Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities

The advent of AI has influenced many aspects of human life, from self-driving cars and intelligent chatbots to text-based image and video generation models capable of creating realistic images and videos based on user prompts (text-to-image, image-to-image, and image-to-video). AI-based methods for image and video super resolution, video frame interpolation, denoising, and compression have already gathered significant attention and interest in the industry and some solutions are already being implemented in real-world products and services. However, to achieve widespread integration and acceptance, AI-generated and enhanced content must be visually accurate, adhere to intended use, and maintain high visual quality to avoid degrading the end user's quality of experience (QoE). One way to monitor and control the visual "quality" of AI-generated and -enhanced content is by deploying Image Quality Assessment (IQA) and Video Quality Assessment (VQA) models. However, most existing IQA and VQA models measure visual fidelity in terms of "reconstruction" quality against a pristine reference content and were not designed to assess the quality of "generative" artifacts. To address this, newer metrics and models have recently been proposed, but their performance evaluation and overall efficacy have been limited by datasets that were too small or otherwise lack representative content and/or distortion capacity; and by performance measures that can accurately report the success of an IQA/VQA model for "GenAI". This paper examines the current shortcomings and possibilities presented by AI-generated and enhanced image and video content, with a particular focus on end-user perceived quality. Finally, we discuss open questions and make recommendations for future work on the "GenAI" quality assessment problems, towards further progressing on this interesting and relevant field of research.

Constructing Per-Shot Bitrate Ladders using Visual Information Fidelity

Adaptive video streaming allows for the construction of bitrate ladders that deliver perceptually optimized visual quality to viewers under bandwidth constraints. Two common approaches to adaptation are per-title encoding and per-shot encoding. The former involves encoding each program, movie, or other content in a manner that is perceptually- and bandwidth-optimized for that content but is otherwise fixed. The latter is a more granular approach that optimizes the encoding parameters for each scene or shot (however defined) of a video content. Per-shot video encoding, as pioneered by Netflix, encodes on a per-shot basis using the Dynamic Optimizer (DO). Under the control of the VMAF perceptual video quality prediction engine, the DO delivers high-quality videos to millions of viewers at considerably reduced bitrates than per-title or fixed bitrate ladder encoding. A variety of per-title and per-shot encoding techniques have been recently proposed that seek to reduce computational overhead and to construct optimal bitrate ladders more efficiently using low-level features extracted from source videos. Here we develop a perceptually optimized method of constructing optimal per-shot bitrate and quality ladders, using an ensemble of low-level features and Visual Information Fidelity (VIF) features extracted from different scales and subbands. We compare the performance of our model, which we call VIF-ladder, against other content-adaptive bitrate ladder prediction methods, counterparts of them that we designed to construct quality ladders, a fixed bitrate ladder, and bitrate ladders constructed via exhaustive encoding using Bjontegaard delta metrics.

YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals

3D generation guided by text-to-image diffusion models enables the creation of visually compelling assets. However previous methods explore generation based on image or text. The boundaries of creativity are limited by what can be expressed through words or the images that can be sourced. We present YouDream, a method to generate high-quality anatomically controllable animals. YouDream is guided using a text-to-image diffusion model controlled by 2D views of a 3D pose prior. Our method generates 3D animals that are not possible to create using previous text-to-3D generative methods. Additionally, our method is capable of preserving anatomic consistency in the generated animals, an area where prior text-to-3D approaches often struggle. Moreover, we design a fully automated pipeline for generating commonly found animals. To circumvent the need for human intervention to create a 3D pose, we propose a multi-agent LLM that adapts poses from a limited library of animal 3D poses to represent the desired animal. A user study conducted on the outcomes of YouDream demonstrates the preference of the animal models generated by our method over others. Turntable results and code are released at https://youdream3d.github.io/

C3DAG: Controlled 3D Animal Generation using 3D pose guidance

Recent advancements in text-to-3D generation have demonstrated the ability to generate high quality 3D assets. However while generating animals these methods underperform, often portraying inaccurate anatomy and geometry. Towards ameliorating this defect, we present C3DAG, a novel pose-Controlled text-to-3D Animal Generation framework which generates a high quality 3D animal consistent with a given pose. We also introduce an automatic 3D shape creator tool, that allows dynamic pose generation and modification via a web-based tool, and that generates a 3D balloon animal using simple geometries. A NeRF is then initialized using this 3D shape using depth-controlled SDS. In the next stage, the pre-trained NeRF is fine-tuned using quadruped-pose-controlled SDS. The pipeline that we have developed not only produces geometrically and anatomically consistent results, but also renders highly controlled 3D animals, unlike prior methods which do not allow fine-grained pose control.

Joint Quality Assessment and Example-Guided Image Processing by Disentangling Picture Appearance from Content

The deep learning revolution has strongly impacted low-level image processing tasks such as style/domain transfer, enhancement/restoration, and visual quality assessments. Despite often being treated separately, the aforementioned tasks share a common theme of understanding, editing, or enhancing the appearance of input images without modifying the underlying content. We leverage this observation to develop a novel disentangled representation learning method that decomposes inputs into content and appearance features. The model is trained in a self-supervised manner and we use the learned features to develop a new quality prediction model named DisQUE. We demonstrate through extensive evaluations that DisQUE achieves state-of-the-art accuracy across quality prediction tasks and distortion types. Moreover, we demonstrate that the same features may also be used for image processing tasks such as HDR tone mapping, where the desired output characteristics may be tuned using example input-output pairs.

