Related papers: AesFormer: Transform Everyday Photos into Beautifu…
Despite rapid advances in photorealistic video generation, real-world applications such as filmmaking require video aesthetics, e.g., harmonious colors and cinematic lighting, beyond visual fidelity. Prior work on visual aesthetics largely…
Editing flat-looking images into stunning photographs requires skill and time. Automated image enhancement algorithms have attracted increased interest by generating high-quality images without user interaction. However, the quality…
Neural style transfer (NST) has evolved significantly in recent years. Yet, despite its rapid progress and advancement, existing NST methods either struggle to transfer aesthetic information from a style effectively or suffer from high…
The highly abstract nature of image aesthetics perception (IAP) poses significant challenge for current multimodal large language models (MLLMs). The lack of human-annotated multi-modality aesthetic data further exacerbates this dilemma,…
Absolute Pose Regression (APR) methods use deep neural networks to directly regress camera poses from RGB images. However, the predominant APR architectures only rely on 2D operations during inference, resulting in limited accuracy of pose…
Traditional photographic image editing typically requires users to possess sufficient aesthetic understanding to provide appropriate instructions for adjusting image quality and camera parameters. However, this paradigm relies on explicit…
Composition matters during the photo-taking process, yet many casual users struggle to frame well-composed images. To provide composition guidance, we introduce PhotoFramer, a multi-modal composition instruction framework. Given a poorly…
Aesthetic-driven image cropping is crucial for applications like view recommendation and thumbnail generation, where visual appeal significantly impacts user engagement. A key factor in visual appeal is composition--the deliberate…
We present EgoPoseFormer, a simple yet effective transformer-based model for stereo egocentric human pose estimation. The main challenge in egocentric pose estimation is overcoming joint invisibility, which is caused by self-occlusion or a…
Photo restoration technology enables preserving visual memories in photographs. However, physical prints are vulnerable to various forms of deterioration, ranging from physical damage to loss of image quality, etc. While restoration by…
Blind face restoration is to recover a high-quality face image from unknown degradations. As face image contains abundant contextual information, we propose a method, RestoreFormer, which explores fully-spatial attentions to model…
Anti-facial recognition (AFR) image filters alter images in ways that are subtle to people but blinding to computer vision. Yet, despite widespread interest in these technologies to subvert surveillance, users rarely use them in practice --…
Real world images often have highly imbalanced content density. Some areas are very uniform, e.g., large patches of blue sky, while other areas are scattered with many small objects. Yet, the commonly used successive grid downsampling…
We introduce EnhanceGAN, an adversarial learning based model that performs automatic image enhancement. Traditional image enhancement frameworks typically involve training models in a fully-supervised manner, which require expensive…
Aspect ratio and spatial layout are two of the principal factors determining the aesthetic value of a photograph. But, incorporating these into the traditional convolution-based frameworks for the task of image aesthetics assessment is…
Blind face restoration aims at recovering high-quality face images from those with unknown degradations. Current algorithms mainly introduce priors to complement high-quality details and achieve impressive progress. However, most of these…
The task of macro- and micro-expression spotting aims to precisely localize and categorize temporal expression instances within untrimmed videos. Given the sparse distribution and varying durations of expressions, existing anchor-based…
Multimodal large language models (MLLMs) are well suited to image aesthetic assessment, as they can capture high-level aesthetic features leveraging their cross-modal understanding capacity. However, the scarcity of multimodal aesthetic…
Replacing the background and simultaneously adjusting foreground objects is a challenging task in image editing. Current techniques for generating such images relies heavily on user interactions with image editing softwares, which is a…
Compared to frame-based methods, computational neuromorphic imaging using event cameras offers significant advantages, such as minimal motion blur, enhanced temporal resolution, and high dynamic range. The multi-view consistency of Neural…