Searcharxiv⌕ Search

arXiv subjects

Chunyi Li

Publications and source records attributed to Chunyi Li.

At least 91 records · Page 5Linked to original sources
arXiv2023

Q-Boost: On Visual Quality Assessment Ability of Low-level Multi-Modality Foundation Models

Recent advancements in Multi-modality Large Language Models (MLLMs) have demonstrated remarkable capabilities in complex high-level vision tasks. However, the exploration of MLLM potential in visual quality assessment, a vital aspect of low-level vision, remains limited. To address this gap, we introduce Q-Boost, a novel strategy designed to enhance low-level MLLMs in image quality assessment (IQA) and video quality assessment (VQA) tasks, which is structured around two pivotal components: 1) Triadic-Tone Integration: Ordinary prompt design simply oscillates between the binary extremes of $positive$ and $negative$. Q-Boost innovates by incorporating a `middle ground' approach through $neutral$ prompts, allowing for a more balanced and detailed assessment. 2) Multi-Prompt Ensemble: Multiple quality-centric prompts are used to mitigate bias and acquire more accurate evaluation. The experimental results show that the low-level MLLMs exhibit outstanding zeros-shot performance on the IQA/VQA tasks equipped with the Q-Boost strategy.

cs.CV↗
arXiv2023

Q-Instruct: Improving Low-level Visual Abilities for Multi-modality Foundation Models

Multi-modality foundation models, as represented by GPT-4V, have brought a new paradigm for low-level visual perception and understanding tasks, that can respond to a broad range of natural human instructions in a model. While existing foundation models have shown exciting potentials on low-level visual tasks, their related abilities are still preliminary and need to be improved. In order to enhance these models, we conduct a large-scale subjective experiment collecting a vast number of real human feedbacks on low-level vision. Each feedback follows a pathway that starts with a detailed description on the low-level visual appearance (*e.g. clarity, color, brightness* of an image, and ends with an overall conclusion, with an average length of 45 words. The constructed **Q-Pathway** dataset includes 58K detailed human feedbacks on 18,973 images with diverse low-level appearance. Moreover, to enable foundation models to robustly respond to diverse types of questions, we design a GPT-participated conversion to process these feedbacks into diverse-format 200K instruction-response pairs. Experimental results indicate that the **Q-Instruct** consistently elevates low-level perception and understanding abilities across several foundational models. We anticipate that our datasets can pave the way for a future that general intelligence can perceive, understand low-level visual appearance and evaluate visual quality like a human. Our dataset, model zoo, and demo is published at: https://q-future.github.io/Q-Instruct.

cs.CV↗
arXiv2023

A Note on Spherical Bundles on K3 Surfaces

Some questions are posted at the end of Chapter 16 of Huybrechts' book 'Lectures on K3 Surfaces', concerning the bounded derived category of a K3 surface $D^b(S)$. Let $E$ be a spherical object in $D^b(S)$. The first question asks if there always exists a non-zero object $F$ satisfying RHom$(E,F)=0$. Further, let $E$ be a spherical bundle. The second question is whether $E$ is always semistable with respect to some polarization on $S$ and if there is a way to `count' spherical bundles with a fixed Mukai vector. In this note, we provide (partial) answers to these two questions. In the appendix, Genki Ouchi shows that any spherical twist associated to an $n$-spherical object on a smooth projective $n$-dimensional variety is not conjugate to a standard autoequivalence.

math.AG↗
arXiv2023

Advancing Zero-Shot Digital Human Quality Assessment through Text-Prompted Evaluation

Digital humans have witnessed extensive applications in various domains, necessitating related quality assessment studies. However, there is a lack of comprehensive digital human quality assessment (DHQA) databases. To address this gap, we propose SJTU-H3D, a subjective quality assessment database specifically designed for full-body digital humans. It comprises 40 high-quality reference digital humans and 1,120 labeled distorted counterparts generated with seven types of distortions. The SJTU-H3D database can serve as a benchmark for DHQA research, allowing evaluation and refinement of processing algorithms. Further, we propose a zero-shot DHQA approach that focuses on no-reference (NR) scenarios to ensure generalization capabilities while mitigating database bias. Our method leverages semantic and distortion features extracted from projections, as well as geometry features derived from the mesh structure of digital humans. Specifically, we employ the Contrastive Language-Image Pre-training (CLIP) model to measure semantic affinity and incorporate the Naturalness Image Quality Evaluator (NIQE) model to capture low-level distortion information. Additionally, we utilize dihedral angles as geometry descriptors to extract mesh features. By aggregating these measures, we introduce the Digital Human Quality Index (DHQI), which demonstrates significant improvements in zero-shot performance. The DHQI can also serve as a robust baseline for DHQA tasks, facilitating advancements in the field. The database and the code are available at https://github.com/zzc-1998/SJTU-H3D.

