Related papers: Iterative Inference-time Scaling with Adaptive Fre…
Test-time scaling through reward-guided generation remains largely unexplored for discrete diffusion models despite its potential as a promising alternative. In this work, we introduce Iterative Reward-Guided Refinement (IterRef), a novel…
We present a novel method for diffusion-guided frameworks for view-consistent super-resolution (SR) in neural rendering. Our approach leverages existing 2D SR models in conjunction with advanced techniques such as Variational Score…
Image Super-Resolution (ISR) has seen significant progress with the introduction of remarkable generative models. However, challenges such as the trade-off issues between fidelity and realism, as well as computational complexity, have also…
Diffusion model deployment has been suffering from high energy consumption and inference latency despite its superior performance in visual generation tasks. Dynamic voltage and frequency scaling (DVFS) offers a promising solution to…
Super-resolution (SR) and image generation are important tasks in computer vision and are widely adopted in real-world applications. Most existing methods, however, generate images only at fixed-scale magnification and suffer from…
Diffusion models have demonstrated strong generative capabilities across domains ranging from image synthesis to complex reasoning tasks. However, most inference-time scaling methods rely on fixed denoising schedules, limiting their ability…
In this paper, we argue that iterative computation with diffusion models offers a powerful paradigm for not only generation but also visual perception tasks. We unify tasks such as depth estimation, optical flow, and amodal segmentation…
Despite the remarkable progress of deep learning in stereo matching, there exists a gap in accuracy between real-time models and slower state-of-the-art models which are suitable for practical applications. This paper presents an iterative…
Diffusion models have gained attention for their success in modeling complex distributions, achieving impressive perceptual quality in SR tasks. However, existing diffusion-based SR methods often suffer from high computational costs,…
Allocating extra computation at inference time has recently improved sample quality in large language models and diffusion-based image generation. In parallel, Flow Matching (FM) has gained traction in language, vision, and scientific…
Effective feature fusion of multispectral images plays a crucial role in multi-spectral object detection. Previous studies have demonstrated the effectiveness of feature fusion using convolutional neural networks, but these methods are…
Recent text-to-image diffusion models achieve impressive visual quality through extensive scaling of training data and model parameters, yet they often struggle with complex scenes and fine-grained details. Inspired by the self-reflection…
Diffusion models have emerged as powerful priors for single-image restoration, but their application to zero-shot video restoration suffers from temporal inconsistencies due to the stochastic nature of sampling and complexity of…
While diffusion-based image restoration (IR) methods have achieved remarkable success, they are still limited by the low inference speed attributed to the necessity of executing hundreds or even thousands of sampling steps. Existing…
Multi-source stationary computed tomography (CT) has recently attracted attention for its ability to achieve rapid image reconstruction, making it suitable for time-sensitive clinical and industrial applications. However, practical systems…
With the rapid advancement of diffusion-based generative models, Stable Diffusion (SD) has emerged as a state-of-the-art framework for high-fidelity im-age synthesis. However, existing SD models suffer from suboptimal feature aggregation,…
Phase retrieval aims to recover a signal from intensity-only measurements, a fundamental problem in many fields such as imaging, holography, optical computing, crystallography, and microscopy. Although there are several well-known phase…
This paper proposes a sparse regression method that continuously interpolates between Forward Stepwise selection (FS) and the LASSO. When tuned appropriately, our solutions are much sparser than typical LASSO fits but, unlike FS fits,…
Infrared and visible image fusion (IVIF) is essential for integrating thermal saliency with textural details to support downstream perception. However, most existing approaches suffer from "semantic blindness," leading to the erroneous…
Implicit Neural Representations (INRs) have emerged as a powerful alternative to traditional pixel-based formats by modeling images as continuous functions over spatial coordinates. A key challenge, however, lies in the spectral bias of…