FakeBench: Uncover the Achilles' Heels of Fake Images with Large Multimodal Models

Recently, fake images generated by artificial intelligence (AI) models have become indistinguishable from the real, exerting new challenges for fake image detection models. To this extent, simple binary judgments of real or fake seem less convincing and credible due to the absence of human-understandable explanations. Fortunately, Large Multimodal Models (LMMs) bring possibilities to materialize the judgment process while their performance remains undetermined. Therefore, we propose FakeBench, the first-of-a-kind benchmark towards transparent defake, consisting of fake images with human language descriptions on forgery signs. FakeBench gropes for two open questions of LMMs: (1) can LMMs distinguish fake images generated by AI, and (2) how do LMMs distinguish fake images? In specific, we construct the FakeClass dataset with 6k diverse-sourced fake and real images, each equipped with a Question&Answer pair concerning the authenticity of images, which are utilized to benchmark the detection ability. To examine the reasoning and interpretation abilities of LMMs, we present the FakeClue dataset, consisting of 15k pieces of descriptions on the telltale clues revealing the falsification of fake images. Besides, we construct the FakeQA to measure the LMMs' open-question answering ability on fine-grained authenticity-relevant aspects. Our experimental results discover that current LMMs possess moderate identification ability, preliminary interpretation and reasoning ability, and passable open-question answering ability for image defake. The FakeBench will be made publicly available soon.

NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results

This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i.e., Kuaishou/Kwai Platform. The KVQ database is divided into three parts, including 2926 videos for training, 420 videos for validation, and 854 videos for testing. The purpose is to build new benchmarks and advance the development of S-UGC VQA. The competition had 200 participants and 13 teams submitted valid solutions for the final testing phase. The proposed solutions achieved state-of-the-art performances for S-UGC VQA. The project can be found at https://github.com/lixinustc/KVQChallenge-CVPR-NTIRE2024.

AesExpert: Towards Multi-modality Foundation Model for Image Aesthetics Perception

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, resulting in MLLMs falling short of aesthetics perception capabilities. To address the above challenge, we first introduce a comprehensively annotated Aesthetic Multi-Modality Instruction Tuning (AesMMIT) dataset, which serves as the footstone for building multi-modality aesthetics foundation models. Specifically, to align MLLMs with human aesthetics perception, we construct a corpus-rich aesthetic critique database with 21,904 diverse-sourced images and 88K human natural language feedbacks, which are collected via progressive questions, ranging from coarse-grained aesthetic grades to fine-grained aesthetic descriptions. To ensure that MLLMs can handle diverse queries, we further prompt GPT to refine the aesthetic critiques and assemble the large-scale aesthetic instruction tuning dataset, i.e. AesMMIT, which consists of 409K multi-typed instructions to activate stronger aesthetic capabilities. Based on the AesMMIT database, we fine-tune the open-sourced general foundation models, achieving multi-modality Aesthetic Expert models, dubbed AesExpert. Extensive experiments demonstrate that the proposed AesExpert models deliver significantly better aesthetic perception performances than the state-of-the-art MLLMs, including the most advanced GPT-4V and Gemini-Pro-Vision. Source data will be available at https://github.com/yipoh/AesExpert.

Towards Open-ended Visual Quality Comparison

Comparative settings (e.g. pairwise choice, listwise ranking) have been adopted by a wide range of subjective studies for image quality assessment (IQA), as it inherently standardizes the evaluation criteria across different observers and offer more clear-cut responses. In this work, we extend the edge of emerging large multi-modality models (LMMs) to further advance visual quality comparison into open-ended settings, that 1) can respond to open-range questions on quality comparison; 2) can provide detailed reasonings beyond direct answers. To this end, we propose the Co-Instruct. To train this first-of-its-kind open-source open-ended visual quality comparer, we collect the Co-Instruct-562K dataset, from two sources: (a) LLM-merged single image quality description, (b) GPT-4V "teacher" responses on unlabeled data. Furthermore, to better evaluate this setting, we propose the MICBench, the first benchmark on multi-image comparison for LMMs. We demonstrate that Co-Instruct not only achieves in average 30% higher accuracy than state-of-the-art open-source LMMs, but also outperforms GPT-4V (its teacher), on both existing related benchmarks and the proposed MICBench. Our model is published at https://huggingface.co/q-future/co-instruct.

