Related papers: RAW-Adapter: Adapting Pre-trained Visual Model to …
The raw-RGB colors of a camera sensor vary due to the spectral sensitivity differences across different sensor makes and models. This paper focuses on the task of mapping between different sensor raw-RGB color spaces. Prior work addressed…
In recent years, with the rapid advancement of transformer models, transformer-based multimodal architectures have found wide application in various downstream tasks, including but not limited to Image Captioning, Visual Question Answering…
Recent adaptations can boost the low-shot capability of Contrastive Vision-Language Pre-training (CLIP) by effectively facilitating knowledge transfer. However, these adaptation methods are usually operated on the global view of an input…
We introduce the BIR-Adapter, a parameter-efficient diffusion adapter for blind image restoration. Diffusion-based restoration methods have demonstrated promising performance in addressing this fundamental problem in computer vision,…
The advent of high-capacity pre-trained models has revolutionized problem-solving in computer vision, shifting the focus from training task-specific models to adapting pre-trained models. Consequently, effectively adapting large pre-trained…
Class-incremental learning is a challenging problem, where the goal is to train a model that can classify data from an increasing number of classes over time. With the advancement of vision-language pre-trained models such as CLIP, they…
RAW to sRGB mapping, which aims to convert RAW images from smartphones into RGB form equivalent to that of Digital Single-Lens Reflex (DSLR) cameras, has become an important area of research. However, current methods often ignore the…
Vision transformers in vision-language models typically use the same amount of compute for every image, regardless of whether it is simple or complex. We propose ICAR (Image Complexity-Aware Retrieval), an adaptive computation approach that…
Recently, fine-tuning language models pre-trained on large text corpora have provided huge improvements on vision-and-language (V&L) tasks as well as on pure language tasks. However, fine-tuning the entire parameter set of pre-trained…
What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step to improve image…
The application of the context-adaptive entropy model significantly improves the rate-distortion (R-D) performance, in which hyperpriors and autoregressive models are jointly utilized to effectively capture the spatial redundancy of the…
In AI-generated image detection, current cutting-edge methods typically adapt pre-trained foundation models through partial-parameter fine-tuning. However, these approaches often struggle to generalize to forgeries from unseen generators,…
Image reconstruction from corrupted images is crucial across many domains. Most reconstruction networks are trained on post-ISP sRGB images, even though the image-signal-processing pipeline irreversibly mixes colors, clips dynamic range,…
Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally…
Current face reenactment and swapping methods mainly rely on GAN frameworks, but recent focus has shifted to pre-trained diffusion models for their superior generation capabilities. However, training these models is resource-intensive, and…
Adapter-based parameter-efficient transfer learning has achieved exciting results in vision-language models. Traditional adapter methods often require training or fine-tuning, facing challenges such as insufficient samples or resource…
Compared to RGB images, raw sensor data provides a richer representation of information, which is crucial for accurate recognition, particularly under challenging conditions such as low-light environments. The traditional Image Signal…
White balance (WB) is a key step in the image signal processor (ISP) pipeline that mitigates color casts caused by varying illumination and restores the scene's true colors. Currently, sRGB-based WB editing for post-ISP WB correction is…
Recent work has shown that learned image compression strategies can outperform standard hand-crafted compression algorithms that have been developed over decades of intensive research on the rate-distortion trade-off. With growing…
Real-world imaging systems acquire measurements that are degraded by noise, optical aberrations, and other imperfections that make image processing for human viewing and higher-level perception tasks challenging. Conventional cameras…