Related papers: HiMat: DiT-based Ultra-High Resolution SVBRDF Gene…

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…

We tackle the problem of generating highly realistic and plausible mirror reflections using diffusion-based generative models. We formulate this problem as an image inpainting task, allowing for more user control over the placement of…

Diffusion Transformers (DiTs) have achieved state-of-the-art (SOTA) image generation quality but suffer from high latency and memory inefficiency, making them difficult to deploy on resource-constrained devices. One major efficiency…

In RGB-D semantic segmentation for indoor scenes, a key challenge is effectively integrating the rich color information from RGB images with the spatial distance information from depth images. However, most existing methods overlook the…

In medical imaging, the diffusion models have shown great potential for synthetic image generation tasks. However, these approaches often lack the interpretable connections between the generated and real images and can create anatomically…

Diffusion-based approaches have recently driven remarkable progress in real-world image super-resolution (SR). However, existing methods still struggle to simultaneously preserve fine details and ensure high-fidelity reconstruction, often…

Generative models trained on internet-scale data are capable of generating novel and realistic texts, images, and videos. A natural next question is whether these models can advance science, for example by generating novel stable materials.…

High-quality material generation is key for virtual environment authoring and inverse rendering. We propose MaterialPicker, a multi-modal material generator leveraging a Diffusion Transformer (DiT) architecture, improving and simplifying…

LED Virtual Production (VP) uses large LED volumes to render backgrounds in real time, enabling in-camera visual effects but making post-shot changes labor-intensive. We address this with CineMatte, a robust background matting framework for…

Achieving high-precision light manipulation is crucial for delivering information through complex media with high fidelity. However, existing spatial light modulation devices face a fundamental tradeoff between speed and accuracy. Digital…

Metasurfaces are ultrathin, engineered materials composed of nanostructures that manipulate light in ways unattainable by natural materials. Recent advances have leveraged computational optimization, machine learning, and deep learning to…

High-resolution lithographic techniques are often limited by low volumetric throughput, since there is no universal and scalable manufacturing process that can produce 3D metasurfaces. In this work, we demonstrate a high-speed holographic…

Deep learning-based super-resolution (SR) methods often perform pixel-wise computations uniformly across entire images, even in homogeneous regions where high-resolution refinement is redundant. We propose the Quadtree Diffusion Model…

This paper explores image modeling from the frequency space and introduces DCTdiff, an end-to-end diffusion generative paradigm that efficiently models images in the discrete cosine transform (DCT) space. We investigate the design space of…

Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration. To address these issues, we propose a robust and efficient…

Estimating scene lighting from a single image or video remains a longstanding challenge in computer vision and graphics. Learning-based approaches are constrained by the scarcity of ground-truth HDR environment maps, which are expensive to…

Recent approaches for segmentation have leveraged pretrained generative models as feature extractors, treating segmentation as a downstream adaptation task via indirect feature retrieval. This implicit use suffers from a fundamental…

In this paper, we introduce DiffusionMat, a novel image matting framework that employs a diffusion model for the transition from coarse to refined alpha mattes. Diverging from conventional methods that utilize trimaps merely as loose…

Traditional speech enhancement methods often oversimplify the task of restoration by focusing on a single type of distortion. Generative models that handle multiple distortions frequently struggle with phone reconstruction and…

Video super-resolution (VSR) seeks to reconstruct high-resolution frames from low-resolution inputs. While diffusion-based methods have substantially improved perceptual quality, extending them to video remains challenging for two reasons:…