Related papers: Implicit Style-Content Separation using B-LoRA

Single image super-resolution (SR) aims to estimate a high-resolution (HR) image from a lowresolution (LR) input. Image priors are commonly learned to regularize the otherwise seriously ill-posed SR problem, either using external LR-HR…

Photorealism is a complex concept that cannot easily be formulated mathematically. Deep Photo Style Transfer is an attempt to transfer the style of a reference image to a content image while preserving its photorealism. This is achieved by…

Processing visual data often involves small adjustments or sequences of changes, e.g., image filtering, surface smoothing, and animation. While established graphics techniques like normal mapping and video compression exploit redundancy to…

Continual Learning (CL) requires models to sequentially adapt to new tasks without forgetting old knowledge. Recently, Low-Rank Adaptation (LoRA), a representative Parameter-Efficient Fine-Tuning (PEFT) method, has gained increasing…

Remote sensing (RS) imagery, requiring specialized satellites to collect and being difficult to annotate, suffers from data scarcity and class imbalance in certain spectrums. Due to data scarcity, training any large-scale RS models from…

Low-Rank Adaptation (LoRA) has become a widely adopted technique in text-to-image diffusion models, enabling the personalisation of visual concepts such as characters, styles, and objects. However, existing approaches struggle to…

Generating images in a consistent reference visual style remains a challenging computer vision task. State-of-the-art methods aiming for style-consistent generation struggle to effectively separate semantic content from stylistic elements,…

Style transfer aims to fuse the artistic representation of a style image with the structural information of a content image. Existing methods train specific networks or utilize pre-trained models to learn content and style features.…

Low-rank adaption (LoRA) is a prominent method that adds a small number of learnable parameters to the frozen pre-trained weights for parameter-efficient fine-tuning. Prompted by the question, ``Can we make its representation enough with…

The personalized text-to-image generation has rapidly advanced with the emergence of Stable Diffusion. Existing methods, which typically fine-tune models using embedded identifiers, often struggle with insufficient stylization and…

Advancements in deep image synthesis techniques, such as generative adversarial networks (GANs) and diffusion models (DMs), have ushered in an era of generating highly realistic images. While this technological progress has captured…

Personalized text-to-image generation has gained significant attention for its capability to generate high-fidelity portraits of specific identities conditioned on user-defined prompts. Existing methods typically involve test-time…

The persistent challenge of medical image synthesis posed by the scarcity of annotated data and the need to synthesize `missing modalities' for multi-modal analysis, underscored the imperative development of effective synthesis methods.…

Low-rank adaptation (LoRA) is widely used for parameter-efficient fine-tuning, but its standard all-token, all-head design ignores the heterogeneous structure of vision language model (VLM) inputs. We introduce \emph{Image-LoRA}, a…

While Multimodal Large Language Models (MLLMs) excel at generalizing across modalities and tasks, effectively adapting them to specific downstream tasks while simultaneously retaining both general and specialized knowledge remains…

Artistic style transfer aims to use a style image and a content image to synthesize a target image that retains the same artistic expression as the style image while preserving the basic content of the content image. Many recently proposed…

Continual Learning (CL) with foundation models has recently emerged as a promising paradigm to exploit abundant knowledge acquired during pre-training for tackling sequential tasks. However, existing prompt-based and Low-Rank…

Low-Rank Adaptation (LoRA) lowers the computational and memory overhead of fine-tuning large models by updating a low-dimensional subspace of the pre-trained weight matrix. Albeit efficient, LoRA exhibits suboptimal convergence and…

Controlling the degree of stylization in the Neural Style Transfer (NST) is a little tricky since it usually needs hand-engineering on hyper-parameters. In this paper, we propose the first deep Reinforcement Learning (RL) based architecture…

In this work, we present a new framework for the stylization of text-based binary images. First, our method stylizes the stroke-based geometric shape like text, symbols and icons in the target binary image based on an input style image.…