eess.IV↗
arXiv2023

AGIQA-3K: An Open Database for AI-Generated Image Quality Assessment

With the rapid advancements of the text-to-image generative model, AI-generated images (AGIs) have been widely applied to entertainment, education, social media, etc. However, considering the large quality variance among different AGIs, there is an urgent need for quality models that are consistent with human subjective ratings. To address this issue, we extensively consider various popular AGI models, generated AGI through different prompts and model parameters, and collected subjective scores at the perceptual quality and text-to-image alignment, thus building the most comprehensive AGI subjective quality database AGIQA-3K so far. Furthermore, we conduct a benchmark experiment on this database to evaluate the consistency between the current Image Quality Assessment (IQA) model and human perception, while proposing StairReward that significantly improves the assessment performance of subjective text-to-image alignment. We believe that the fine-grained subjective scores in AGIQA-3K will inspire subsequent AGI quality models to fit human subjective perception mechanisms at both perception and alignment levels and to optimize the generation result of future AGI models. The database is released on https://github.com/lcysyzxdxc/AGIQA-3k-Database.

cs.CV↗
arXiv2023

XGC-VQA: A unified video quality assessment model for User, Professionally, and Occupationally-Generated Content

With the rapid growth of Internet video data amounts and types, a unified Video Quality Assessment (VQA) is needed to inspire video communication with perceptual quality. To meet the real-time and universal requirements in providing such inspiration, this study proposes a VQA model from a classification of User Generated Content (UGC), Professionally Generated Content (PGC), and Occupationally Generated Content (OGC). In the time domain, this study utilizes non-uniform sampling, as each content type has varying temporal importance based on its perceptual quality. In the spatial domain, centralized downsampling is performed before the VQA process by utilizing a patch splicing/sampling mechanism to lower complexity for real-time assessment. The experimental results demonstrate that the proposed method achieves a median correlation of $0.7$ while limiting the computation time below 5s for three content types, which ensures that the communication experience of UGC, PGC, and OGC can be optimized altogether.

cs.MM↗
arXiv2023

A Perceptual Quality Assessment Exploration for AIGC Images

\underline{AI} \underline{G}enerated \underline{C}ontent (\textbf{AIGC}) has gained widespread attention with the increasing efficiency of deep learning in content creation. AIGC, created with the assistance of artificial intelligence technology, includes various forms of content, among which the AI-generated images (AGIs) have brought significant impact to society and have been applied to various fields such as entertainment, education, social media, etc. However, due to hardware limitations and technical proficiency, the quality of AIGC images (AGIs) varies, necessitating refinement and filtering before practical use. Consequently, there is an urgent need for developing objective models to assess the quality of AGIs. Unfortunately, no research has been carried out to investigate the perceptual quality assessment for AGIs specifically. Therefore, in this paper, we first discuss the major evaluation aspects such as technical issues, AI artifacts, unnaturalness, discrepancy, and aesthetics for AGI quality assessment. Then we present the first perceptual AGI quality assessment database, AGIQA-1K, which consists of 1,080 AGIs generated from diffusion models. A well-organized subjective experiment is followed to collect the quality labels of the AGIs. Finally, we conduct a benchmark experiment to evaluate the performance of current image quality assessment (IQA) models.

cs.CV↗
arXiv2023

A real-time blind quality-of-experience assessment metric for HTTP adaptive streaming

In today's Internet, HTTP Adaptive Streaming (HAS) is the mainstream standard for video streaming, which switches the bitrate of the video content based on an Adaptive BitRate (ABR) algorithm. An effective Quality of Experience (QoE) assessment metric can provide crucial feedback to an ABR algorithm. However, predicting such real-time QoE on the client side is challenging. The QoE prediction requires high consistency with the Human Visual System (HVS), low latency, and blind assessment, which are difficult to realize together. To address this challenge, we analyzed various characteristics of HAS systems and propose a non-uniform sampling metric to reduce time complexity. Furthermore, we design an effective QoE metric that integrates resolution and rebuffering time as the Quality of Service (QoS), as well as spatiotemporal output from a deep neural network and specific switching events as content information. These reward and penalty features are regressed into quality scores with a Support Vector Regression (SVR) model. Experimental results show that the accuracy of our metric outperforms the mainstream blind QoE metrics by 0.3, and its computing time is only 60\% of the video playback, indicating that the proposed metric is capable of providing real-time guidance to ABR algorithms and improving the overall performance of HAS.

eess.IV↗
arXiv2022

Contractibility of space of stability conditions on the projective plane via global dimension function

We compute the global dimension function $\mathrm{gldim}$ on the principal component $\mathrm{Stab}^†(\mathbb{P}^2)$ of the space of Bridgeland stability conditions on $\mathbb{P}^2$. It admits $2$ as the minimum value and the preimage $\mathrm{gldim}^{-1}(2)$ is contained in the closure $\bar{\mathrm{Stab}^{\mathrm{Geo}}(\mathbb{P}^2)}$ of the subspace consisting of geometric stability conditions. We show that $\mathrm{gldim}^{-1}[2,x)$ contracts to $\mathrm{gldim}^{-1}(2)$ for any real number $x\geq 2$ and that $\mathrm{gldim}^{-1}(2)$ is contractible.

