We aim to address a significant but understudied problem in the anime industry, namely the inbetweening of cartoon line drawings. Inbetweening involves generating intermediate frames between two black-and-white line drawings and is a time-consuming and expensive process that can benefit from automation. However, existing frame interpolation methods that rely on matching and warping whole raster images are unsuitable for line inbetweening and often produce blurring artifacts that damage the intricate line structures. To preserve the precision and detail of the line drawings, we propose a new approach, called AnimeInbet, which geometrizes raster line drawings into graphs of endpoints and reframes the inbetweening task as a graph fusion problem with vertex repositioning. Our method can effectively capture the sparsity and unique structure of line drawings while preserving the details during inbetweening. This is made possible through our novel modules, i.e., vertex encoding, a vertex correspondence Transformer, an effective mechanism for vertex repositioning and a visibility predictor. To train our method, we introduce MixamoLine240, a new dataset of line drawings with ground truth vectorization and matching labels. Our experiments demonstrate that AnimeInbet synthesizes high-quality, clean, and complete intermediate line drawings, outperforming existing methods quantitatively and qualitatively, especially in cases with large motions.
论文检索
输入标题、作者或关键词，从 8,216 篇学术成果中精准定位
Recent advances in semi-supervised semantic segmentation have been heavily reliant on pseudo labeling to compensate for limited labeled data, disregarding the valuable relational knowledge among semantic concepts. To bridge this gap, we devise LogicDiag, a brand new neural-logic semi-supervised learning framework. Our key insight is that conflicts within pseudo labels, identified through symbolic knowledge, can serve as strong yet commonly ignored learning signals. LogicDiag resolves such conflicts via reasoning with logic-induced diagnoses, enabling the recovery of (potentially) erroneous pseudo labels, ultimately alleviating the notorious error accumulation problem. We showcase the practical application of LogicDiag in the data-hungry segmentation scenario, where we formalize the structured abstraction of semantic concepts as a set of logic rules. Extensive experiments on three standard semi-supervised semantic segmentation benchmarks demonstrate the effectiveness and generality of LogicDiag. Moreover, LogicDiag highlights the promising opportunities arising from the systematic integration of symbolic reasoning into the prevalent statistical, neural learning approaches.
The surprisingly fluent predictive performance of LLM (Large Language Models) as well as the high-quality photo-realistic rendering of Diffusion Models has heralded a new beginning in the area of Generative AI. Such kinds of deep learning based models with billions of parameters and pre-trained on massive-scale data-sets are also called Large Foundation Models (LFM). These models not only have caught the public imagination but also have led to an unprecedented surge in interest towards the applications of these models. Instead of the previous approach of developing AI models for specific tasks, more and more researchers are developing large task-agnostic models pre-trained on massive data, which can then be adapted to a variety of downstream tasks via fine-tuning, fewshot learning, or zero-shot learning. Some examples are ChatGPT, LLaMA, GPT-4, Flamingo, MidJourney, Stable-Diffusion and DALLE. Some of them can handle text (e.g., ChatGPT, LLaMA) while some others (e.g., GPT-4 and Flamingo) can utilize multimodal data and can hence be considered Multimodal Large Foundation Models (MLFM). Several recent studies have shown that when adapted to specific tasks (e.g., visual question answering), the foundation models can often surpass the performance of state-of-the-art, fully supervised AI models. However, applying foundation models to specialized domain tasks (e.g., medical diagnosis, financial recommendation etc.) raises many ethical issues (e.g., privacy, model bias or hallucinations). The panel members will discuss the emerging trends in the development and use of large multimodal foundation models. Some of the issues to be discussed are: Research issues in going from LLM to MLFM Behaviour of MLFM Application Potential of MLFM Trust issues in MLFM Limitations of MLFM Societal, Legal and Regulatory issues of MLFM Promising future research in MLFM This panel will bring together several leading experts from universities, research institutions, and industry who will discuss and debate together with the audience. We invite everybody to participate and contribute towards this important and promising research direction.
This is the overview paper for the Deep Video Understanding (DVU) Grand Challenge. In recent years, a growing trend towards working on understanding videos (in particular movies) to a deeper level started to motivate researchers working in multimedia and computer vision to present new approaches and datasets to tackle this problem. This is a challenging research area which aims to develop a deep understanding of the relations which exist between different individuals and entities in movies using all available modalities such as video, audio, text and metadata. The aim of this grand challenge is to foster innovative research in this new direction and to provide benchmarking evaluations to advance technologies in the deep video understanding community.
