论文检索

Guanqi Ding, Chengyu Yang, Shuhui Wang, Xincheng Li, Jinzhe Zhang, Xin Jin, Qingming Huang

Personalized image generation enables customized content creation based on the text-to-image diffusion models.However, existing personalization methods focus on fine-tuning generative models to learn to generate specific single individuals or concepts, such as an image of a specific Corgi, but are unable to generate data for multiple individuals or concepts with common characteristics, such as images of multiple different Corgis. In this work, we focus on personalizing a diffusion model to generated varied data usually containing multiple subjects, which has a more diverse and complex data distribution. Our basic assumption is that the varied data distribution is composed of the common features shared among all samples, as well as the reasonable variations within it. Accordingly, we are capable to decompose the learning process of complex data distributions into two simpler sub-tasks, employing a divide-and-conquer approach. To this end we propose Dis2Booth, a framework that can learn complex image Distribution by Disentangling data distribution in an unsupervised manner.Specifically, Dis2Booth contains two modules, Anchor LoRA and Delta LoRA, that are tasked with learning the common features and variational features constrained by Contextual Loss and Delta Loss unsupervisedly. Besides, the Asynchronous Optimization Strategy is proposed to ensure the collaborative training of the two modules. Extensive experiments suggest that Dis2Booth is able to learn the data distribution with higher diversity and complexity while maintaining the same level of flexibility as LoRA.

Bonan Ding, Jin Xie, Jing Nie, Jiale Cao

Multimodal 3D object detection based on deep neural networks has indeed made significant progress. However, it still faces challenges due to the misalignment of scale and spatial information between features extracted from 2D images and those derived from 3D point clouds. Existing methods usually aggregate multimodal features at a single stage. However, leveraging multi-stage cross-modal features is crucial for detecting objects of various scales. Therefore, these methods often struggle to integrate features across different scales and modalities effectively, thereby restricting the accuracy of detection. Additionally, the time-consuming Query-Key-Value-based (QKV-based) cross-attention operations often utilized in existing methods aid in reasoning the location and existence of objects by capturing non-local contexts. However, this approach tends to increase computational complexity. To address these challenges, we present SSLFusion, a novel Scale & Space Aligned Latent Fusion Model, consisting of a scale-aligned fusion strategy (SAF), a 3D-to-2D space alignment module (SAM), and a latent cross-modal fusion module (LFM). SAF mitigates scale misalignment between modalities by aggregating features from both images and point clouds across multiple levels. SAM is designed to reduce the inter-modal gap between features from images and point clouds by incorporating 3D coordinate information into 2D image features. Additionally, LFM captures cross-modal non-local contexts in the latent space without utilizing the QKV-based attention operations, thus mitigating computational complexity. Experiments on the KITTI and DENSE datasets demonstrate that our SSLFusion outperforms state-of-the-art methods. Our approach obtains an absolute gain of 2.15% in 3D AP, compared with the state-of-art method GraphAlign on the moderate level of the KITTI test set.

Yuhui Deng, Yuqin Lu, Yangyang Xu, Yongwei Nie, Shengfeng He

Talking head video generation involves animating a still face image using facial motion cues derived from a driving video to replicate target poses and expressions. Traditional methods often rely on the assumption that the relative positions of facial keypoints remain unchanged. However, this assumption fails when keypoints are occluded or when the head is in a profile pose, leading to inconsistencies in identity and blurring in certain facial regions. In this paper, we introduce Occlusion-Insensitive Talking Head Video Generation, a novel approach that eliminates the reliance on spatial correlation of keypoints and instead leverages semantic correlation. Our method transforms facial features into a facelet semantic bank, where each facelet token represents a specific facial semantic. This bank is devoid of spatial information, allowing it to compensate for any invisible or occluded face regions during motion warping. The facelet compensation module then populates the facelet tokens within the initially warped features by learning a correlation matrix between facial semantics and the facelet bank. This approach enables precise compensation for occlusions and pose changes, enhancing the fidelity of the generated videos. Extensive experiments demonstrate that our method achieves state-of-the-art results, preserving source identity, maintaining fine-grained facial details, and capturing nuanced facial expressions with remarkable accuracy.

