arXiv subjects

Ziqi Huang

Publications and source records attributed to Ziqi Huang.

48 records · Page 3Linked to original sources

arXiv2024

FreeInit: Bridging Initialization Gap in Video Diffusion Models

Though diffusion-based video generation has witnessed rapid progress, the inference results of existing models still exhibit unsatisfactory temporal consistency and unnatural dynamics. In this paper, we delve deep into the noise initialization of video diffusion models, and discover an implicit training-inference gap that attributes to the unsatisfactory inference quality.Our key findings are: 1) the spatial-temporal frequency distribution of the initial noise at inference is intrinsically different from that for training, and 2) the denoising process is significantly influenced by the low-frequency components of the initial noise. Motivated by these observations, we propose a concise yet effective inference sampling strategy, FreeInit, which significantly improves temporal consistency of videos generated by diffusion models. Through iteratively refining the spatial-temporal low-frequency components of the initial latent during inference, FreeInit is able to compensate the initialization gap between training and inference, thus effectively improving the subject appearance and temporal consistency of generation results. Extensive experiments demonstrate that FreeInit consistently enhances the generation quality of various text-to-video diffusion models without additional training or fine-tuning.

cs.CV↗

arXiv2023

VBench: Comprehensive Benchmark Suite for Video Generative Models

Video generation has witnessed significant advancements, yet evaluating these models remains a challenge. A comprehensive evaluation benchmark for video generation is indispensable for two reasons: 1) Existing metrics do not fully align with human perceptions; 2) An ideal evaluation system should provide insights to inform future developments of video generation. To this end, we present VBench, a comprehensive benchmark suite that dissects "video generation quality" into specific, hierarchical, and disentangled dimensions, each with tailored prompts and evaluation methods. VBench has three appealing properties: 1) Comprehensive Dimensions: VBench comprises 16 dimensions in video generation (e.g., subject identity inconsistency, motion smoothness, temporal flickering, and spatial relationship, etc). The evaluation metrics with fine-grained levels reveal individual models' strengths and weaknesses. 2) Human Alignment: We also provide a dataset of human preference annotations to validate our benchmarks' alignment with human perception, for each evaluation dimension respectively. 3) Valuable Insights: We look into current models' ability across various evaluation dimensions, and various content types. We also investigate the gaps between video and image generation models. We will open-source VBench, including all prompts, evaluation methods, generated videos, and human preference annotations, and also include more video generation models in VBench to drive forward the field of video generation.

cs.CV↗

arXiv2023

FreeU: Free Lunch in Diffusion U-Net

In this paper, we uncover the untapped potential of diffusion U-Net, which serves as a "free lunch" that substantially improves the generation quality on the fly. We initially investigate the key contributions of the U-Net architecture to the denoising process and identify that its main backbone primarily contributes to denoising, whereas its skip connections mainly introduce high-frequency features into the decoder module, causing the network to overlook the backbone semantics. Capitalizing on this discovery, we propose a simple yet effective method-termed "FreeU" - that enhances generation quality without additional training or finetuning. Our key insight is to strategically re-weight the contributions sourced from the U-Net's skip connections and backbone feature maps, to leverage the strengths of both components of the U-Net architecture. Promising results on image and video generation tasks demonstrate that our FreeU can be readily integrated to existing diffusion models, e.g., Stable Diffusion, DreamBooth, ModelScope, Rerender and ReVersion, to improve the generation quality with only a few lines of code. All you need is to adjust two scaling factors during inference. Project page: https://chenyangsi.top/FreeU/.

cs.CV↗

arXiv2023

LAVIE: High-Quality Video Generation with Cascaded Latent Diffusion Models

This work aims to learn a high-quality text-to-video (T2V) generative model by leveraging a pre-trained text-to-image (T2I) model as a basis. It is a highly desirable yet challenging task to simultaneously a) accomplish the synthesis of visually realistic and temporally coherent videos while b) preserving the strong creative generation nature of the pre-trained T2I model. To this end, we propose LaVie, an integrated video generation framework that operates on cascaded video latent diffusion models, comprising a base T2V model, a temporal interpolation model, and a video super-resolution model. Our key insights are two-fold: 1) We reveal that the incorporation of simple temporal self-attentions, coupled with rotary positional encoding, adequately captures the temporal correlations inherent in video data. 2) Additionally, we validate that the process of joint image-video fine-tuning plays a pivotal role in producing high-quality and creative outcomes. To enhance the performance of LaVie, we contribute a comprehensive and diverse video dataset named Vimeo25M, consisting of 25 million text-video pairs that prioritize quality, diversity, and aesthetic appeal. Extensive experiments demonstrate that LaVie achieves state-of-the-art performance both quantitatively and qualitatively. Furthermore, we showcase the versatility of pre-trained LaVie models in various long video generation and personalized video synthesis applications.

cs.CV↗

arXiv2023

WiCV@CVPR2023: The Eleventh Women In Computer Vision Workshop at the Annual CVPR Conference

