Related papers: DP$^2$O-SR: Direct Perceptual Preference Optimizat…

Single-image super-resolution (SR) has achieved remarkable progress with deep learning, yet most approaches rely on distortion-oriented losses or heuristic perceptual priors, which often lead to a trade-off between fidelity and visual…

Visual Quality Assessment (QA) seeks to predict human perceptual judgments of visual fidelity. While recent multimodal large language models (MLLMs) show promise in reasoning about image and video quality, existing approaches mainly rely on…

Most of the recent generative image super-resolution (SR) methods rely on adapting large text-to-image (T2I) diffusion models pretrained on web-scale text-image data. While effective, this paradigm starts from a generic T2I generator,…

The effectiveness of Direct Preference Optimization (DPO) depends on preference data that reflect the quality differences that matter in multimodal tasks. Existing pipelines often rely on off-policy perturbations or coarse outcome-based…

Large-scale pre-trained diffusion models have been extensively adopted for real-world image Super-Resolution because of their powerful generative priors through textual guidance. However, when super-resolving high-resolution images with…

Enhancing the conformity of large language models (LLMs) to human preferences remains an ongoing research challenge. Recently, offline approaches such as Direct Preference Optimization (DPO) have gained prominence as attractive options due…

Stereo image super-resolution (SSR) aims to enhance high-resolution details by leveraging information from stereo image pairs. However, existing stereo super-resolution (SSR) upsampling methods (e.g., pixel shuffle) often overlook…

Recent research has shown that fine-tuning diffusion models (DMs) with arbitrary rewards, including non-differentiable ones, is feasible with reinforcement learning (RL) techniques, enabling flexible model alignment. However, applying…

The application of diffusion models in 3D LiDAR scene completion is limited due to diffusion's slow sampling speed. Score distillation accelerates diffusion sampling but with performance degradation, while post-training with direct policy…

This study addresses the challenge of noise in training datasets for Direct Preference Optimization (DPO), a method for aligning Large Language Models (LLMs) with human preferences. We categorize noise into pointwise noise, which includes…

Recently, there has been significant interest in replacing the reward model in Reinforcement Learning with Human Feedback (RLHF) methods for Large Language Models (LLMs), such as Direct Preference Optimization (DPO) and its variants. These…

We address the problem of interactive text-to-image (T2I) generation, designing a reinforcement learning (RL) agent which iteratively improves a set of generated images for a user through a sequence of prompt expansions. Using human raters,…

In this work, we aim to address the challenging task of open set recognition (OSR). Many recent OSR methods rely on auto-encoders to extract class-specific features by a reconstruction strategy, requiring the network to restore the input…

Super-resolution (SR) is an ill-posed inverse problem with a large set of feasible solutions that are consistent with a given low-resolution image. Various deterministic algorithms aim to find a single solution that balances fidelity and…

Despite the rapid progress of text-to-image (T2I) models, generating images that accurately reflect complex compositional prompts (covering attribute bindings, object relationships, counting) still remains challenging. To address this, we…

This study presents a new image super-resolution (SR) technique based on diffusion inversion, aiming at harnessing the rich image priors encapsulated in large pre-trained diffusion models to improve SR performance. We design a Partial noise…

Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences…

Real-world image super-resolution is particularly challenging for diffusion models because real degradations are complex, heterogeneous, and rarely modeled explicitly. We propose a degradation-aware and structure-preserving diffusion…

Diffusion-based models have been widely used in various visual generation tasks, showing promising results in image super-resolution (SR), while typically being limited by dozens or even hundreds of sampling steps. Although existing methods…

Recent advances in audio-based generative language models have accelerated AI-driven lyric-to-song generation. However, these models frequently suffer from content hallucination, producing outputs misaligned with the input lyrics and…