Xiongwen Deng, Haoyu Tang, Han Jiang, Qinghai Zheng, Jihua Zhu

Zero-shot Natural Language Video Localization (NLVL) aims to automatically generate moments and corresponding pseudo queries from raw videos for the training of the localization model without any manual annotations. Existing approaches typically produce pseudo queries as simple words, which overlook the complexity of queries in real-world scenarios. Considering the powerful text modeling capabilities of large language models (LLMs), leveraging LLMs to generate complete queries that are closer to human descriptions is a potential solution. However, directly integrating LLMs into existing approaches introduces several issues, including insensitivity, isolation, and lack of regulation, which prevent the full exploitation of LLMs to enhance zero-shot NLVL performance. To address these issues, we propose BTDP, an innovative framework for Boundary-aware Temporal Dynamic Pseudo-supervision pairs generation. Our method contains two crucial operations: 1) Boundary Segmentation that identifies both visual boundaries and semantic boundaries to generate the atomic segments and activity descriptions, tackling the issue of insensitivity. 2) Context Aggregation that employs the LLMs with a self-evaluation process to aggregate and summarize global video information for optimized pseudo moment-query pairs, tackling the issue of isolation and lack of regulation. Comprehensive experimental results on the Charades-STA and ActivityNet Captions datasets demonstrate the effectiveness of our BTDP method.

Shangqi Deng, Jun Ma, Liang-Jian Deng, Ping Wei

Implicit Neural Representation (INR) methods have demonstrated great potential in arbitrary-scale super-resolution tasks. This success is primarily due to their ability to continuously represent images using coordinates. In the task of remote sensing image fusion, INR methods have also shown promising applications. However, the previous INR methods neglect channel-wise modeling, while sharing a single kernel across all channels at each position, resulting in a lack of sensitivity to data specificity. To address these issues, we propose the OcTree Implicit Adaptive Sampling (OTIAS) method, which innovatively applies the octree structure to restore data from both horizontal and vertical directions, effectively incorporating spatial and spectral information from hyperspectral data. Additionally, we introduce a novel method to adaptively generate interpolation kernels based on coordinates. This approach efficiently produces customized interpolation kernel parameters for octree nodes, tailored to different spectral information. Overall, our method achieves state-of-the-art performance on the CAVE and Harvard datasets with 4× and 8× scaling factors, outperforming existing approaches.

Jiacheng Deng, Jiahao Lu

Unsupervised point cloud shape correspondence aims to establish point-wise correspondences between point clouds without annotated data. Ensuring efficiency and accuracy is crucial for practically implementing point cloud shape correspondence. Although the current methods have achieved desirable performance, the nature of encoding at dense points limits their application in actual scenarios. Moreover, independently computing per-point correspondences results in numerous multiple-to-one erroneous correspondences. To address these issues, we present an Adaptive siamese Masked autoencoder with Global Optimization (AMIGO), comprising a siamese masked autoencoder and a global optimization module. In the siamese masked autoencoder, we downsample the input point cloud and employ adaptive siamese mask operations to boost the coding capabilities of the encoder, thereby mitigating the information loss caused by downsampling. In the global optimization module, optimal transport is only utilized to generate pseudo-labels during the training phase, facilitating the efficient global planning of the correspondence results. Extensive experiments on four standard human and animal benchmarks demonstrate that AMIGO surpasses existing methods with remarkable margins, achieving new state-of-the-art results.

