Recent advances in text-to-image diffusion models spurred research on personalization, i.e., a customized image synthesis, of subjects within reference images. Although existing personalization methods are able to alter the subjects’ positions or to personalize multiple subjects simultaneously, they often struggle to modify the behaviors of subjects or their dynamic interactions. The difficulty is attributable to overfitting to reference images, which worsens if only a single reference image is available. We propose DynASyn, an effective multi-subject personalization from a single reference image addressing these challenges. DynASyn preserves the subject identity in the personalization process by aligning concept-based priors with subject appearances and actions. This is achieved by regularizing the attention maps between the subject token and images through concept-based priors. In addition, we propose concept-based prompt-and-image augmentation for an enhanced trade-off between identity preservation and action diversity. We adopt an SDE-based editing guided by augmented prompts to generate diverse appearances and actions while maintaining identity consistency in the augmented images. Experiments show that DynASyn is capable of synthesizing highly realistic images of subjects with novel contexts and dynamic interactions with the surroundings, and outperforms baseline methods in both quantitative and qualitative aspects.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
Intrinsic Image Decomposition for Robust Self-supervised Monocular Depth Estimation on Reflective Surfaces
PDF ↗Self-supervised monocular depth estimation (SSMDE) has gained attention in the field of deep learning as it estimates depth without requiring ground truth depth maps. This approach typically uses a photometric consistency loss between a synthesized image, generated from the estimated depth, and the original image, thereby reducing the need for extensive dataset acquisition. However, the conventional photometric consistency loss relies on the Lambertian assumption, which often leads to significant errors when dealing with reflective surfaces that deviate from this model. To address this limitation, we propose a novel framework that incorporates intrinsic image decomposition into SSMDE. Our method synergistically trains for both monocular depth estimation and intrinsic image decomposition. The accurate depth estimation facilitates multi-image consistency for intrinsic image decomposition by aligning different view coordinate systems, while the decomposition process identifies reflective areas and excludes corrupted gradients from the depth training process. Furthermore, our framework introduces a pseudo-depth generation and knowledge distillation technique to further enhance the performance of the student model across both reflective and non-reflective surfaces. Comprehensive evaluations on multiple datasets show that our approach significantly outperforms existing SSMDE baselines in depth prediction, especially on reflective surfaces.
Smartphone cameras are ubiquitous in daily life, yet their performance can be severely impacted by dirty lenses, leading to degraded image quality. This issue is often overlooked in image restoration research, which assumes ideal or controlled lens conditions. To address this gap, we introduced SIDL (Smartphone Images with Dirty Lenses), a novel dataset designed to restore images captured through contaminated smartphone lenses. SIDL contains diverse real-world images taken under various lighting conditions and environments. These images feature a wide range of lens contaminants, including water drops, fingerprints, and dust. Each contaminated image is paired with a clean reference image, enabling supervised learning approaches for restoration tasks. To evaluate the challenge posed by SIDL, various state-of-the-art restoration models were trained and compared on this dataset. Their performances achieved some level of restoration but did not adequately address the diverse and realistic nature of the lens contaminants in SIDL. This challenge highlights the need for more robust and adaptable image restoration techniques for restoring images with dirty lenses.
Distribution-Level Feature Distancing for Machine Unlearning: Towards a Better Trade-off Between Model Utility and Forgetting
PDF ↗With the explosive growth of deep learning applications and increasing privacy concerns, the right to be forgotten has become a critical requirement in various AI industries. For example, given a facial recognition system, some individuals may wish to remove their personal data that might have been used in the training phase. Unfortunately, deep neural networks sometimes unexpectedly leak personal identities, making this removal challenging. While recent machine unlearning algorithms aim to enable models to forget specific data, we identify an unintended utility drop—correlation collapse—in which the essential correlations between image features and true labels weaken during the forgetting process. To address this challenge, we propose Distribution-Level Feature Distancing (DLFD), a novel method that efficiently forgets instances while preserving task-relevant feature correlations. Our method synthesizes data samples by optimizing the feature distribution to be distinctly different from that of forget samples, achieving effective results within a single training epoch. Through extensive experiments on facial recognition datasets, we demonstrate that our approach significantly outperforms state-of-the-art machine unlearning methods in both forgetting performance and model utility preservation.