Image editing plays a vital role in computer vision field, aiming to realistically manipulate images while ensuring seamless integration. It finds numerous applications across various fields. In this work, we present EditAnything, a novel approach that empowers users with unparalleled flexibility in editing and generating image content. EditAnything introduces an array of advanced features, including cross-image dragging (e.g., try-on), region-interactive editing, controllable layout generation, and virtual character replacement. By harnessing these capabilities, users can engage in interactive and flexible editing, giving captivating outcomes that uphold the integrity of the original image. With its diverse range of tools, EditAnything caters to a wide spectrum of editing needs, pushing the boundaries of image editing and unlocking exciting new possibilities. The source code is released at https://github.com/sail-sg/EditAnything.
Developing realistic and interactive virtual environments is a major hurdle in the progress of Metaverse. At present, majority of Metaverse applications necessitate the manual construction of 3D models which is both time-consuming and costly. Additionally, it is challenging to design environments that can promptly react to users’ actions. To address this challenge, this PhD Forum paper proposes a novel approach to generate virtual worlds using digital twin (DT) technology and AI through a Text-to-Metaverse pipeline. This pipeline converts natural language input into a scene JSON, which is used to generate a 3D virtual world using two engines: Generative Script Engine (GSE) and Generative Metaverse Engine (GME). GME generates a design script from the JSON file, and then uses it to generate 3D objects in an environment. It aims to use multimodal AI and DT technology to produce realistic and highly detailed virtual environments. The proposed pipeline has potential applications including education, training, architecture, healthcare and entertainment, and could change the way designers and developers create virtual worlds. While this paper covers an initial work as per the PhD Forum’s guidelines, it contributes to the research on generative models for multimodal data and provides a new direction for creating immersive virtual experiences.
MovieFactory: Automatic Movie Creation from Text using Large Generative Models for Language and Images
PDF ↗In this paper, we present MovieFactory, a powerful framework to generate cinematic-picture (3072x1280), film-style (multi-scene), and multi-modality (sounding) movies on the demand of natural languages. As the first fully automated movie generation model to the best of our knowledge, our approach empowers users to create captivating movies with smooth transitions using simple text inputs, surpassing existing methods that produce soundless videos limited to a single scene of modest quality. To facilitate this distinctive functionality, we leverage ChatGPT to expand user-provided text into detailed sequential scripts for movie generation. Then we bring scripts to life visually and acoustically through vision generation and audio retrieval. To generate videos, we extend the capabilities of a pretrained text-to-image diffusion model through a two-stage process. Firstly, we employ spatial finetuning to bridge the gap between the pretrained image model and the new video dataset. Subsequently, we introduce temporal learning to capture object motion. In terms of audio, we leverage sophisticated retrieval models to select and align audio elements that correspond to the plot and visual content of the movie.
Misinformation has been a persistent and harmful phenomenon affecting our society in various ways, including individuals' physical health and economic stability. With the rise of short video platforms and related applications, the spread of multi-modal misinformation, encompassing images, texts, audios, and videos have exacerbated these concerns. The introduction of generative AI models like ChatGPT and Stable Diffusion has further complicated matters, giving rise to Artificial Intelligence Generated Content (AIGC) and presenting new challenges in detecting and mitigating misinformation. Consequently, traditional approaches to misinformation detection and intervention have become inadequate in this evolving landscape. This paper explores the challenges posed by AIGC in the context of misinformation. It examines the issue from psychological and societal perspectives, and explores the subtle manipulation traces found in AIGC at signal, perceptual, semantic, and human levels. By scrutinizing manipulation traces such as signal manipulation, semantic inconsistencies, logical incoherence, and psychological strategies, our objective is to tackle AI-generated misinformation and provide a conceptual design of systematic explainable solution. Ultimately, we aim for this paper to contribute valuable insights into combating misinformation, particularly in the era of AIGC.
Live video streaming has grown dramatically in recent years. A key challenge is achieving high video quality of experience (QoE) in low-rate networks. To tackle this problem, recent streaming approaches strategically drop video frames, thus reducing the bandwidth required. However, these methods are usually designed for video on demand (VoD) services and perform poorly in live video streaming. In this paper, we design a new live video streaming approach, Reparo, which aims to improve users' QoE in low-rate networks. On the upload client side, Reparo discards video frames such that they are never encoded or transmitted. To decide which frames should be dropped, we design a real-time Video Frame Discarding (VFD) model, which strives to minimize the impact on video quality while maximizing bandwidth savings. To complement this, Reparo further proposes a modified adaptive bitrate algorithm and two encoding modes, targeting low-frame-rate encoding. On the server side, Reparo then recovers the dropped frames using a lightweight Video Frame Interpolation Deep Neural Network (VFI-DNN). Experimental results show that, compared with vanilla DASH, Reparo reaches an SSIM gain of 0.018, or reduces bandwidth consumption by 30.86%. With an average bandwidth of 0.974Mbps, it improves QoE by 18.13% on average compared to DASH.
