论文检索

Yue Han, Jiangning Zhang, Junwei Zhu, Runze Hou, Xiaozhong Ji, Chuming Lin, Xiaobin Hu, Zhucun Xue, Yong Liu

Multimodal Language Learning Models (MLLMs) have shown remarkable performance in image understanding, generation, and editing, with recent advancements achieving pixel-level grounding with reasoning. However, these models for common objects struggle with fine-grained face understanding. In this work, we introduce the FacePlayGround-240K dataset, the first pioneering large-scale, pixel-grounded face caption and question-answer (QA) dataset, meticulously curated for alignment pretraining and instruction-tuning. We present the GroundingFace framework, specifically designed to enhance fine-grained face understanding. This framework significantly augments the capabilities of existing grounding models in face part segmentation, face attribute comprehension, while preserving general scene understanding. Comprehensive experiments validate that our approach surpasses current state-of-the-art models in pixel-grounded face captioning/QA and various downstream tasks, including face captioning, referring segmentation, and zero-shot face attribute recognition.

Qitao Zhao, Amy Lin, Jeff Tan, Jason Y. Zhang, Deva Ramanan, Shubham Tulsiani

Current Structure-from-Motion (SfM) methods typically follow a two-stage pipeline, combining learned or geometric pairwise reasoning with a subsequent global optimization step. In contrast, we propose a data-driven multi-view reasoning approach that directly infers 3D scene geometry and camera poses from multi-view images. Our framework, DiffusionSfM, parameterizes scene geometry and cameras as pixel-wise ray origins and endpoints in a global frame and employs a transformer-based denoising diffusion model to predict them from multi-view inputs. To address practical challenges in training diffusion models with missing data and unbounded scene coordinates, we introduce specialized mechanisms that ensure robust learning. We empirically validate DiffusionSfM on both synthetic and real datasets, demonstrating that it outperforms classical and learning-based approaches while naturally modeling uncertainty.

Lanyun Zhu, Tianrun Chen, Qianxiong Xu, Xuanyi Liu, Deyi Ji, Haiyang Wu, De Wen Soh, Jun Liu

Existing LVLM-based reasoning segmentation methods often suffer from imprecise segmentation results and hallucinations in their text responses. This paper introduces POPEN, a novel framework designed to address these issues and achieve improved results. POPEN includes a preference-based optimization method to finetune the LVLM, aligning it more closely with human preferences and thereby generating better text responses and segmentation results. Additionally, POPEN introduces a preference-based ensemble method for inference, which integrates multiple outputs from the LVLM using a preference-score-based attention mechanism for refinement. To better adapt to the segmentation task, we incorporate several task-specific designs in our POPEN framework, including a new approach for collecting segmentation preference data with a curriculum learning mechanism, and a novel preference optimization loss to refine the segmentation capability of the LVLM. Experiments demonstrate that our method achieves state-of-the-art performance in reasoning segmentation, exhibiting minimal hallucination in text responses and the highest segmentation accuracy compared to previous advanced methods like LISA and PixelLM.

Xuecheng Wu, Heli Sun, Yifan Wang, Jiayu Nie, Jie Zhang, Yabing Wang, Junxiao Xue, Liang He

Affective Video Facial Analysis (AVFA) is important for advancing emotion-aware AI, yet the persistent data scarcity in AVFA presents challenges. Recently, the self-supervised learning (SSL) technique of Masked Autoencoders (MAE) has gained significant attention, particularly in its audio-visual adaptation. Insights from general domains suggest that scaling is vital for unlocking impressive improvements, though its effects on AVFA remain largely unexplored. Additionally, capturing both intra- and inter-modal correlations through scalable representations is a crucial challenge in this field. To tackle these gaps, we introduce AVF-MAE++, a series audio-visual MAE designed to explore the impact of scaling on AVFA with a focus on advanced correlation modeling. Our method incorporates a novel audio-visual dual masking strategy and an improved modality encoder with a holistic view to better support scalable pre-training. Furthermore, we propose the Iteratively Audio-Visual Correlations Learning Module to improve correlations capture within the SSL framework, bridging the limitations of prior methods. To support smooth adaptation and mitigate overfitting, we also introduce a progressive semantics injection strategy, which structures training in three stages. Extensive experiments across 17 datasets, spanning three key AVFA tasks, demonstrate the superior performance of AVF-MAE++, establishing new state-of-the-art outcomes. Ablation studies provide further insights into the critical design choices driving these gains. Code is released at https://github.com/XuecWu/AVF-MAE.