Cut-FUNQUE: An Objective Quality Model for Compressed Tone-Mapped High Dynamic Range Videos

High Dynamic Range (HDR) videos have enjoyed a surge in popularity in recent years due to their ability to represent a wider range of contrast and color than Standard Dynamic Range (SDR) videos. Although HDR video capture has seen increasing popularity because of recent flagship mobile phones such as Apple iPhones, Google Pixels, and Samsung Galaxy phones, a broad swath of consumers still utilize legacy SDR displays that are unable to display HDR videos. As result, HDR videos must be processed, i.e., tone-mapped, before streaming to a large section of SDR-capable video consumers. However, server-side tone-mapping involves automating decisions regarding the choices of tone-mapping operators (TMOs) and their parameters to yield high-fidelity outputs. Moreover, these choices must be balanced against the effects of lossy compression, which is ubiquitous in streaming scenarios. In this work, we develop a novel, efficient model of objective video quality named Cut-FUNQUE that is able to accurately predict the visual quality of tone-mapped and compressed HDR videos. Finally, we evaluate Cut-FUNQUE on a large-scale crowdsourced database of such videos and show that it achieves state-of-the-art accuracy.

Subjective Quality Assessment of Compressed Tone-Mapped High Dynamic Range Videos

High Dynamic Range (HDR) videos are able to represent wider ranges of contrasts and colors than Standard Dynamic Range (SDR) videos, giving more vivid experiences. Due to this, HDR videos are expected to grow into the dominant video modality of the future. However, HDR videos are incompatible with existing SDR displays, which form the majority of affordable consumer displays on the market. Because of this, HDR videos must be processed by tone-mapping them to reduced bit-depths to service a broad swath of SDR-limited video consumers. Here, we analyze the impact of tone-mapping operators on the visual quality of streaming HDR videos. To this end, we built the first large-scale subjectively annotated open-source database of compressed tone-mapped HDR videos, containing 15,000 tone-mapped sequences derived from 40 unique HDR source contents. The videos in the database were labeled with more than 750,000 subjective quality annotations, collected from more than 1,600 unique human observers. We demonstrate the usefulness of the new subjective database by benchmarking objective models of visual quality on it. We envision that the new LIVE Tone-Mapped HDR (LIVE-TMHDR) database will enable significant progress on HDR video tone mapping and quality assessment in the future. To this end, we make the database freely available to the community at https://live.ece.utexas.edu/research/LIVE_TMHDR/index.html

Subjective and Objective Analysis of Indian Social Media Video Quality

We conducted a large-scale subjective study of the perceptual quality of User-Generated Mobile Video Content on a set of mobile-originated videos obtained from the Indian social media platform ShareChat. The content viewed by volunteer human subjects under controlled laboratory conditions has the benefit of culturally diversifying the existing corpus of User-Generated Content (UGC) video quality datasets. There is a great need for large and diverse UGC-VQA datasets, given the explosive global growth of the visual internet and social media platforms. This is particularly true in regard to videos obtained by smartphones, especially in rapidly emerging economies like India. ShareChat provides a safe and cultural community oriented space for users to generate and share content in their preferred Indian languages and dialects. Our subjective quality study, which is based on this data, offers a boost of cultural, visual, and language diversification to the video quality research community. We expect that this new data resource will also allow for the development of systems that can predict the perceived visual quality of Indian social media videos, to control scaling and compression protocols for streaming, provide better user recommendations, and guide content analysis and processing. We demonstrate the value of the new data resource by conducting a study of leading blind video quality models on it, including a new model, called MoEVA, which deploys a mixture of experts to predict video quality. Both the new LIVE-ShareChat dataset and sample source code for MoEVA are being made freely available to the research community at https://github.com/sandeep-sm/LIVE-SC

A FUNQUE Approach to the Quality Assessment of Compressed HDR Videos

Recent years have seen steady growth in the popularity and availability of High Dynamic Range (HDR) content, particularly videos, streamed over the internet. As a result, assessing the subjective quality of HDR videos, which are generally subjected to compression, is of increasing importance. In particular, we target the task of full-reference quality assessment of compressed HDR videos. The state-of-the-art (SOTA) approach HDRMAX involves augmenting off-the-shelf video quality models, such as VMAF, with features computed on non-linearly transformed video frames. However, HDRMAX increases the computational complexity of models like VMAF. Here, we show that an efficient class of video quality prediction models named FUNQUE+ achieves SOTA accuracy. This shows that the FUNQUE+ models are flexible alternatives to VMAF that achieve higher HDR video quality prediction accuracy at lower computational cost.

Bitrate Ladder Construction using Visual Information Fidelity

Recently proposed perceptually optimized per-title video encoding methods provide better BD-rate savings than fixed bitrate-ladder approaches that have been employed in the past. However, a disadvantage of per-title encoding is that it requires significant time and energy to compute bitrate ladders. Over the past few years, a variety of methods have been proposed to construct optimal bitrate ladders including using low-level features to predict cross-over bitrates, optimal resolutions for each bitrate, predicting visual quality, etc. Here, we deploy features drawn from Visual Information Fidelity (VIF) (VIF features) extracted from uncompressed videos to predict the visual quality (VMAF) of compressed videos. We present multiple VIF feature sets extracted from different scales and subbands of a video to tackle the problem of bitrate ladder construction. Comparisons are made against a fixed bitrate ladder and a bitrate ladder obtained from exhaustive encoding using Bjontegaard delta metrics.