Massive numbers of new images are uploaded to the internet every day. However, existing cross-modal retrieval (CMR) approaches struggle to accommodate this continuously growing data. The prevalent practice involves periodically retraining or fine-tuning a new model based on the accumulated data, which in turn invalidates billions of indexed features extracted by the previous model and incurs another substantial computational cost to extract new features for the entire data archive. Is it possible to develop a retrieval model that effectively captures the knowledge of upcoming sessions while preserving the discriminative power of features extracted in previous sessions? In this paper, we propose an online continual learning setup, OC-CMR, to formalize the data-incremental growth challenge faced by cross-modal retrieval systems. It consists of two key settings: 1) Similar to the real-world scenarios, the streaming multi-modal data arrives once per session; 2) Consider the computational costs, each instance of archived data has its feature extracted only once and by its corresponding model in its session. Based on our OC-CMR, we perform in-depth evaluations of state-of-the-art cross-modal retrieval methods and observe that they suffer from representational shift and collapse due to the catastrophic forgetting. To address this issue, we propose the Continual Cross-Modal Retrieval (C2MR) approach, which learns a shared common space not only across modalities but also sessions and maintains relationships between samples from distinct sessions via cross-modal relational coherence and semantic representation coordination. We construct two new benchmarks by adapting MS-COCO and Flickr30K datasets to the OC-CMR setting, providing a more challenging evaluation framework for CMR tasks. Experimental results demonstrate that our method effectively alleviates forgetting and significantly outperforms combinations of previous arts in cross-modal retrieval and continual learning.
Unlearnable Examples Give a False Sense of Security: Piercing through Unexploitable Data with Learnable Examples
PDF ↗Safeguarding data from unauthorized exploitation is vital for privacy and security, especially in recent rampant research in security breach such as adversarial/membership attacks. To this end,unlearnable examples (UEs) have been recently proposed as a compelling protection, by adding imperceptible perturbation to data so that models trained on them cannot classify them accurately on original clean distribution. Unfortunately, we find UEs provide a false sense of security, because they cannot stop unauthorized users from utilizing other unprotected data to remove the protection, by turning unlearnable data into learnable again. Motivated by this observation, we formally define a new threat by introducinglearnable unauthorized examples (LEs) which are UEs with their protection removed. The core of this approach is a novel purification process that projects UEs onto the manifold of LEs. This is realized by a new joint-conditional diffusion model which denoises UEs conditioned on the pixel and perceptual similarity between UEs and LEs. Extensive experiments demonstrate that LE delivers state-of-the-art countering performance against both supervised UEs and unsupervised UEs in various scenarios, which is the first generalizable countermeasure to UEs across supervised learning and unsupervised learning. Our code is available at https://github.com/jiangw-0/LE_JCDP.
Cuing Without Sharing: A Federated Cued Speech Recognition Framework via Mutual Knowledge Distillation
PDF ↗Cued Speech (CS) is a visual coding tool to encode spoken languages at the phonetic level, which combines lip-reading and hand gestures to effectively assist communication among people with hearing impairments. The Automatic CS Recognition (ACSR) task aims to recognize CS videos into linguistic texts, which involves both lips and hands as two distinct modalities conveying complementary information. However, the traditional centralized training approach poses potential privacy risks due to the use of facial and gesture videos in CS data. To address this issue, we propose a new Federated Cued Speech Recognition (FedCSR) framework to train an ACSR model over the decentralized CS data without sharing private information. In particular, a mutual knowledge distillation method is proposed to maintain cross-modal semantic consistency of the Non-IID CS data, which ensures learning a unified feature space for linguistic and visual information. On the server side, a globally shared linguistic model is trained to capture the long-term dependencies in the text sentences, which is aligned with the visual information from the local clients via visual-to-linguistic distillation. On the client side, the visual model of each client is trained with its own local data, assisted by linguistic-to-visual distillation treating the linguistic model as the teacher. To the best of our knowledge, this is the first approach to consider the federated ACSR task for privacy protection. Experimental results on the Chinese CS dataset with multiple cuers demonstrate that our approach outperforms both mainstream federated learning baselines and existing centralized state-of-the-art ACSR methods, achieving 9.7% performance improvement for character error rate (CER) and 15.0% for word error rate (WER). The Chinese CS dataset and our code will be open-sourced.