Jiacheng Deng, Jiahao Lu, Zhixin Cheng, Wenfei Yang

Unsupervised point cloud shape correspondence aims to establish dense correspondences between source and target point clouds. Existing methods universally follow a one-step paradigm to obtain shape correspondence directly, but it often fails in large-scale motions of humans and animals. To address this challenge, we propose a conditional Diffusion model with reliable pseudo-label guidance for unsupervised point cloud shape Correspondence (DiffCorr), including a transformer-based conditional diffusion model and a reliable pseudo-label generator. The proposed DiffCorr enjoys several merits. Firstly, the transformer-based conditional diffusion model implements a coarse-to-fine optimization for coarse correspondences. Secondly, we design a reliable pseudo-label generator to provide high-quality pseudo-labels for training. Extensive experiments on four human and animal datasets demonstrate that DiffCorr surpasses state-of-the-art methods and exhibits favorable generalization capabilities.

Hui Deng, Jiawei Shi, Zhen Qin, Yiran Zhong, Yuchao Dai

Non-Rigid Structure-from-Motion (NRSfM) is a classic 3D vision problem, where a 2D sequence is taken as input to estimate the corresponding 3D sequence. Recently, the deep neural networks have greatly advanced the task of NRSfM. However, existing deep NRSfM methods still have limitations in handling the inherent sequence property and motion ambiguity associated with the NRSfM problem. In this paper, we revisit deep NRSfM from two perspectives to address the limitations of current deep NRSfM methods : (1) canonicalization and (2) sequence modeling. We propose an easy-to-implement per-sequence canonicalization method as opposed to the previous per-dataset canonicalization approaches. With this in mind, we propose a sequence modeling method that combines temporal information and subspace constraint. As a result, we have achieved a more optimal NRSfM reconstruction pipeline compared to previous efforts. The effectiveness of our method is verified by testing the sequence-to-sequence deep NRSfM pipeline with corresponding regularization modules on several commonly used datasets.

Gabriel Della Maggiora, Luis Alberto Croquevielle, Harry Horsley, Thomas Heinis, Artur Yakimovich

Phase imaging is gaining importance due to its applications in fields like biomedical imaging and material characterization. In biomedical applications, it can provide quantitative information missing in label-free microscopy modalities. One of the most prominent methods in phase quantification is the Transport-of-Intensity Equation (TIE). TIE often requires multiple acquisitions at different defocus distances, which is not always feasible in a clinical setting due to hardware constraints. To address this issue, we propose the use of chromatic aberrations to induce the required through-focus images with a single exposure, effectively generating a through-focus stack. Since the defocus distance induced by the aberrations is small, conventional TIE solvers are insufficient to address the resulting artifacts. We propose Zero-Mean Diffusion, a modified version of diffusion models designed for quantitative image prediction, and train it with synthetic data to ensure robust phase retrieval. Our contributions offer an alternative TIE approach that leverages chromatic aberrations, achieving accurate single-exposure phase measurement with white light and thus improving the efficiency of phase imaging. Additionally, we present a new class of diffusion models that are well-suited for quantitative data and have a sound theoretical basis. To validate our approach, we employ a widespread brightfield microscope equipped with a commercially available color camera. We apply our model to clinical microscopy of patients' urine, obtaining accurate phase measurements.

Shristi Das Biswas, Matthew Shreve, Xuelu Li, Prateek Singhal, Kaushik Roy

Recent advancements in language-guided diffusion models for image editing are often bottle-necked by cumbersome prompt engineering to precisely articulate desired changes. An intuitive alternative calls on guidance from in-the-wild image exemplars to help users bring their imagined edits to life. Contemporary exemplar-based editing methods shy away from leveraging the rich latent space learnt by pre-existing large text-to-image (TTI) models and fall back on training with curated objective functions to achieve the task. Though somewhat effective, this demands significant computational resources and lacks compatibility with diverse base models and arbitrary exemplar count. On further investigation, we also find that these techniques restrict user control to only applying uniform global changes over the entire edited region. In this paper, we introduce a novel framework for progressive exemplar-driven editing with off-the-shelf diffusion models, dubbed PIXELS, to enable customization by providing granular control over edits, allowing adjustments at the pixel or region level. Our method operates solely during inference to facilitate imitative editing, enabling users to draw inspiration from a dynamic number of reference images, or multimodal prompts, and progressively incorporate all the desired changes without retraining or fine-tuning existing TTI models. This capability of fine-grained control opens up a range of new possibilities, including selective modification of individual objects and specifying gradual spatial changes. We demonstrate that PIXELS delivers high-quality edits efficiently, leading to a notable improvement in quantitative metrics as well as human evaluation. By making high-quality image editing more accessible, PIXELS has the potential to enable professional-grade edits to a wider audience with the ease of using any open-source image generation model.