math.AG↗
arXiv2022

Derived categories of hearts on Kuznetsov components

We prove a general criterion which guarantees that an admissible subcategory $\mathcal{K}$ of the derived category of an abelian category is equivalent to the bounded derived category of the heart of a bounded t-structure. As a consequence, we show that $\mathcal{K}$ has a strongly unique dg enhancement, applying the recent results of Canonaco, Neeman and Stellari. We apply this criterion to the Kuznetsov component $\mathop{\mathcal{K}u}(X)$ when $X$ is a cubic fourfold, a Gushel--Mukai variety or a quartic double solid. In particular, we obtain that these Kuznetsov components have strongly unique dg enhancement and that exact equivalences of the form $\mathop{\mathcal{K}u}(X) \xrightarrow{\sim} \mathop{\mathcal{K}u}(X')$ are of Fourier--Mukai type when $X$, $X'$ belong to these classes of varieties, as predicted by a conjecture of Kuznetsov.

math.AG↗
arXiv2022

Stability manifolds of varieties with finite Albanese morphisms

For a smooth projective complex variety whose Albanese morphism is finite, we show that every Bridgeland stability condition on its bounded derived category of coherent sheaves is geometric, in the sense that all skyscraper sheaves are stable with the same phase. Furthermore, we describe the stability manifolds of irregular surfaces and abelian threefolds with Picard rank one, and show that they are connected and contractible.

math.AG↗
arXiv2020

A refined Derived Torelli Theorem for Enriques surfaces

We prove that two general Enriques surfaces defined over an algebraically closed field of characteristic different from $2$ are isomorphic if their Kuznetsov components are equivalent. We apply the same techniques to give a new simple proof of a conjecture by Ingalls and Kuznetsov relating the derived categories of the blow-up of general Artin\textendash Mumford quartic double solids and of the associated Enriques surfaces. This paper originated from one of the problem sections at the workshop \emph{Semiorthogonal decompositions, stability conditions and sheaves of categories}, Université de Toulouse, May 2--5, 2018.

math.AG↗
arXiv2020

Twisted cubics on cubic fourfolds and stability conditions

We give an interpretation of the Fano variety of lines on a cubic fourfold and of the hyperkahler eightfold, constructed by Lehn, Lehn, Sorger and van Straten from twisted cubic curves in a cubic fourfold non containing a plane, as moduli spaces of Bridgeland stable objects in the Kuznetsov component. As a consequence, we reprove the categorical version of Torelli Theorem for cubic fourfolds, we obtain the identification of the period point of LLSvS eightfold with that of the Fano variety, and we discuss derived Torelli Theorem for cubic fourfolds.

math.AG↗
arXiv2020

Elliptic quintics on cubic fourfolds, O'Grady 10, and Lagrangian fibrations

For a smooth cubic fourfold Y, we study the moduli space M of semistable objects of Mukai vector $2λ_1+2λ_2$ in the Kuznetsov component of Y. We show that with a certain choice of stability conditions, M admits a symplectic resolution $\tilde M$, which is a smooth projective hyperkähler manifold, deformation equivalent to the 10-dimensional examples constructed by O'Grady. As applications, we show that a birational model of $\tilde M$ provides a hyperkähler compactification of the twisted family of intermediate Jacobians associated to Y. This generalizes the previous result of Voisin arXiv:1611.06679 in the very general case. We also prove that $\tilde M$ is the MRC quotient of the main component of the Hilbert scheme of elliptic quintic curves in Y, confirming a conjecture of Castravet.

math.AG↗
arXiv2020

A Survey on Dynamic Network Embedding

Real-world networks are composed of diverse interacting and evolving entities, while most of existing researches simply characterize them as particular static networks, without consideration of the evolution trend in dynamic networks. Recently, significant progresses in tracking the properties of dynamic networks have been made, which exploit changes of entities and links in the network to devise network embedding techniques. Compared to widely proposed static network embedding methods, dynamic network embedding endeavors to encode nodes as low-dimensional dense representations that effectively preserve the network structures and the temporal dynamics, which is beneficial to multifarious downstream machine learning tasks. In this paper, we conduct a systematical survey on dynamic network embedding. In specific, basic concepts of dynamic network embedding are described, notably, we propose a novel taxonomy of existing dynamic network embedding techniques for the first time, including matrix factorization based, Skip-Gram based, autoencoder based, neural networks based and other embedding methods. Additionally, we carefully summarize the commonly used datasets and a wide variety of subsequent tasks that dynamic network embedding can benefit. Afterwards and primarily, we suggest several challenges that the existing algorithms faced and outline possible directions to facilitate the future research, such as dynamic embedding models, large-scale dynamic networks, heterogeneous dynamic networks, dynamic attributed networks, task-oriented dynamic network embedding and more embedding spaces.

cs.SI↗
arXiv2019

On stability conditions for the quintic threefold

We study the Clifford type inequality for a particular type of curves $C_{2,2,5}$, which are contained in smooth quintic threefolds. This allows us to prove some stronger Bogomolov-Gieseker type inequalities for Chern characters of stable sheaves and tilt-stable objects on smooth quintic threefolds. Employing the previous framework by Bayer, Bertram, Macrì, Stellari and Toda, we construct an open subset of stability conditions on every smooth quintic threefold in $\mathbf{P}^4_{\mathbb C}$.

math.AG↗