Search Results for author:
Found 21 papers, 7 papers with code
Bigger is not Always Better: Scaling Properties of Latent Diffusion Models
We study the scaling properties of latent diffusion models (LDMs) with an emphasis on their sampling efficiency.
TIP: Text-Driven Image Processing with Semantic and Restoration Instructions
Text-driven diffusion models have become increasingly popular for various image editing tasks, including inpainting, stylization, and object replacement.
CoDi: Conditional Diffusion Distillation for Higher-Fidelity and Faster Image Generation
Our conditional-task learning and distillation approach outperforms previous distillation methods, achieving a new state-of-the-art in producing high-quality images with very few steps (e. g., 1-4) across multiple tasks, including super-resolution, text-guided image editing, and depth-to-image generation.
MULLER: Multilayer Laplacian Resizer for Vision
Specifically, we select a state-of-the-art vision Transformer, MaxViT, as the baseline, and show that, if trained with MULLER, MaxViT gains up to 0. 6% top-1 accuracy, and meanwhile enjoys 36% inference cost saving to achieve similar top-1 accuracy on ImageNet-1k, as compared to the standard training scheme.
Multiscale Structure Guided Diffusion for Image Deblurring
We evaluate a single-dataset trained model on diverse datasets and demonstrate more robust deblurring results with fewer artifacts on unseen data.
Soft Diffusion: Score Matching for General Corruptions
To reverse these general diffusions, we propose a new objective called Soft Score Matching that provably learns the score function for any linear corruption process and yields state of the art results for CelebA.
Ranked #7 on
Image Generation
on CelebA 64x64
MaxViT: Multi-Axis Vision Transformer
We also show that our proposed model expresses strong generative modeling capability on ImageNet, demonstrating the superior potential of MaxViT blocks as a universal vision module.
Ranked #1 on
Object Detection
on COCO 2017
MAXIM: Multi-Axis MLP for Image Processing
In this work, we present a multi-axis MLP based architecture called MAXIM, that can serve as an efficient and flexible general-purpose vision backbone for image processing tasks.
Ranked #1 on
Deblurring
on HIDE (trained on GOPRO)
Deblurring via Stochastic Refinement
Unlike existing techniques, we train a stochastic sampler that refines the output of a deterministic predictor and is capable of producing a diverse set of plausible reconstructions for a given input.
Rich Features for Perceptual Quality Assessment of UGC Videos
Besides the subjective ratings and content labels of the dataset, we also propose a DNN-based framework to thoroughly analyze importance of content, technical quality, and compression level in perceptual quality.
Exponentiated Gradient Reweighting for Robust Training Under Label Noise and Beyond
Many learning tasks in machine learning can be viewed as taking a gradient step towards minimizing the average loss of a batch of examples in each training iteration.
Learning to Resize Images for Computer Vision Tasks
Moreover, we show that the proposed resizer can also be useful for fine-tuning the classification baselines for other vision tasks.
Deep Perceptual Image Quality Assessment for Compression
In this paper we propose the largest image compression quality dataset to date with human perceptual preferences, enabling the use of deep learning, and we develop a full reference perceptual quality assessment metric for lossy image compression that outperforms the existing state-of-the-art methods.
Projected Distribution Loss for Image Enhancement
More explicitly, we show that in imaging applications such as denoising, super-resolution, demosaicing, deblurring and JPEG artifact removal, the proposed learning loss outperforms the current state-of-the-art on reference-based perceptual losses.
Rank-smoothed Pairwise Learning In Perceptual Quality Assessment
Training a model on these pairwise preferences is a common deep learning approach.
The Rate-Distortion-Accuracy Tradeoff: JPEG Case Study
As a case study, we focus on the design of the quantization tables in the JPEG compression standard.
Super-Resolving Commercial Satellite Imagery Using Realistic Training Data
We propose a realistic training data generation model for commercial satellite imagery products, which includes not only the imaging process on satellites but also the post-process on the ground.
Better Compression with Deep Pre-Editing
In this work we aim to break the unholy connection between bit-rate and image quality, and propose a way to circumvent compression artifacts by pre-editing the incoming image and modifying its content to fit the given bits.
Learned Perceptual Image Enhancement
Learning a typical image enhancement pipeline involves minimization of a loss function between enhanced and reference images.
NIMA: Neural Image Assessment
Automatically learned quality assessment for images has recently become a hot topic due to its usefulness in a wide variety of applications such as evaluating image capture pipelines, storage techniques and sharing media.
Ranked #4 on
Aesthetics Quality Assessment
on AVA
Fast Multi-Layer Laplacian Enhancement
A novel, fast and practical way of enhancing images is introduced in this paper.