Quan Dao, Hao Phung, Trung Tuan Dao, Dimitris N. Metaxas, Anh Tran

Flow matching has emerged as a promising framework for training generative models, demonstrating impressive empirical performance while offering relative ease of training compared to diffusion-based models. However, this method still requires numerous function evaluations in the sampling process. To address these limitations, we introduce a self-corrected flow distillation method that effectively integrates consistency models and adversarial training within the flow-matching framework. This work is a pioneer in achieving consistent generation quality in both few-step and one-step sampling. Our extensive experiments validate the effectiveness of our method, yielding superior results both quantitatively and qualitatively on CelebA-HQ and zero-shot benchmarks on the COCO dataset.

Yuqin Dai, Wanlu Zhu, Ronghui Li, Zeping Ren, Xiangzheng Zhou, Jixuan Ying, Jun Li, Jian Yang

Creating group choreography from music is crucial in cultural entertainment and virtual reality, with a focus on generating harmonious movements. Despite growing interest, recent approaches often struggle with two major challenges: multi-dancer collisions and single-dancer foot sliding. To address these challenges, we propose a Trajectory-Controllable Diffusion (TCDiff) framework, which leverages non-overlapping trajectories to ensure coherent and aesthetically pleasing dance movements. To mitigate collisions, we introduce a Dance-Trajectory Navigator that generates collision-free trajectories for multiple dancers, utilizing a distance-consistency loss to maintain optimal spacing. Furthermore, to reduce foot sliding, we present a footwork adaptor that adjusts trajectory displacement between frames, supported by a relative forward-kinematic loss to further reinforce the correlation between movements and trajectories. Experiments demonstrate our method's superiority.

Tao Dai, Yanzi Wang, Jianyu Xiong, Yaohua Zha, Shu-Tao Xia, Zexuan Zhu

Sampling strategy (e.g., fixed farthest point sampling) of point cloud has been an essential step for developing practical solutions in 3D computer vision tasks. Previous fixed sampling is simple, but suffer from suboptimal performance for downstream tasks. To adapt to target networks properly, adaptive sampling methods with trainable parameters have been recently developed to enhance the performance. However, existing adaptive sampling methods still suffer from the over-coupling problem of target network, and thus become model-specific, which limits their practical applications. To address this issue, we propose a novel general cross-scale decoupled sampling method (GCD-sampling) for point cloud, which consists of original feature cache, cross-scale feature fusion and convex combination learning for better feature extraction. To reduce the coupling relationship with the target task network, our method only utilizes the point cloud coordinates as the input and output of itself. Besides, we introduce an arbitrary scale structure to enable parameter sharing across multi-scale sampling in point cloud networks. Extensive experiments on different architectures demonstrate the effectiveness of our method over other existing adaptive sampling methods.

Tao Dai, Yang Lin, Hang Guo, Jinbao Wang, Zexuan Zhu

Knowledge distillation (KD) has recently gained great success in the field of object detection. By transferring the knowledge of the spatial or channel domain from the teacher model to the student model, it allows for a more compact representation with minimal performance loss. Despite this progress, existing KD methods typically treat knowledge from spatial or channel domains independently, ignoring the exploitation of the mutual relationship between these domains. In this work, we first explore the connection between spatial and channel domains and find there exists a strong correlation between them, i.e. the salient channels tend to contain significant object regions in the spatial domain. Motivated by this observation, we propose DCSF-KD, a novel Dynamic Channel-wise Spatial Feature Knowledge Distillation framework for object detection by fully exploiting both spatial and channel knowledge. Specifically, we introduce channel-wise spatial feature distillation and global channel attention distillation, using information from both domains to improve the accuracy of the student network. Experiments demonstrate that our DCSF-KD outperforms existing detection methods on both homogeneous and heterogeneous teacher-student network pairs. For example, when using the MaskRCNN-Swin detector as the teacher, and based on RetinaNet and FCOS with ResNet-50 on MS COCO, our DCSF-KD can achieve 41.9% and 44.1% mAP, respectively.