In comparison to symmetric embedding, asymmetric methods generally provide better steganography security. However, the performance of existing asymmetric methods is limited by their reliance on symmetric embedding costs. In this paper, we present a novel Generative Adversarial Network (GAN)-based steganography approach that independently learns asymmetric embedding costs from scratch. Our proposed framework features a generator with a dual-branch architecture and a discriminator that integrates multiple steganalytic networks. To address the issues of model instability and non-convergence that often arise in GAN model training, we implement an adaptive strategy that updates the GAN model parameters according to the performance of multiple steganalytic networks in each iteration. Furthermore, we introduce a new adversarial loss function that effectively learns asymmetric embedding costs by utilizing features like image residuals, gradients, asymmetric embedding probability maps, and the sign of the modification map to train the dual-branch network within the generator. Our comprehensive experiments show that our method achieves state-of-the-art steganography security results, significantly outperforming existing top-performing symmetric and asymmetric methods. Additionally, numerous ablation experiments confirm the rationality of our GAN-based model design.
Spike camera is a new type of bio-inspired vision sensor that records light intensity in the form of a spike array with high temporal resolution (20,000 Hz). This new paradigm of vision sensor offers significant advantages for many vision tasks such as high speed image reconstruction. However, existing spike-based approaches typically assume that the scenes are with sufficient light intensity, which is usually unavailable in many real-world scenarios such as rainy days or dusk scenes. To unlock more spike-based application scenarios, we propose a Recurrent Spike-based Image Restoration (RSIR) network, which is the first work towards restoring clear images from spike arrays under general illumination. Specifically, to accurately describe the noise distribution under different illuminations, we build a physical-based spike noise model according to the sampling process of the spike camera. Based on the noise model, we design our RSIR network which consists of an adaptive spike transformation module, a recurrent temporal feature fusion module, and a frequency-based spike denoising module. Our RSIR can process the spike array in a recursive manner to ensure that the spike temporal information is well utilized. In the training process, we generate the simulated spike data based on our noise model to train our network. Extensive experiments on real-world datasets with different illuminations demonstrate the effectiveness of the proposed network. The code and dataset are released at https://github.com/BIT-Vision/RSIR.
The process of drawing digital comics and animations is a complex process that involves multiple stages. Flat-coloring, the task of filling segmented regions in a line art image with uniform tone and hue, is a particularly time-consuming and labor-intensive task. We have identified that artists suffer from not only adjusting colors in overflowing regions due to line discontinuity but also finding to replace misaligned pixels near the line due to region-bleeding problems (aliasing issues). To address these issues, we propose a holistic data generation pipeline (FlatGAN-DG) that awares the region of line discontinuity and augments the input sketch image to build robust models for noise. In addition, we propose a real-time post-processing method (FlatGAN-PP) that automatically finds and replaces miscolored pixels to alleviate the region-bleeding problems (aliasing issues). To enhance inference speed, we build FlatGAN, which shares the parameters of a generator to predict the foreground, background, and trimap at once to learn in a multi-task manner. Our experimental results show that our method outperforms other rule-and learning-based methods on three different datasets with different painting styles. To evaluate the segmented regions, we collect datasets with the annotation of split-score, merge-hard-score, and merge-easy-score. We also introduce a new evaluation metric (Region Score) on these datasets, validating the efficacy of our methods through a user study. Code is available at https://github.com/hanish3464/FlatGAN.
The malicious use and widespread dissemination of deepfake pose a significant crisis of trust. Current deepfake detection models can generally recognize forgery images by training on a large dataset. However, the accuracy of detection models degrades significantly on images generated by new deepfake methods due to the difference in data distribution. To tackle this issue, we present a novel incremental learning framework that improves the generalization of deepfake detection models by continual learning from a small number of new samples. To cope with different data distributions, we propose to learn a domain-invariant representation based on supervised contrastive learning, preventing overfit to the insufficient new data. To mitigate catastrophic forgetting, we regularize our model in both feature-level and label-level based on a multi-perspective knowledge distillation approach. Finally, we propose to select both central and hard representative samples to update the replay set, which is beneficial for both domain-invariant representation learning and rehearsal-based knowledge preserving. We conduct extensive experiments on four benchmark datasets, obtaining the new state-of-the-art average forgetting rate of 7.01 and average accuracy of 85.49 on FF++, DFDC-P, DFD, and CDF2. Our code is released at \textcolorblue https://github.com/DeepFakeIL/DFIL.