Video inpainting (VI) is a challenging task that requires effective propagation of observable content across frames while simultaneously generating new content not present in the original video. In this study, we propose a robust and practical VI framework that leverages a large generative model for reference generation in combination with an advanced pixel propagation algorithm. Powered by a strong generative model, our method not only significantly enhances frame-level quality for object removal but also synthesizes new content in the missing areas based on user-provided text prompts. For pixel propagation, we introduce a one-shot pixel pulling method that effectively avoids error accumulation from repeated sampling while maintaining sub-pixel precision. To evaluate various VI methods in realistic scenarios, we also propose a high-quality VI benchmark, HQVI, comprising carefully generated videos using alpha matte composition. On public benchmarks and the HQVI dataset, our method demonstrates significantly higher visual quality and metric scores compared to existing solutions. Furthermore, it can process high-resolution videos exceeding 2K resolution with ease, underscoring its superiority for real-world applications.
Adversarial training is one of the most effective approaches against adversarial attacks. However, adversarial training has primarily been studied in scenarios where data for all classes is provided, with limited research conducted in the context of incremental learning where knowledge is introduced sequentially. In this study, we investigate Adversarially Robust Class Incremental Learning (ARCIL), which deals with adversarial robustness in incremental learning. We first explore a series of baselines that integrate incremental learning with existing adversarial training methods, finding that they lead to conflicts between acquiring new knowledge and retaining past knowledge. Furthermore, we discover that training new knowledge causes the disappearance of a key characteristic in robust models: a flat loss landscape in input space. To address such issues, we propose a novel and robust baseline for ARCIL, named FLatness preserving Adversarial Incremental learning for Robustness (FLAIR). Experimental results demonstrate that FLAIR significantly outperforms other baselines. To the best of our knowledge, we are the first to comprehensively investigate the baselines, challenges, and solutions for ARCIL, which we believe represents a significant advance toward achieving real-world robustness.
We present a novel, training-free approach to scene change detection. Our method leverages tracking models, which inherently perform change detection between consecutive frames of video by identifying common objects and detecting new or missing objects. Specifically, our method takes advantage of the change detection effect of the tracking model by inputting reference and query images instead of consecutive frames. Furthermore, we focus on the content gap and style gap between two input images in change detection, and address both issues by proposing adaptive content threshold and style bridging layers, respectively. Finally, we extend our approach to video, leveraging rich temporal information to enhance the performance of scene change detection. We compare our approach and baseline through various experiments. While existing train-based baseline tend to specialize only in the trained domain, our method shows consistent performance across various domains, proving the competitiveness of our approach.
Ambiguity-Restrained Text-Video Representation Learning for Partially Relevant Video Retrieval
PDF ↗Partially Relevant Video Retrieval~(PRVR) aims to retrieve a video where a specific segment is relevant to a given text query. Typical training processes of PRVR assume a one-to-one relationship where each text query is relevant to only one video. However, we point out the inherent ambiguity between text and video content based on their conceptual scope and propose a framework that incorporates this ambiguity into the model learning process. Specifically, we propose Ambiguity-Restrained representation Learning~(ARL) to address ambiguous text-video pairs. Initially, ARL detects ambiguous pairs based on two criteria: uncertainty and similarity. Uncertainty represents whether instances include commonly shared context across the dataset, while similarity indicates pair-wise semantic overlap. Then, with the detected ambiguous pairs, our ARL hierarchically learns the semantic relationship via multi-positive contrastive learning and dual triplet margin loss. Additionally, we delve into fine-grained relationships within the video instances. Unlike typical training at the text-video level, where pairwise information is provided, we address the inherent ambiguity within frames of the same untrimmed video, which often contains multiple contexts. This allows us to further enhance learning at the text-frame level. Lastly, we propose cross-model ambiguity detection to mitigate the error propagation that occurs when a single model is employed to detect ambiguous pairs for its training. With all components combined, our proposed method demonstrates its effectiveness in PRVR.