Fine Structure-Aware Sampling: A New Sampling Training Scheme for Pixel-Aligned Implicit Models in Single-View Human Reconstruction

Pixel-aligned implicit models, such as PIFu, PIFuHD, and ICON, are used for single-view clothed human reconstruction. These models need to be trained using a sampling training scheme. Existing sampling training schemes either fail to capture thin surfaces (e.g. ears, fingers) or cause noisy artefacts in reconstructed meshes. To address these problems, we introduce Fine Structured-Aware Sampling (FSS), a new sampling training scheme to train pixel-aligned implicit models for single-view human reconstruction. FSS resolves the aforementioned problems by proactively adapting to the thickness and complexity of surfaces. In addition, unlike existing sampling training schemes, FSS shows how normals of sample points can be capitalized in the training process to improve results. Lastly, to further improve the training process, FSS proposes a mesh thickness loss signal for pixel-aligned implicit models. It becomes computationally feasible to introduce this loss once a slight reworking of the pixel-aligned implicit function framework is carried out. Our results show that our methods significantly outperform SOTA methods qualitatively and quantitatively. Our code is publicly available at https://github.com/kcyt/FSS.

MISC: Ultra-low Bitrate Image Semantic Compression Driven by Large Multimodal Model

With the evolution of storage and communication protocols, ultra-low bitrate image compression has become a highly demanding topic. However, existing compression algorithms must sacrifice either consistency with the ground truth or perceptual quality at ultra-low bitrate. In recent years, the rapid development of the Large Multimodal Model (LMM) has made it possible to balance these two goals. To solve this problem, this paper proposes a method called Multimodal Image Semantic Compression (MISC), which consists of an LMM encoder for extracting the semantic information of the image, a map encoder to locate the region corresponding to the semantic, an image encoder generates an extremely compressed bitstream, and a decoder reconstructs the image based on the above information. Experimental results show that our proposed MISC is suitable for compressing both traditional Natural Sense Images (NSIs) and emerging AI-Generated Images (AIGIs) content. It can achieve optimal consistency and perception results while saving 50% bitrate, which has strong potential applications in the next generation of storage and communication. The code will be released on https://github.com/lcysyzxdxc/MISC.

A Benchmark for Multi-modal Foundation Models on Low-level Vision: from Single Images to Pairs

The rapid development of Multi-modality Large Language Models (MLLMs) has navigated a paradigm shift in computer vision, moving towards versatile foundational models. However, evaluating MLLMs in low-level visual perception and understanding remains a yet-to-explore domain. To this end, we design benchmark settings to emulate human language responses related to low-level vision: the low-level visual perception (A1) via visual question answering related to low-level attributes (e.g. clarity, lighting); and the low-level visual description (A2), on evaluating MLLMs for low-level text descriptions. Furthermore, given that pairwise comparison can better avoid ambiguity of responses and has been adopted by many human experiments, we further extend the low-level perception-related question-answering and description evaluations of MLLMs from single images to image pairs. Specifically, for perception (A1), we carry out the LLVisionQA+ dataset, comprising 2,990 single images and 1,999 image pairs each accompanied by an open-ended question about its low-level features; for description (A2), we propose the LLDescribe+ dataset, evaluating MLLMs for low-level descriptions on 499 single images and 450 pairs. Additionally, we evaluate MLLMs on assessment (A3) ability, i.e. predicting score, by employing a softmax-based approach to enable all MLLMs to generate quantifiable quality ratings, tested against human opinions in 7 image quality assessment (IQA) datasets. With 24 MLLMs under evaluation, we demonstrate that several MLLMs have decent low-level visual competencies on single images, but only GPT-4V exhibits higher accuracy on pairwise comparisons than single image evaluations (like humans). We hope that our benchmark will motivate further research into uncovering and enhancing these nascent capabilities of MLLMs. Datasets will be available at https://github.com/Q-Future/Q-Bench.