Currently, reference-based super-resolution (RefSR) techniques leverage high-resolution (HR) reference images to provide useful content and texture information for low-resolution (LR) images during the super-resolution (SR) process. Nevertheless, it is time-consuming, laborious, and even impossible in some cases to find high-quality reference images. To tackle this problem, we propose a brand-new self-reference image super-resolution approach using a pre-trained diffusion large model and a window adjustable transformer, termed DWTrans. Our proposed method does not require explicitly inputting manually acquired reference images during training and inference. Specifically, we feed the degraded LR images into a pre-trained stable diffusion large model to automatically generate corresponding high-quality self-reference (SRef) images that provide valuable high-frequency details for the LR images in the process of SR. To extract valuable high-frequency information in SRef images, we design a window adjustable transformer with both non-adjustable window layer (NWL) and adjustable window layer (AWL). The NWL learns local features from LR images using a dense window, while the AWL acquires global features from the SRef images using a random sparse window. Furthermore, to fully utilize the high-frequency features in the SRef image, we introduce the adaptive deformable fusion module to adaptively fuse the features of the LR and SRef images. Experimental results validate that our proposed DWTrans outperforms state-of-the-art methods on various benchmark datasets both quantitatively and visually.
FCBoost-Net: A Generative Network for Synthesizing Multiple Collocated Outfits via Fashion Compatibility Boosting
PDF ↗Outfit generation is a challenging task in the field of fashion technology, in which the aim is to create a collocated set of fashion items that complement a given set of items. Previous studies in this area have been limited to generating a unique set of fashion items based on a given set of items, without providing additional options to users. This lack of a diverse range of choices necessitates the development of a more versatile framework. However, when the task of generating collocated and diversified outfits is approached with multimodal image-to-image translation methods, it poses a challenging problem in terms of non-aligned image translation, which is hard to address with existing methods. In this research, we present FCBoost-Net, a new framework for outfit generation that leverages the power of pre-trained generative models to produce multiple collocated and diversified outfits. Initially, FCBoost-Net randomly synthesizes multiple sets of fashion items, and the compatibility of the synthesized sets is then improved in several rounds using a novel fashion compatibility booster. This approach was inspired by boosting algorithms and allows the performance to be gradually improved in multiple steps. Empirical evidence indicates that the proposed strategy can improve the fashion compatibility of randomly synthesized fashion items as well as maintain their diversity. Extensive experiments confirm the effectiveness of our proposed framework with respect to visual authenticity, diversity, and fashion compatibility.
Backdoor attack aims to compromise a model, which returns an adversary-wanted output when a specific trigger pattern appears yet behaves normally for clean inputs. Current backdoor attacks require changing pixels of clean images, which results in poor stealthiness of attacks and increases the difficulty of the physical implementation. This paper proposes a novel physical invisible backdoor based on camera imaging without changing nature image pixels. Specifically, a compromised model returns a target label for images taken by a particular camera, while it returns correct results for other images. To implement and evaluate the proposed backdoor, we take shots of different objects from multi-angles using multiple smartphones to build a new dataset of 21,500 images. Conventional backdoor attacks work ineffectively with some classical models, such as ResNet18, over the above-mentioned dataset. Therefore, we propose a three-step training strategy to mount the backdoor attack. First, we design and train a camera identification model with the phone IDs to extract the camera fingerprint feature. Subsequently, we elaborate a special network architecture, which is easily compromised by our backdoor attack, by leveraging the attributes of the CFA interpolation algorithm and combining it with the feature extraction block in the camera identification model. Finally, we transfer the backdoor from the elaborated special network architecture to the classical architecture model via teacher-student distillation learning. Since the trigger of our method is related to the specific phone, our attack works effectively in the physical world. Experiment results demonstrate the feasibility of our proposed approach and robustness against various backdoor defences.
Recently, there has been a growing interest in constructing deep learning schemes for Low-Light Vision (LLV). Existing techniques primarily focus on designing task-specific and data-dependent vision models on the standard RGB domain, which inherently contain latent data associations. In this study, we propose a generic low-light vision solution by introducing a generative block to convert data from the RAW to the RGB domain. This novel approach connects diverse vision problems by explicitly depicting data generation, which is the first in the field. To precisely characterize the latent correspondence between the generative procedure and the vision task, we establish a bilevel model with the parameters of the generative block defined as the upper level and the parameters of the vision task defined as the lower level. We further develop two types of learning strategies targeting different goals, namely low cost and high accuracy, to acquire a new bilevel generative learning paradigm. The generative blocks embrace a strong generalization ability in other low-light vision tasks through the bilevel optimization on enhancement tasks. Extensive experimental evaluations on three representative low-light vision tasks, namely enhancement, detection, and segmentation, fully demonstrate the superiority of our proposed approach. The code will be available at https://github.com/Yingchi1998/BGL.