Ming Dai, Jian Li, Jiedong Zhuang, Xian Zhang, Wankou Yang

Multi-task visual grounding involves the simultaneous execution of localization and segmentation in images based on textual expressions. The majority of advanced methods predominantly focus on transformer-based multimodal fusion, aiming to extract robust multimodal representations. However, ambiguity between referring expression comprehension (REC) and referring image segmentation (RIS) is error-prone, leading to inconsistencies between multi-task predictions. Besides, insufficient multimodal understanding directly contributes to biased target perception. To overcome these challenges, we propose a Coarse-to-fine Consistency Constraints Visual Grounding architecture (C3VG), which integrates implicit and explicit modeling approaches within a two-stage framework. Initially, query and pixel decoders are employed to generate preliminary detection and segmentation outputs, a process referred to as the Rough Semantic Perception (RSP) stage. These coarse predictions are subsequently refined through the proposed Mask-guided Interaction Module (MIM) and a novel explicit bidirectional consistency constraint loss to ensure consistent representations across tasks, which we term the Refined Consistency Interaction (RCI) stage. Furthermore, to address the challenge of insufficient multimodal understanding, we leverage pre-trained models based on visual-linguistic fusion representations. Empirical evaluations on the RefCOCO, RefCOCO+, and RefCOCOg datasets demonstrate the efficacy and soundness of C3VG, which significantly outperforms state-of-the-art REC and RIS methods by a substantial margin.

Yubo Cui, Zhiheng Li, Jiaqiang Wang, Zheng Fang

Vision-based 3D occupancy prediction has become a popular research task due to its versatility and affordability. Nowadays, conventional methods usually project the image-based vision features to 3D space and learn the geometric information through the attention mechanism, enabling the 3D semantic occupancy prediction. However, these works usually face two main challenges: 1) Limited geometric information. Due to the lack of geometric information in the image itself, it is challenging to directly predict 3D space information, especially in large-scale outdoor scenes. 2) Local restricted interaction. Due to the quadratic complexity of the attention mechanism, they often use modified local attention to fuse features, resulting in a restricted fusion. To address these problems, in this paper, we propose a language-assisted 3D semantic occupancy prediction network, named LOMA. In the proposed vision-language framework, we first introduce a VL-aware Scene Generator (VSG) module to generate the 3D language feature of the scene. By leveraging the vision-language model, this module provides implicit geometric knowledge and explicit semantic information from the language. Furthermore, we present a Tri-plane Fusion Mamba (TFM) block to efficiently fuse the 3D language feature and 3D vision feature. The proposed module not only fuses the two features with global modeling but also avoids too much computation costs. Experiments on the SemanticKITTI and SSCBench-KITTI360 datasets show that our algorithm achieves new state-of-the-art performances in both geometric and semantic completion tasks. Our code will be open soon.

Antonio Emanuele Cinà, Jérôme Rony, Maura Pintor, Luca Demetrio, Ambra Demontis, Battista Biggio, Ismail Ben Ayed, Fabio Roli