Guangzhao He, Chen Geng, Shangzhe Wu, Jiajun Wu

The motion of deformable 4D objects lies in a low-dimensional manifold. To better capture the low dimensionality and enable better controllability, traditional methods have devised several heuristic-based methods, i.e., rigging, for manipulating dynamic objects in an intuitive fashion. However, such representations are not scalable due to the need for expert knowledge of specific categories. Instead, we study the automatic exploration of such low-dimensional structures in a purely data-driven manner. Specifically, we design a novel representation that encodes deformable 4D objects into a sparse set of spatially grounded blobs and an instance-aware feature volume to disentangle the pose and instance information of the 3D shape. With such a representation, we can manipulate the pose of 3D objects intuitively by modifying the parameters of the blobs, while preserving rich instance-specific information. We evaluate the proposed method on a variety of object categories and demonstrate the effectiveness of the proposed framework. Project page: https://guangzhaohe.com/canor.

Yang Bai, Yucheng Ji, Min Cao, Jinqiao Wang, Mang Ye

Traditional text-based person retrieval (TPR) relies on a single-shot text as query to retrieve the target person, assuming that the query completely captures the user's search intent. However, in real-world scenarios, it can be challenging to ensure the information completeness of such single-shot text. To address this limitation, we propose chat-based person retrieval (ChatPR), a new paradigm that takes an interactive dialogue as query to perform the person retrieval, engaging the user in conversational context to progressively refine the query for accurate person retrieval. The primary challenge in ChatPR is the lack of available dialogue-image paired data. To overcome this challenge, we establish ChatPedes, the first dataset designed for ChatPR, which is constructed by leveraging large language models to automate the question generation and simulate user responses. Additionally, to bridge the modality gap between dialogues and images, we propose a dialogue-refined cross-modal alignment (DiaNA) framework, which leverages two adaptive attribute refiners to bottleneck the conversational and visual information for fine-grained cross-modal alignment. Moreover, we propose a dialogue-specific data augmentation strategy, random round retaining, to further enhance the model's generalization ability across varying dialogue lengths. Extensive experiments demonstrate that DiaNA significantly outperforms existing TPR approaches, highlighting the effectiveness of conversational interactions for person retrieval.

Xiangyu Liu, Xiaomei Zhang, Zhiyuan Ma, Xiangyu Zhu, Zhen Lei

Recent advancements in 3D object reconstruction have been remarkable, yet most current 3D models rely heavily on existing 3D datasets. The scarcity of diverse 3D datasets results in limited generalization capabilities of 3D reconstruction models. In this paper, we propose a novel framework for boosting 3D reconstruction with multi-view refinement (MVBoost) by generating pseudo-GT data. The key of MVBoost is combining the advantages of the high accuracy of the multi-view generation model and the consistency of the 3D reconstruction model to create a reliable data source. Specifically, given a single-view input image, we employ a multi-view diffusion model to generate multiple views, followed by a large 3D reconstruction model to produce consistent 3D data. MVBoost then adaptively refines these multi-view images, rendered from the consistent 3D data, to build a large-scale multi-view dataset for training a feed-forward 3D reconstruction model. Additionally, the input view optimization is designed to optimize the corresponding viewpoints based on the user's input image, ensuring that the most important viewpoint is accurately tailored to the user's needs. Extensive evaluations demonstrate that our method achieves superior reconstruction results and robust generalization compared to prior works.

Zijian He, Yuwei Ning, Yipeng Qin, Guangrun Wang, Sibei Yang, Liang Lin, Guanbin Li

Virtual Try-On (VTON) is a transformative technology in e-commerce and fashion design, enabling realistic digital visualization of clothing on individuals. In this work, we propose VTON 360, a novel 3D VTON method that addresses the open challenge of achieving high-fidelity VTON that supports any-view rendering. Specifically, we leverage the equivalence between a 3D model and its rendered multi-view 2D images, and reformulate 3D VTON as an extension of 2D VTON that ensures 3D consistent results across multiple views.To achieve this, we extend 2D VTON models to include multi-view garments and clothing-agnostic human body images as input, and propose several novel techniques to enhance them, including: i) a pseudo-3D pose representation using normal maps derived from the SMPL-X 3D human model, ii) a multi-view spatial attention mechanism that models the correlations between features from different viewing angles, and iii) a multi-view CLIP embedding that enhances the garment CLIP features used in 2D VTON with camera information. Extensive experiments on large-scale real datasets and clothing images from e-commerce platforms demonstrate the effectiveness of our approach.