The method for image-to-point cloud registration typically determines the rigid transformation using a coarse-to-fine pipeline. However, directly and uniformly matching image patches with point cloud patches may lead to focusing on incorrect noise patches during matching while ignoring key ones. Moreover, due to the significant differences between image and point cloud modalities, it may be challenging to bridge the domain gap without specific improvements in design. To address the above issues, we innovatively propose the Uncertainty-aware Hierarchical Matching Module (UHMM) and the Adversarial Modal Alignment Module (AMAM). Within the UHMM, we model the uncertainty of critical information in image patches and facilitate multi-level fusion interactions between image and point cloud features. In the AMAM, we design an adversarial approach to reduce the domain gap between image and point cloud. Extensive experiments and ablation studies on RGB-D Scene V2 and 7-Scenes benchmarks demonstrate the superiority of our method, making it a state-of-the-art approach for image-to-point cloud registration tasks.
Temporally locating objects with arbitrary class texts is the primary pursuit of open-vocabulary Video Instance Segmentation (VIS). Because of the insufficient vocabulary of video data, previous methods leverage the image-text pretraining model for recognizing object instances by separately aligning each frame with class texts. As a result, the separation breaks the instance movement context of videos and requires a lot of inference overhead. To tackle these issues, we propose BridgeText Alignment (BTA) to link frame-level instance representations as a Brownian Bridge. On one hand, we can calculate the global descriptor of a Brownian bridge for capturing instance dynamics, which enables extra considering temporal information rather than only static information of each frame for aligning with texts. On the other hand, according to the goal-conditioned property of the Brownian bridge, we can estimate the middle frame features via the start and the end frame features so the global feature calculation of a Brownian bridge only needs to infer a few frames, which largely reduces inference overhead. We term our overall pipeline as BriVIS. Following the training settings of previous works, BriVIS surpasses the SOTA (OV2Seg) by a clear margin. For example, on the challenging large-vocabulary datasets (BURST, LVVIS), BriVIS achieves 5.7 and 20.9 mAP, which exhibits +2.2∼+6.7 mAP improvement compared to OV2Seg. Furthermore, after training via BTA, using only the head and the tail frames for alignment improves the speed by 32% (2.77 → 1.88 s/iter) while just decreasing the performance by 0.2 mAP (21.1 → 20.9 mAP).
In the field of graphic design, automating the integration of design elements into a cohesive multi-layered artwork not only boosts productivity but also paves the way for the democratization of graphic design. One existing practice is Graphic Layout Generation (GLG), which aims to layout sequential design elements. It has been constrained by the necessity for a predefined correct sequence of layers, thus limiting creative potential and increasing user workload. In this paper, we present Hierarchical Layout Generation (HLG) as a more flexible and pragmatic setup, which creates graphic composition from any-ordered sets of design elements. To tackle the HLG task, we introduce Graphist, the first layout generation model based on large multimodal models. Graphist efficiently reframes the HLG as a sequence generation problem, utilizing RGB-A images as input, outputs a JSON draft protocol, indicating the coordinates, size, and order of each element. We develop multiple evaluation metrics for HLG. Graphist outperforms prior arts and establishes a strong baseline for this field.
DIDiffGes: Decoupled Semi-Implicit Diffusion Models for Real-time Gesture Generation from Speech
PDF ↗Diffusion models have demonstrated remarkable synthesis quality and diversity in generating co-speech gestures. However, the computationally intensive sampling steps associated with diffusion models hinder their practicality in real-world applications. Hence, we present DIDiffGes, for a Decoupled Semi-Implicit Diffusion model-based framework, that can synthesize high-quality, expressive gestures from speech using only a few sampling steps. Our approach leverages Generative Adversarial Networks (GANs) to enable large-step sampling for diffusion model. We decouple gesture data into body and hands distributions and further decompose them into marginal and conditional distributions. GANs model the marginal distribution implicitly, while L2 reconstruction loss learns the conditional distributions exciplictly. This strategy enhances GAN training stability and ensures expressiveness of generated full-body gestures. Our framework also learns to denoise root noise conditioned on local body representation, guaranteeing stability and realism. DIDiffGes can generate gestures from speech with just 10 sampling steps, without compromising quality and expressiveness, reducing the number of sampling steps by a factor of 100 compared to existing methods. Our user study reveals that our method outperforms state-of-the-art approaches in human likeness, appropriateness, and style correctness.
