Related papers: ScaleDiff: Higher-Resolution Image Synthesis via E…
Diffusion models are powerful, but they require a lot of time and data to train. We propose Patch Diffusion, a generic patch-wise training framework, to significantly reduce the training time costs while improving data efficiency, which…
Recently Data-Free Knowledge Distillation (DFKD) has garnered attention and can transfer knowledge from a teacher neural network to a student neural network without requiring any access to training data. Although diffusion models are adept…
Text-to-image generation via Stable Diffusion models (SDM) have demonstrated remarkable capabilities. However, their computational intensity, particularly in the iterative denoising process, hinders real-time deployment in latency-sensitive…
We propose SymDiff, a method for constructing equivariant diffusion models using the framework of stochastic symmetrisation. SymDiff resembles a learned data augmentation that is deployed at sampling time, and is lightweight,…
Recently, the transfer application of diffusion models in super-resolu-tion tasks has faced the problem ofdecreased fidelity. Due to the inherent randomsampling characteristics ofdiffusion models, direct application in super-resolu-tion…
Transferring visual style between images while preserving semantic correspondence between similar objects remains a central challenge in computer vision. While existing methods have made great strides, most of them operate at global level…
This paper reports on the development of \textbf{a novel style guided diffusion model (SGDiff)} which overcomes certain weaknesses inherent in existing models for image synthesis. The proposed SGDiff combines image modality with a…
Diffusion models have shown remarkable success across generative tasks, yet their high computational demands challenge deployment on resource-limited platforms. This paper investigates a critical question for compute-optimal diffusion model…
Diffusion models have made tremendous progress in text-driven image and video generation. Now text-to-image foundation models are widely applied to various downstream image synthesis tasks, such as controllable image generation and image…
Text-to-image diffusion models have achieved remarkable fidelity in synthesizing images from explicit text prompts, yet exhibit a critical deficiency in processing implicit prompts that require deep-level world knowledge, ranging from…
Text-based image segmentation aims to delineate object boundaries within an image from text prompts, offering higher flexibility and broader application scope compared to traditional fixed-category segmentation tasks. Recent studies have…
The diffusion model has demonstrated superior performance in synthesizing diverse and high-quality images for text-guided image translation. However, there remains room for improvement in both the formulation of text prompts and the…
The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled.…
Previous raw image-based low-light image enhancement methods predominantly relied on feed-forward neural networks to learn deterministic mappings from low-light to normally-exposed images. However, they failed to capture critical…
Neural Radiance Fields and 3D Gaussian Splatting have advanced novel view synthesis, yet still rely on dense inputs and often degrade at extrapolated views. Recent approaches leverage generative models, such as diffusion models, to provide…
Diffusion-based text-to-image generation models have significantly advanced the field of art content synthesis. However, current portrait stylization methods generally require either model fine-tuning based on examples or the employment of…
Diffusionmodels(DMs)havedemonstratedremarkableachievements in synthesizing images of high fidelity and diversity. However, the extensive computational requirements and slow generative speed of diffusion models have limited their widespread…
Recent breakthroughs in text-to-image synthesis have been driven by diffusion models trained on billions of image-text pairs. Adapting this approach to 3D synthesis would require large-scale datasets of labeled 3D data and efficient…
Existing low-light image enhancement (LIE) methods have achieved noteworthy success in solving synthetic distortions, yet they often fall short in practical applications. The limitations arise from two inherent challenges in real-world LIE:…
Generative graph models struggle to scale due to the need to predict the existence or type of edges between all node pairs. To address the resulting quadratic complexity, existing scalable models often impose restrictive assumptions such as…