Zichen Miao, Wei Chen, Qiang Qiu

Transformer-based large pre-trained models have shown remarkable generalization ability, and various parameter-efficient fine-tuning (PEFT) methods have been proposed to customize these models on downstream tasks with minimal computational and memory budgets. Previous PEFT methods are primarily designed from a tensor-decomposition perspective that tries to effectively tune the linear transformation by finding the smallest subset of parameters to train. Our study adopts an orthogonal view by representing the attention operation as a graph convolution and formulating the multi-head attention maps as a convolutional filter subspace, with each attention map as a subspace element. In this paper, we propose to tune the large pre-trained transformers by learning a small set of combination coefficients that construct a more expressive filter subspace from the original multi-head attention maps. We show analytically and experimentally that the tuned filter subspace can effectively expand the feature space of the multi-head attention and further enhance the capacity of transformers. We further stabilize the fine-tuning with a residual parameterization of the tunable subspace coefficients, and enhance the generalization with a regularization design by directly applying dropout on the tunable coefficient during training. The tunable coefficients take a tiny number of parameters and can be combined with previous PEFT methods in a plug-and-play manner. Extensive experiments show that our approach achieves superior performances than PEFT baselines with neglectable additional parameters.

Nanye Ma, Shangyuan Tong, Haolin Jia, Hexiang Hu, Yu-Chuan Su, Mingda Zhang, Xuan Yang, Yandong Li, Tommi Jaakkola, Xuhui Jia 等

Generative models have made significant impacts across various domains, largely due to their ability to scale during training by increasing data, computational resources, and model size, a phenomenon characterized by the scaling laws. Recent research has begun to explore inference-time scaling behavior in Large Language Models (LLMs), revealing how performance can further improve with additional computation during inference. Unlike LLMs, diffusion models inherently possess the flexibility to adjust inference-time computation via the number of denoising steps, although the performance gains typically flatten after a few dozen. In this work, we explore the inference-time scaling behavior of diffusion models beyond increasing denoising steps and investigate how the generation performance can further improve with increased computation. Specifically, we consider a search problem aimed at identifying better noises for the diffusion sampling process. We structure the design space along two axes: the verifiers used to provide feedback, and the algorithms used to find better noise candidates. Through extensive experiments on class-conditioned and text-conditioned image generation benchmarks, our findings reveal that increasing inference-time compute leads to substantial improvements in the quality of samples generated by diffusion models, and with the complicated nature of images, combinations of the components in the framework can be specifically chosen to conform with different application scenario.

Cheng-De Fan, Chen-Wei Chang, Yi-Ruei Liu, Jie-Ying Lee, Jiun-Long Huang, Yu-Chee Tseng, Yu-Lun Liu

We present SpectroMotion, a novel approach that combines 3D Gaussian Splatting (3DGS) with physically-based rendering (PBR) and deformation fields to reconstruct dynamic specular scenes. Previous methods extending 3DGS to model dynamic scenes have struggled to represent specular surfaces accurately. Our method addresses this limitation by introducing a residual correction technique for accurate surface normal computation during deformation, complemented by a deformable environment map that adapts to time-varying lighting conditions. We implement a coarse-to-fine training strategy significantly enhancing scene geometry and specular color prediction. It is the only existing 3DGS method capable of synthesizing photorealistic real-world dynamic specular scenes, outperforming state-of-the-art methods in rendering complex, dynamic, and specular scenes. Please see our project page at https://cdfan0627.github.io/spectromotion/.

Zhangqi Jiang, Junkai Chen, Beier Zhu, Tingjin Luo, Yankun Shen, Xu Yang

Hallucinations in Large Vision-Language Models (LVLMs) significantly undermine their reliability, motivating researchers to explore the causes of hallucination. However, most studies primarily focus on the language aspect rather than the visual. In this paper, we address how LVLMs process visual information and whether this process causes hallucination. Firstly, we use the attention lens to identify the stages at which LVLMs handle visual data, discovering that the middle layers are crucial. Moreover, we find that these layers can be further divided into two stages: "visual information enrichment" and "semantic refinement" which respectively propagate visual data to object tokens and interpret it through text. By analyzing attention patterns during the visual information enrichment stage, we find that real tokens consistently receive higher attention weights than hallucinated ones, serving as a strong indicator of hallucination. Further examination of multi-head attention maps reveals that hallucination tokens often result from heads interacting with inconsistent objects. Based on these insights, we propose a simple inference-time method that adjusts visual attention by integrating information across various heads. Extensive experiments demonstrate that this approach effectively mitigates hallucinations in mainstream LVLMs without additional training costs.