Recent advances indicate that diffusion model holds great promise in image super-resolution. While latest methods are primarily based on latent diffusion models with convolutional neural networks, there are few attempts to explore transformers, which have demonstrated remarkable performance in image generation. In this work, we design an effective diffusion transformer for image super resolution (DiT-SR) that achieves the visual quality of prior-based methods, but through a training-from-scratch manner. In practice, DiT-SR leverages an overall U-shaped architecture, and adopts uniform isotropic design for all the transformer blocks across different stages. The former facilitates multi-scale hierarchical feature extraction, while the latter reallocate the computational resources to critical layers to further enhance performance. Moreover, we thoroughly analyze the limitation of the widely used AdaLN, and present a frequency-adaptive time-step conditioning module, enhancing the model's capacity to process distinct frequency information at different time steps. Extensive experiments demonstrate that DiT-SR outperforms the existing training-from-scratch diffusion-based SR methods significantly, and even beats some of the prior-based methods on pretrained Stable Diffusion, proving the superiority of diffusion transformer in image super resolution.
In this paper, we propose a new benchmark called "Archaeological Piece Grouping." In the field of archaeology, it is common for broken archaeological pieces, such as artifact fragments, to be mixed. Archaeologists often spend significant time distinguishing these pieces and categorizing them into different groups. Our benchmark introduces a novel, comprehensive dataset named ArcPie, along with new evaluation metrics for this task. Additionally, we propose a new framework called "3D Probabilistic Graph Search" (3DPGS) to address the problem of grouping mixed archaeological pieces. This framework includes a relation network designed to learn the relationships among all the input 3D pieces. Utilizing the relationships learned, our framework generates a probabilistic matching graph that describes the affinity of any two pieces. We also introduce a novel search algorithm to identify groups according to this matrix. Our framework significantly outperforms other baselines.
Recent advancement in text-to-image models and corresponding personalized technologies enables individuals to generate high-quality and imaginative images. However, they often suffer from limitations when generating images with resolutions outside of their trained domain. To overcome this limitation, we present the resolution adapter \textbf{(ResAdapter)}, a domain-consistent adapter designed for diffusion models to generate images with unrestricted resolutions and aspect ratios. Unlike other multi-resolution generation methods that process images of static resolution with complex post-process operations, ResAdapter directly generates images with the dynamical resolution. Especially, after learning a deep understanding of pure resolution priors, ResAdapter trained on the general dataset, generates resolution-free images with personalized diffusion models while preserving their original style domain. Comprehensive experiments demonstrate that ResAdapter with only 0.5M can process images with flexible resolutions for arbitrary diffusion models. More extended experiments demonstrate that ResAdapter is compatible with other modules for image generation across a broad range of resolutions, and can be integrated into other multi-resolution model for efficiently generating higher-resolution images.
Although recent years have witnessed significant advancements in medical image segmentation, the pervasive issue of domain shift among medical images from diverse centres hinders the effective deployment of pre-trained models. Many Test-time Adaptation (TTA) methods have been proposed to address this issue by fine-tuning pre-trained models with test data during inference. These methods, however, often suffer from less-satisfactory optimization due to suboptimal optimization direction (dictated by the gradient) and fixed step-size (predicated on the learning rate). In this paper, we propose the Gradient alignment-based Test-time adaptation (GraTa) method to improve both the gradient direction and learning rate in the optimization procedure. Unlike conventional TTA methods, which primarily optimize the pseudo gradient derived from a self-supervised objective, our method incorporates an auxiliary gradient with the pseudo one to facilitate gradient alignment. Such gradient alignment enables the model to excavate the similarities between different gradients and correct the gradient direction to approximate the empirical gradient related to the current segmentation task. Additionally, we design a dynamic learning rate based on the cosine similarity between the pseudo and auxiliary gradients, thereby empowering the adaptive fine-tuning of pre-trained models on diverse test data. Extensive experiments establish the effectiveness of the proposed gradient alignment and dynamic learning rate and substantiate the superiority of our GraTa method over other state-of-the-art TTA methods on a benchmark medical image segmentation task.