In this paper, we present the details of Women in Computer Vision Workshop - WiCV 2023, organized alongside the hybrid CVPR 2023 in Vancouver, Canada. WiCV aims to amplify the voices of underrepresented women in the computer vision community, fostering increased visibility in both academia and industry. We believe that such events play a vital role in addressing gender imbalances within the field. The annual WiCV@CVPR workshop offers a) opportunity for collaboration between researchers from minority groups, b) mentorship for female junior researchers, c) financial support to presenters to alleviate finanacial burdens and d) a diverse array of role models who can inspire younger researchers at the outset of their careers. In this paper, we present a comprehensive report on the workshop program, historical trends from the past WiCV@CVPR events, and a summary of statistics related to presenters, attendees, and sponsorship for the WiCV 2023 workshop.

cs.CV↗

arXiv2023

Literal-Aware Knowledge Graph Embedding for Welding Quality Monitoring: A Bosch Case

Recently there has been a series of studies in knowledge graph embedding (KGE), which attempts to learn the embeddings of the entities and relations as numerical vectors and mathematical mappings via machine learning (ML). However, there has been limited research that applies KGE for industrial problems in manufacturing. This paper investigates whether and to what extent KGE can be used for an important problem: quality monitoring for welding in manufacturing industry, which is an impactful process accounting for production of millions of cars annually. The work is in line with Bosch research of data-driven solutions that intends to replace the traditional way of destroying cars, which is extremely costly and produces waste. The paper tackles two very challenging questions simultaneously: how large the welding spot diameter is; and to which car body the welded spot belongs to. The problem setting is difficult for traditional ML because there exist a high number of car bodies that should be assigned as class labels. We formulate the problem as link prediction, and experimented popular KGE methods on real industry data, with consideration of literals. Our results reveal both limitations and promising aspects of adapted KGE methods.

cs.AI↗

arXiv2023

Understanding Privacy Over-collection in WeChat Sub-app Ecosystem

Nowadays the app-in-app paradigm is becoming increasingly popular, and sub-apps have become an important form of mobile applications. WeChat, the leading app-in-app platform, provides millions of sub-apps that can be used for online shopping, financing, social networking, etc. However, privacy issues in this new ecosystem have not been well understood. This paper performs the first systematic study of privacy over-collection in sub-apps (denoted as SPO), where sub-apps actually collect more privacy data than they claim in their privacy policies. We propose a taxonomy of privacy for this ecosystem and a framework named SPOChecker to automatically detect SPO in real-world sub-apps. Based on SPOChecker, we collect 5,521 popular and representative WeChat sub-apps and conduct a measurement study to understand SPO from three aspects: its landscape, accountability, and defense methods. The result is worrisome, that more than half of all studied sub-apps do not provide users with privacy policies. Among 2,511 sub-apps that provide privacy policies, 489 (19.47%) of them contain SPO. We look into the detailed characteristics of SPO, figure out possible reasons and the responsibilities of stakeholders in the ecosystem, and rethink current defense methods. The measurement leads to several insightful findings that can help the community to better understand SPO and protect privacy in sub-apps.

cs.CR↗

arXiv2023

Collaborative Diffusion for Multi-Modal Face Generation and Editing

Diffusion models arise as a powerful generative tool recently. Despite the great progress, existing diffusion models mainly focus on uni-modal control, i.e., the diffusion process is driven by only one modality of condition. To further unleash the users' creativity, it is desirable for the model to be controllable by multiple modalities simultaneously, e.g., generating and editing faces by describing the age (text-driven) while drawing the face shape (mask-driven). In this work, we present Collaborative Diffusion, where pre-trained uni-modal diffusion models collaborate to achieve multi-modal face generation and editing without re-training. Our key insight is that diffusion models driven by different modalities are inherently complementary regarding the latent denoising steps, where bilateral connections can be established upon. Specifically, we propose dynamic diffuser, a meta-network that adaptively hallucinates multi-modal denoising steps by predicting the spatial-temporal influence functions for each pre-trained uni-modal model. Collaborative Diffusion not only collaborates generation capabilities from uni-modal diffusion models, but also integrates multiple uni-modal manipulations to perform multi-modal editing. Extensive qualitative and quantitative experiments demonstrate the superiority of our framework in both image quality and condition consistency.

cs.CV↗

arXiv2022

DS3-Net: Difficulty-perceived Common-to-T1ce Semi-Supervised Multimodal MRI Synthesis Network