Suho Ryu, Kihyun Kim, Eugene Baek, Dongsoo Shin, Joonseok Lee

A variety of text-guided image editing models have been proposed recently. However, there is no widely-accepted standard evaluation method mainly due to the subjective nature of the task, letting researchers rely on manual user study. To address this, we introduce a novel Human-Aligned benchmark for Text-guided Image Editing (HATIE). Providing a large-scale benchmark set covering a wide range of editing tasks, it allows reliable evaluation, not limited to specific easy-to-evaluate cases. Also, HATIE provides a fully-automated and omnidirectional evaluation pipeline. Particularly, we combine multiple scores measuring various aspects of editing so as to align with human perception. We empirically verify that the evaluation of HATIE is indeed human-aligned in various aspects, and provide benchmark results on several state-of-the-art models to provide deeper insights on their performance.

Sizai Hou, Songze Li, Duanyi Yao

Self-supervised learning (SSL) is pervasively exploited in training high-quality upstream encoders with a large amount of unlabeled data. However, it is found to be susceptible to backdoor attacks merely via polluting a small portion of training data. The victim encoders associate triggered inputs with target embeddings, e.g., mapping a triggered cat image to an airplane embedding, such that the downstream tasks inherit unintended behaviors when the trigger is activated. Emerging backdoor attacks have shown great threats across different SSL paradigms such as contrastive learning and CLIP, yet limited research is devoted to defending against such attacks, and existing defenses fall short in detecting advanced stealthy backdoors. To address the limitations, we propose a novel detection mechanism, DeDe, which detects the activation of backdoor mappings caused by triggered inputs on victim encoders. Specifically, DeDe trains a decoder for any given SSL encoder using an auxiliary dataset (which can be out-of-distribution or even slightly poisoned), so that for any triggered input that misleads the encoder into the target embedding, the decoder generates an output image significantly different from the input. DeDe leverages the discrepancy between the input and the decoded output to identify potential backdoor misbehavior during inference. We empirically evaluate DeDe on both contrastive learning and CLIP models against various types of backdoor attacks. Our results demonstrate promising detection effectiveness over various advanced attacks and superior performance compared over state-of-the-art detection methods.

Junyuan Deng, Xinyi Wu, Yongxing Yang, Congchao Zhu, Song Wang, Zhenyao Wu

Recently, pre-trained text-to-image (T2I) models have been extensively adopted for real-world image restoration because of their powerful generative prior. However, controlling these large models for image restoration usually requires a large number of high-quality images and immense computational resources for training, which is costly and not privacy-friendly. In this paper, we find that the well-trained large T2I model (i.e., Flux) is able to produce a variety of high-quality images aligned with real-world distributions, offering an unlimited supply of training samples to mitigate the above issue. Specifically, we proposed a training data construction pipeline for image restoration, namely FluxGen, which includes unconditional image generation, image selection, and degraded image simulation. A novel light-weighted adapter (FluxIR) with squeeze-and-excitation layers is also carefully designed to control the large Diffusion Transformer (DiT)-based T2I model so that reasonable details can be restored. Experiments demonstrate that our proposed method enables the Flux model to adapt effectively to real-world image restoration tasks, achieving superior scores and visual quality on both synthetic and real-world degradation datasets - at only about 8.5% of the training cost compared to current approaches.

Ye Chen, Zhangli Hu, Zhongyin Zhao, Yupeng Zhu, Yue Shi, Yuxuan Xiong, Bingbing Ni

Current parameterized image representations embed visual information along the semantic boundaries and struggle to express the internal detailed texture structures of image components, leading to a lack of content consistency after image editing and driving. To address these challenges, this work proposes a novel parameterized representation based on hierarchical image proxy geometry, utilizing multi-layer hierarchically interrelated proxy geometric control points to embed multi-scale long-range structures and fine-grained texture details. The proposed representation enables smoother and more continuous interpolation during image rendering and ensures high-quality consistency within image components during image editing. Additionally, under the layer-wise representation strategy based on semantic-aware image layer decomposition, we enable decoupled image shape/texture editing of the targets of interest within the image. Extensive experimental results on image vectorization and editing tasks demonstrate that our proposed method achieves high rendering accuracy of general images, including natural images, with a significantly higher image parameter compression ratio, facilitating user-friendly editing of image semantic components.