Filter or Compensate: Towards Invariant Representation from Distribution Shift for Anomaly Detection
PDF ↗Recent Anomaly Detection (AD) methods have achieved great success with In-Distribution (ID) data. However, real-world data often exhibits distribution shift, causing huge performance decay on traditional AD methods. From this perspective, few previous work has explored AD with distribution shift, and the distribution-invariant normality learning has been proposed based on the Reverse Distillation (RD) framework. However, we observe the misalignment issue between the teacher and the student network that causes detection failure, thereby propose FiCo, Filter or Compensate, to address the distribution shift issue in AD. FiCo firstly compensates the distribution-specific information to reduce the misalignment between the teacher and student network via the Distribution-Specific Compensation (DiSCo) module, and secondly filters all abnormal information to capture distribution-invariant normality with the Distribution-Invariant Filter (DiIFi) module. Extensive experiments on three different AD benchmarks demonstrate the effectiveness of FiCo, which outperforms all existing state-of-the-art (SOTA) methods, and even achieves better results on the ID scenario compared with RD-based methods.
Spatiotemporal Blind-Spot Network with Calibrated Flow Alignment for Self-Supervised Video Denoising
PDF ↗Self-supervised video denoising aims to remove noise from videos without relying on ground truth data, leveraging the video itself to recover clean frames. Existing methods often rely on simplistic feature stacking or apply optical flow without thorough analysis. This results in suboptimal utilization of both inter-frame and intra-frame information, and it also neglects the potential of optical flow alignment under self-supervised conditions, leading to biased and insufficient denoising outcomes. To this end, we first explore the practicality of optical flow in the self-supervised setting and introduce a SpatioTemporal Blind-spot Network (STBN) for global frame feature utilization. In the temporal domain, we utilize bidirectional blind-spot feature propagation through the proposed blind-spot alignment block to ensure accurate temporal alignment and effectively capture long-range dependencies. In the spatial domain, we introduce the spatial receptive field expansion module, which enhances the receptive field and improves global perception capabilities. Additionally, to reduce the sensitivity of optical flow estimation to noise, we propose an unsupervised optical flow distillation mechanism that refines fine-grained inter-frame interactions during optical flow alignment. Our method demonstrates superior performance across both synthetic and real-world video denoising datasets.
The area of portrait image animation, propelled by audio input, has witnessed notable progress in the generation of lifelike and dynamic portraits. Conventional methods are limited to utilizing either audios or facial key points to drive images into videos, while they can yield satisfactory results, certain issues exist. For instance, methods driven solely by audios can be unstable at times due to the relatively weaker audio signal, while methods driven exclusively by facial key points, although more stable in driving, can result in unnatural outcomes due to the excessive control of key point information. In addressing the previously mentioned challenges, in this paper, we introduce a novel approach which we named EchoMimic. EchoMimic is concurrently trained using both audios and facial landmarks. Through the implementation of a novel training strategy, EchoMimic is capable of generating portrait videos not only by audios and facial landmarks individually, but also by a combination of both audios and selected facial landmarks. EchoMimic has been comprehensively compared with alternative algorithms across various public datasets and our collected dataset, showcasing superior performance in both quantitative and qualitative evaluations. The code and models are available on the project page.
Despite the rapid advancements in text-to-image (T2I) synthesis, enabling precise visual control remains a significant challenge. Existing works attempted to incorporate multi-facet controls (text and sketch), aiming to enhance the creative control over generated images. However, our pilot study reveals that the expressive power of humans far surpasses the capabilities of current methods. Users desire a more versatile approach that can accommodate their diverse creative intents, ranging from controlling individual subjects to manipulating the entire scene composition. We present VersaGen, a generative AI agent that enables versatile visual control in T2I synthesis. VersaGen admits four types of visual controls: i) single visual subject; ii) multiple visual subjects; iii) scene background; iv) any combination of the three above or merely no control at all. We train an adaptor upon a frozen T2I model to accommodate the visual information into the text-dominated diffusion process. We introduce three optimization strategies during the inference phase of VersaGen to improve generation results and enhance user experience. Comprehensive experiments on COCO and Sketchy validate the effectiveness and flexibility of VersaGen, as evidenced by both qualitative and quantitative results.