Search Results for author:
Found 25 papers, 11 papers with code
Layer- and Timestep-Adaptive Differentiable Token Compression Ratios for Efficient Diffusion Transformers
To address this, we propose DiffRatio-MoD, a dynamic DiT inference framework with differentiable compression ratios, which automatically learns to dynamically route computation across layers and timesteps for each image token, resulting in Mixture-of-Depths (MoD) efficient DiT models.
Distilling Diffusion Models into Conditional GANs
We propose a method to distill a complex multistep diffusion model into a single-step conditional GAN student model, dramatically accelerating inference, while preserving image quality.
Brush2Prompt: Contextual Prompt Generator for Object Inpainting
Object inpainting is a task that involves adding objects to real images and seamlessly compositing them.
Perceptual Artifacts Localization for Image Synthesis Tasks
Recent advancements in deep generative models have facilitated the creation of photo-realistic images across various tasks.
SimpSON: Simplifying Photo Cleanup with Single-Click Distracting Object Segmentation Network
In photo editing, it is common practice to remove visual distractions to improve the overall image quality and highlight the primary subject.
Automatic High Resolution Wire Segmentation and Removal
In this paper, we present an automatic wire clean-up system that eases the process of wire segmentation and removal/inpainting to within a few seconds.
Structure-Guided Image Completion with Image-level and Object-level Semantic Discriminators
Moreover, the object-level discriminators take aligned instances as inputs to enforce the realism of individual objects.
Inpainting at Modern Camera Resolution by Guided PatchMatch with Auto-Curation
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.
Perceptual Artifacts Localization for Inpainting
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.
Deep 360$^\circ$ Optical Flow Estimation Based on Multi-Projection Fusion
Optical flow computation is essential in the early stages of the video processing pipeline.
CM-GAN: Image Inpainting with Cascaded Modulation GAN and Object-Aware Training
We propose cascaded modulation GAN (CM-GAN), a new network design consisting of an encoder with Fourier convolution blocks that extract multi-scale feature representations from the input image with holes and a dual-stream decoder with a novel cascaded global-spatial modulation block at each scale level.
Ranked #3 on
Image Inpainting
on Places2
GeoFill: Reference-Based Image Inpainting with Better Geometric Understanding
Our approach achieves state-of-the-art performance on both RealEstate10K and MannequinChallenge dataset with large baselines, complex geometry and extreme camera motions.
Modulated Periodic Activations for Generalizable Local Functional Representations
Our approach produces generalizable functional representations of images, videos and shapes, and achieves higher reconstruction quality than prior works that are optimized for a single signal.
TransFill: Reference-guided Image Inpainting by Merging Multiple Color and Spatial Transformations
Image inpainting is the task of plausibly restoring missing pixels within a hole region that is to be removed from a target image.
Learning from Shader Program Traces
We investigate this learning task for a variety of applications: our model can learn to predict a low-noise output image from shader programs that exhibit sampling noise; this model can also learn from a simplified shader program that approximates the reference solution with less computation, as well as learn the output of postprocessing filters like defocus blur and edge-aware sharpening.
Unselfie: Translating Selfies to Neutral-pose Portraits in the Wild
Due to the ubiquity of smartphones, it is popular to take photos of one's self, or "selfies."
Generative Tweening: Long-term Inbetweening of 3D Human Motions
We introduce a biomechanically constrained generative adversarial network that performs long-term inbetweening of human motions, conditioned on keyframe constraints.
Image Morphing with Perceptual Constraints and STN Alignment
In image morphing, a sequence of plausible frames are synthesized and composited together to form a smooth transformation between given instances.
Foreground-aware Image Inpainting
We show that by such disentanglement, the contour completion model predicts reasonable contours of objects, and further substantially improves the performance of image inpainting.
Texture Mixer: A Network for Controllable Synthesis and Interpolation of Texture
This paper addresses the problem of interpolating visual textures.
On the Continuity of Rotation Representations in Neural Networks
Thus, widely used representations such as quaternions and Euler angles are discontinuous and difficult for neural networks to learn.
Where and Who? Automatic Semantic-Aware Person Composition
Image compositing is a method used to generate realistic yet fake imagery by inserting contents from one image to another.
Stable and Controllable Neural Texture Synthesis and Style Transfer Using Histogram Losses
These losses can improve the quality of large features, improve the separation of content and style, and offer artistic controls such as paint by numbers.
Learning to Detect Multiple Photographic Defects
Our new dataset enables us to formulate the problem as a multi-task learning problem and train a multi-column deep convolutional neural network (CNN) to simultaneously predict the severity of all the defects.
Camouflaging an Object from Many Viewpoints
We address the problem of camouflaging a 3D object from the many viewpoints that one might see it from.