Xingguo Lv, Xingbo Dong, Liwen Wang, Jiewen Yang, Lei Zhao, Bin Pu, Zhe Jin, Xuejun Li

Despite domain generalization (DG) has significantly addressed the performance degradation of pre-trained models caused by domain shifts, it often falls short in real-world deployment. Test-time adaptation (TTA), which adjusts a learned model using unlabeled test data, presents a promising solution. However, most existing TTA methods struggle to deliver strong performance in medical image segmentation, primarily because they overlook the crucial prior knowledge inherent to medical images. To address this challenge, we incorporate morphological information and propose a framework based on multi-graph matching. Specifically, we introduce learnable universe embeddings that integrate morphological priors during multi-source training, along with novel unsupervised test-time paradigms for domain adaptation. This approach guarantees cycle-consistency in multi-matching while enabling the model to more effectively capture the invariant priors of unseen data, significantly mitigating the effects of domain shifts. Extensive experiments demonstrate that our method outperforms other state-of-the-art approaches on two medical image segmentation benchmarks for both multi-source and single-source domain generalization tasks. The source code is available at https://github.com/Yore0/TTDG-MGM.

Hou-I Liu, Christine Wu, Jen-Hao Cheng, Wenhao Chai, Shian-Yun Wang, Gaowen Liu, Hugo Latapie, Jhih-Ciang Wu, Jenq-Neng Hwang, Hong-Han Shuai 等

Monocular 3D object detection (Mono3D) holds noteworthy promise for autonomous driving applications owing to the cost-effectiveness and rich visual context of monocular camera sensors. However, depth ambiguity poses a significant challenge, as it requires extracting precise 3D scene geometry from a single image, resulting in suboptimal performance when transferring knowledge from a LiDAR-based teacher model to a camera-based student model. To facilitate effective distillation, we introduce Monocular Teaching Assistant Knowledge Distillation (MonoTAKD), which proposes a camera-based teaching assistant (TA) model to transfer robust 3D visual knowledge to the student model, leveraging the smaller feature representation gap. Additionally, we define 3D spatial cues as residual features that capture the differences between the teacher and the TA models. We then leverage these cues to improve the student model's 3D perception capabilities. Experimental results show that our MonoTAKD achieves state-of-the-art performance on the KITTI3D dataset. Furthermore, we evaluate the performance on nuScenes and KITTI raw datasets to demonstrate the generalization of our model to multi-view 3D and unsupervised data settings. Our code is available at https://github.com/hoiliu-0801/MonoTAKD.

Kang Liu, Zhuoqi Ma, Xiaolu Kang, Yunan Li, Kun Xie, Zhicheng Jiao, Qiguang Miao

Automated radiology report generation offers an effective solution to alleviate radiologists' workload. However, most existing methods focus primarily on single or fixed-view images to model current disease conditions, which limits diagnostic accuracy and overlooks disease progression. Although some approaches utilize longitudinal data to track disease progression, they still rely on single images to analyze current visits. To address these issues, we propose enhanced contrastive learning with Multi-view Longitudinal data to facilitate chest X-ray Report Generation, named MLRG. Specifically, we introduce a multi-view longitudinal contrastive learning method that integrates spatial information from current multi-view images and temporal information from longitudinal data. This method also utilizes the inherent spatiotemporal information of radiology reports to supervise the pre-training of visual and textual representations. Subsequently, we present a tokenized absence encoding technique to flexibly handle missing patient-specific prior knowledge, allowing the model to produce more accurate radiology reports based on available prior knowledge. Extensive experiments on MIMIC-CXR, MIMIC-ABN, and Two-view CXR datasets demonstrate that our MLRG outperforms recent state-of-the-art methods, achieving a 2.3% BLEU-4 improvement on MIMIC-CXR, a 5.5% F1 score improvement on MIMIC-ABN, and a 2.7% F1 RadGraph improvement on Two-view CXR.

Xingxuan Zhang, Jiansheng Li, Wenjing Chu, junjia hai, Renzhe Xu, Yuqing Yang, Shikai Guan, Jiazheng Xu, Liping Jing, Peng Cui

We investigate the generalization boundaries of current Large Multimodal Models (LMMs) via comprehensive evaluation under out-of-distribution scenarios and domain-specific tasks. We evaluate their zero-shot generalization across synthetic images, real-world distributional shifts, and specialized datasets like medical and molecular imagery. Empirical results indicate that LMMs struggle with generalization beyond common training domains, limiting their direct application without adaptation. To understand the cause of unreliable performance, we analyze three hypotheses: semantic misinterpretation, visual feature extraction insufficiency, and mapping deficiency. Results identify mapping deficiency as the primary hurdle. To address this problem, we show that in-context learning (ICL) can significantly enhance LMMs' generalization, opening new avenues for overcoming generalization barriers. We further explore the robustness of ICL under distribution shifts and show its vulnerability to domain shifts, label shifts, and spurious correlation shifts between in-context examples and test data.