Contrast-enhanced T1 (T1ce) is one of the most essential magnetic resonance imaging (MRI) modalities for diagnosing and analyzing brain tumors, especially gliomas. In clinical practice, common MRI modalities such as T1, T2, and fluid attenuation inversion recovery are relatively easy to access while T1ce is more challenging considering the additional cost and potential risk of allergies to the contrast agent. Therefore, it is of great clinical necessity to develop a method to synthesize T1ce from other common modalities. Current paired image translation methods typically have the issue of requiring a large amount of paired data and do not focus on specific regions of interest, e.g., the tumor region, in the synthesization process. To address these issues, we propose a Difficulty-perceived common-to-T1ce Semi-Supervised multimodal MRI Synthesis network (DS3-Net), involving both paired and unpaired data together with dual-level knowledge distillation. DS3-Net predicts a difficulty map to progressively promote the synthesis task. Specifically, a pixelwise constraint and a patchwise contrastive constraint are guided by the predicted difficulty map. Through extensive experiments on the publiclyavailable BraTS2020 dataset, DS3-Net outperforms its supervised counterpart in each respect. Furthermore, with only 5% paired data, the proposed DS3-Net achieves competitive performance with state-of-theart image translation methods utilizing 100% paired data, delivering an average SSIM of 0.8947 and an average PSNR of 23.60.

eess.IV↗

arXiv2022

Multi-modal Brain Tumor Segmentation via Missing Modality Synthesis and Modality-level Attention Fusion

Multi-modal magnetic resonance (MR) imaging provides great potential for diagnosing and analyzing brain gliomas. In clinical scenarios, common MR sequences such as T1, T2 and FLAIR can be obtained simultaneously in a single scanning process. However, acquiring contrast enhanced modalities such as T1ce requires additional time, cost, and injection of contrast agent. As such, it is clinically meaningful to develop a method to synthesize unavailable modalities which can also be used as additional inputs to downstream tasks (e.g., brain tumor segmentation) for performance enhancing. In this work, we propose an end-to-end framework named Modality-Level Attention Fusion Network (MAF-Net), wherein we innovatively conduct patchwise contrastive learning for extracting multi-modal latent features and dynamically assigning attention weights to fuse different modalities. Through extensive experiments on BraTS2020, our proposed MAF-Net is found to yield superior T1ce synthesis performance (SSIM of 0.8879 and PSNR of 22.78) and accurate brain tumor segmentation (mean Dice scores of 67.9%, 41.8% and 88.0% on segmenting the tumor core, enhancing tumor and whole tumor).

eess.IV↗

arXiv2022

Unsupervised Domain Adaptation for Cross-Modality Retinal Vessel Segmentation via Disentangling Representation Style Transfer and Collaborative Consistency Learning

Various deep learning models have been developed to segment anatomical structures from medical images, but they typically have poor performance when tested on another target domain with different data distribution. Recently, unsupervised domain adaptation methods have been proposed to alleviate this so-called domain shift issue, but most of them are designed for scenarios with relatively small domain shifts and are likely to fail when encountering a large domain gap. In this paper, we propose DCDA, a novel cross-modality unsupervised domain adaptation framework for tasks with large domain shifts, e.g., segmenting retinal vessels from OCTA and OCT images. DCDA mainly consists of a disentangling representation style transfer (DRST) module and a collaborative consistency learning (CCL) module. DRST decomposes images into content components and style codes and performs style transfer and image reconstruction. CCL contains two segmentation models, one for source domain and the other for target domain. The two models use labeled data (together with the corresponding transferred images) for supervised learning and perform collaborative consistency learning on unlabeled data. Each model focuses on the corresponding single domain and aims to yield an expertized domain-specific segmentation model. Through extensive experiments on retinal vessel segmentation, our framework achieves Dice scores close to target-trained oracle both from OCTA to OCT and from OCT to OCTA, significantly outperforming other state-of-the-art methods.

eess.IV↗

arXiv2021

Talk-to-Edit: Fine-Grained Facial Editing via Dialog

Facial editing is an important task in vision and graphics with numerous applications. However, existing works are incapable to deliver a continuous and fine-grained editing mode (e.g., editing a slightly smiling face to a big laughing one) with natural interactions with users. In this work, we propose Talk-to-Edit, an interactive facial editing framework that performs fine-grained attribute manipulation through dialog between the user and the system. Our key insight is to model a continual "semantic field" in the GAN latent space. 1) Unlike previous works that regard the editing as traversing straight lines in the latent space, here the fine-grained editing is formulated as finding a curving trajectory that respects fine-grained attribute landscape on the semantic field. 2) The curvature at each step is location-specific and determined by the input image as well as the users' language requests. 3) To engage the users in a meaningful dialog, our system generates language feedback by considering both the user request and the current state of the semantic field. We also contribute CelebA-Dialog, a visual-language facial editing dataset to facilitate large-scale study. Specifically, each image has manually annotated fine-grained attribute annotations as well as template-based textual descriptions in natural language. Extensive quantitative and qualitative experiments demonstrate the superiority of our framework in terms of 1) the smoothness of fine-grained editing, 2) the identity/attribute preservation, and 3) the visual photorealism and dialog fluency. Notably, user study validates that our overall system is consistently favored by around 80% of the participants. Our project page is https://www.mmlab-ntu.com/project/talkedit/.

cs.CV↗