AesBench: An Expert Benchmark for Multimodal Large Language Models on Image Aesthetics Perception

With collective endeavors, multimodal large language models (MLLMs) are undergoing a flourishing development. However, their performances on image aesthetics perception remain indeterminate, which is highly desired in real-world applications. An obvious obstacle lies in the absence of a specific benchmark to evaluate the effectiveness of MLLMs on aesthetic perception. This blind groping may impede the further development of more advanced MLLMs with aesthetic perception capacity. To address this dilemma, we propose AesBench, an expert benchmark aiming to comprehensively evaluate the aesthetic perception capacities of MLLMs through elaborate design across dual facets. (1) We construct an Expert-labeled Aesthetics Perception Database (EAPD), which features diversified image contents and high-quality annotations provided by professional aesthetic experts. (2) We propose a set of integrative criteria to measure the aesthetic perception abilities of MLLMs from four perspectives, including Perception (AesP), Empathy (AesE), Assessment (AesA) and Interpretation (AesI). Extensive experimental results underscore that the current MLLMs only possess rudimentary aesthetic perception ability, and there is still a significant gap between MLLMs and humans. We hope this work can inspire the community to engage in deeper explorations on the aesthetic potentials of MLLMs. Source data will be available at https://github.com/yipoh/AesBench.

Towards A Better Metric for Text-to-Video Generation

Generative models have demonstrated remarkable capability in synthesizing high-quality text, images, and videos. For video generation, contemporary text-to-video models exhibit impressive capabilities, crafting visually stunning videos. Nonetheless, evaluating such videos poses significant challenges. Current research predominantly employs automated metrics such as FVD, IS, and CLIP Score. However, these metrics provide an incomplete analysis, particularly in the temporal assessment of video content, thus rendering them unreliable indicators of true video quality. Furthermore, while user studies have the potential to reflect human perception accurately, they are hampered by their time-intensive and laborious nature, with outcomes that are often tainted by subjective bias. In this paper, we investigate the limitations inherent in existing metrics and introduce a novel evaluation pipeline, the Text-to-Video Score (T2VScore). This metric integrates two pivotal criteria: (1) Text-Video Alignment, which scrutinizes the fidelity of the video in representing the given text description, and (2) Video Quality, which evaluates the video's overall production caliber with a mixture of experts. Moreover, to evaluate the proposed metrics and facilitate future improvements on them, we present the TVGE dataset, collecting human judgements of 2,543 text-to-video generated videos on the two criteria. Experiments on the TVGE dataset demonstrate the superiority of the proposed T2VScore on offering a better metric for text-to-video generation.

Q-Refine: A Perceptual Quality Refiner for AI-Generated Image

With the rapid evolution of the Text-to-Image (T2I) model in recent years, their unsatisfactory generation result has become a challenge. However, uniformly refining AI-Generated Images (AIGIs) of different qualities not only limited optimization capabilities for low-quality AIGIs but also brought negative optimization to high-quality AIGIs. To address this issue, a quality-award refiner named Q-Refine is proposed. Based on the preference of the Human Visual System (HVS), Q-Refine uses the Image Quality Assessment (IQA) metric to guide the refining process for the first time, and modify images of different qualities through three adaptive pipelines. Experimental shows that for mainstream T2I models, Q-Refine can perform effective optimization to AIGIs of different qualities. It can be a general refiner to optimize AIGIs from both fidelity and aesthetic quality levels, thus expanding the application of the T2I generation models.