Related papers: Banding vs. Quality: Perceptual Impact and Objecti…
Increasing the frame rate of a 3D video generally results in improved Quality of Experience (QoE). However, higher frame rates involve a higher degree of complexity in capturing, transmission, storage, and display. The question that arises…
The field of automatic image inpainting has progressed rapidly in recent years, but no one has yet proposed a standard method of evaluating algorithms. This absence is due to the problem's challenging nature: image-inpainting algorithms…
Pose estimation is usually tackled as either a bin classification or a regression problem. In both cases, the idea is to directly predict the pose of an object. This is a non-trivial task due to appearance variations between similar poses…
Video frame interpolation (VFI) serves as a useful tool for many video processing applications. Recently, it has also been applied in the video compression domain for enhancing both conventional video codecs and learning-based compression…
Vision-language models can encode societal biases and stereotypes, but there are challenges to measuring and mitigating these multimodal harms due to lacking measurement robustness and feature degradation. To address these challenges, we…
Panoramic videos have the advantage of providing an immersive and interactive viewing experience. Nevertheless, their spherical nature gives rise to various and uncertain user viewing behaviors, which poses significant challenges for…
Video dimensions are continuously increasing to provide more realistic and immersive experiences to global streaming and social media viewers. However, increments in video parameters such as spatial resolution and frame rate are inevitably…
Recently, point clouds have shown to be a promising way to represent 3D visual data for a wide range of immersive applications, from augmented reality to autonomous cars. Emerging imaging sensors have made easier to perform richer and…
Large Multimodal Models (LMMs) have shown promise for video quality assessment, but most methods still predict an absolute score for each video. Such pointwise supervision often mixes perceptual quality with dataset-specific calibration,…
Existing video captioning approaches typically require to first sample video frames from a decoded video and then conduct a subsequent process (e.g., feature extraction and/or captioning model learning). In this pipeline, manual frame…
Videos often have to be transmitted and stored at low bitrates due to poor network connectivity during adaptive bitrate streaming. Designing optimal bitrate ladders that would select the perceptually-optimized resolution, frame-rate, and…
Modern computer vision foundation models are trained on massive amounts of data, incurring large economic and environmental costs. Recent research has suggested that improving data quality can significantly reduce the need for data…
Blind or no-reference (NR) perceptual picture quality prediction is a difficult, unsolved problem of great consequence to the social and streaming media industries that impacts billions of viewers daily. Unfortunately, popular NR prediction…
Neural networks are prone to adversarial attacks. In general, such attacks deteriorate the quality of the input by either slightly modifying most of its pixels, or by occluding it with a patch. In this paper, we propose a method that keeps…
Nowadays digital image compression and decompression techniques are very much important. So our aim is to calculate the quality of face and other regions of the compressed image with respect to the original image. Image segmentation is…
In this work, we investigate facial anonymization techniques in 360{\deg} videos and assess their influence on the perceived realism, anonymization effect, and presence of participants. In comparison to traditional footage, 360{\deg} videos…
Generative AI has revolutionised visual content editing, empowering users to effortlessly modify images and videos. However, not all edits are equal. To perform realistic edits in domains such as natural image or medical imaging,…
Neural network quantization is a critical technique for deploying models on resource-limited devices. Despite its widespread use, the impact of quantization on model perceptual fields, particularly in relation to class activation maps…
Wide-angle video is favored for its wide viewing angle and ability to capture a large area of scenery, making it an ideal choice for sports and adventure recording. However, wide-angle video is prone to deformation, exposure and other…
The CLIP model has been recently proven to be very effective for a variety of cross-modal tasks, including the evaluation of captions generated from vision-and-language architectures. In this paper, we propose a new recipe for a…