Related papers: ACPO: Anchor-Constrained Perceptual Optimization f…

Recent years have witnessed the success of the deep learning-based technique in research of no-reference point cloud quality assessment (NR-PCQA). For a more accurate quality prediction, many previous studies have attempted to capture…

Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge.…

Reinforcement learning fine-tuning has proven effective for steering generative diffusion models toward desired properties in image and molecular domains. Graph diffusion models have similarly been applied to combinatorial structure…

This paper presents a high-performance general-purpose no-reference (NR) image quality assessment (IQA) method based on image entropy. The image features are extracted from two domains. In the spatial domain, the mutual information between…

Recent advances in diffusion models have shown remarkable potential in the conditional generation of novel molecules. These models can be guided in two ways: (i) explicitly, through additional features representing the condition, or (ii)…

Fine-tuning large diffusion models for custom applications demands substantial power and time, which poses significant challenges for efficient implementation on mobile devices. In this paper, we develop a novel training accelerator…

We present a framework for high-fidelity product image recontextualization using text-to-image diffusion models and a novel data augmentation pipeline. This pipeline leverages image-to-video diffusion, in/outpainting & negatives to create…

Despite great success in modeling visual perception, deep neural network based image quality assessment (IQA) still remains unreliable in real-world applications due to its vulnerability to adversarial perturbations and the inexplicit…

Direct preference optimization (DPO) has shown success in aligning diffusion models with human preference. Previous approaches typically assume a consistent preference label between final generations and noisy samples at intermediate steps,…

Using reinforcement learning with human feedback (RLHF) has shown significant promise in fine-tuning diffusion models. Previous methods start by training a reward model that aligns with human preferences, then leverage RL techniques to…

Incremental learning requires a model to continually learn new tasks from streaming data. However, traditional fine-tuning of a well-trained deep neural network on a new task will dramatically degrade performance on the old task -- a…

Preference alignment in diffusion models has primarily focused on benign human preferences (e.g., aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with…

Although recent efforts in image quality assessment (IQA) have achieved promising performance, there still exists a considerable gap compared to the human visual system (HVS). One significant disparity lies in humans' seamless transition…

Large-scale diffusion models have achieved state-of-the-art results on text-to-image synthesis (T2I) tasks. Despite their ability to generate high-quality yet creative images, we observe that attribution-binding and compositional…

The conventional training approach for image captioning involves pre-training a network using teacher forcing and subsequent fine-tuning with Self-Critical Sequence Training to maximize hand-crafted captioning metrics. However, when…

In the task of reference-based image inpainting, an additional reference image is provided to restore a damaged target image to its original state. The advancement of diffusion models, particularly Stable Diffusion, allows for simple…

This paper introduces a novel approach to aesthetic quality improvement in pre-trained text-to-image diffusion models when given a simple prompt. Our method, dubbed Prompt Embedding Optimization (PEO), leverages a pre-trained text-to-image…

Blind Image Quality Assessment (BIQA) aims to evaluate image quality in line with human perception, without reference benchmarks. Currently, deep learning BIQA methods typically depend on using features from high-level tasks for transfer…

Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding performance by utilizing rich semantic embeddings optimized for…

Image quality assessment (IQA) is traditionally classified into full-reference (FR) IQA and no-reference (NR) IQA according to whether the original image is required. Although NR-IQA is widely used in practical applications, room for…