single-patient dataset.
Discussion (0). Continue with ORCID to comment.