While novel gradient-based attacks are continuously proposed to improve the optimization of adversarial examples, each is shown to outperform its predecessors using different experimental setups, implementations, and computational budgets, leading to biased and unfair comparisons. In this work, we overcome this issue by proposing AttackBench, i.e., an attack evaluation framework that evaluates the effectiveness of each attack (along with its different library implementations) under the same maximum available computational budget. To this end, we (i) define a novel optimality metric that quantifies how close each attack is to the optimal solution (empirically estimated by ensembling all attacks), and (ii) limit the maximum number of forward and backward queries that each attack can execute on the target model. Our extensive experimental analysis compares more than 100 attack implementations over 800 different configurations, considering both CIFAR-10 and ImageNet models, and shows that only a few attack implementations outperform all the remaining approaches. These findings suggest that novel defenses should be evaluated against different attacks than those normally used in the literature to avoid overly-optimistic robustness evaluations. We release AttackBench as a publicly-available benchmark that will be continuously updated with new attack implementations to maintain an up-to-date ranking of the best gradient-based attacks. We release AttackBench as a publicly available benchmark, including a continuously updated leaderboard and source code to maintain an up-to-date ranking of the best gradient-based attacks.

Jiwan Chung, Seungwon Lim, Sangkyu Lee, Youngjae Yu

Pretrained visual-language models have made significant advancements in multimodal tasks, including image-text retrieval. However, a major challenge in image-text matching lies in language bias, where models predominantly rely on language priors and neglect to adequately consider the visual content. We thus present Multimodal ASsociation Score (MASS), a framework that reduces the reliance on language priors for better visual accuracy in image-text matching problems. It can be seamlessly incorporated into existing visual-language models without necessitating additional training. Our experiments have shown that \modelname effectively lessens language bias without losing an understanding of linguistic compositionality. Overall, MASS offers a promising solution for enhancing image-text matching performance in visual-language models.

Chaeyeon Chung, Sunghyun Park, Jeongho Kim, Jaegul Choo

Hairstyle transfer is a challenging task in the image editing field that modifies the hairstyle of a given face image while preserving its other appearance and background features. The existing hairstyle transfer approaches heavily rely on StyleGAN, which is pre-trained on cropped and aligned face images. Hence, they struggle to generalize under challenging conditions such as extreme variations of head poses or focal lengths. To address this issue, we propose a one-stage hairstyle transfer diffusion model, HairFusion, that applies to real-world scenarios. Specifically, we carefully design a hair-agnostic representation as the input of the model, where the original hair information is thoroughly eliminated. Next, we introduce a hair align cross-attention (Align-CA) to accurately align the reference hairstyle with the face image while considering the difference in their head poses. To enhance the preservation of the face image’s original features, we leverage adaptive hair blending during the inference, where the output’s hair regions are estimated by the cross-attention map in Align-CA and blended with non-hair areas of the face image. Our experimental results show that our method achieves state-of-the-art performance compared to the existing methods in preserving the integrity of both the transferred hairstyle and the surrounding features.

Jisheng Chu, Wenrui Li, Xingtao Wang, Kanglin Ning, Yidan Lu, Xiaopeng Fan

The common occurrence of occlusion-induced incompleteness in point clouds has made point cloud completion (PCC) a highly-concerned task in the field of geometric processing. Existing PCC methods typically produce complete point clouds from partial point clouds in a coarse-to-fine paradigm, with the coarse stage generating entire shapes and the fine stage improving texture details. Though diffusion models have demonstrated effectiveness in the coarse stage, the fine stage still faces challenges in producing high-fidelity results due to the ill-posed nature of PCC. The intrinsic contextual information for texture details in partial point clouds is the key to solving the challenge. In this paper, we propose a high-fidelity PCC method that digs into both short and long-range contextual information from the partial point cloud in the fine stage. Specifically, after generating the coarse point cloud via a diffusion-based coarse generator, a mixed sampling module introduces short-range contextual information from partial point clouds into the fine stage. A surface freezing module safeguards points from noise-free partial point clouds against disruption. As for the long-range contextual information, we design a similarity modeling module to derive similarity with rigid transformation invariance between points, conducting effective matching of geometric manifold features globally. In this way, the high-quality components present in the partial point cloud serve as valuable references to refine the coarse point cloud with high fidelity. Extensive experiments have demonstrated the superiority of the proposed method over SOTA competitors.