论文检索

Yifan Zhou, Zeqi Xiao, Shuai Yang, Xingang Pan

Latent Diffusion Models (LDMs) are known to have an unstable generation process, where even small perturbations or shifts in the input noise can lead to significantly different outputs. This hinders their applicability in applications requiring consistent results. In this work, we redesign LDMs to enhance consistency by making them shift-equivariant. While introducing anti-aliasing operations can partially improve shift-equivariance, significant aliasing and inconsistency persist due to the unique challenges in LDMs, including 1) aliasing amplification during VAE training and multiple U-Net inferences, and 2) self-attention modules that inherently lack shift-equivariance. To address these issues, we redesign the attention modules to be shift-equivariant and propose an equivariance loss that effectively suppresses the frequency bandwidth of the features in the continuous domain. The resulting alias-free LDM (AF-LDM) achieves strong shift-equivariance and is also robust to irregular warping. Extensive experiments demonstrate that AF-LDM produces significantly more consistent results than vanilla LDM across various applications, including video editing and image-to-image translation.

Hoigi Seo, Wongi Jeong, Kyungryeol Lee, Se Young Chun

Diffusion models have shown remarkable performance in image synthesis, but they demand extensive computational and memory resources for training, fine-tuning and inference. Although advanced quantization techniques have successfully minimized memory usage for inference, training and fine-tuning these quantized models still require large memory possibly due to dequantization for accurate computation of gradients and/or backpropagation for gradient-based algorithms. However, memory-efficient fine-tuning is particularly desirable for applications such as personalization that often must be run on edge devices like mobile phones with private data. In this work, we address this challenge by quantizing a diffusion model with personalization via Textual Inversion and by leveraging a zeroth-order optimization on personalization tokens without dequantization so that it does not require gradient and activation storage for backpropagation that consumes considerable memory. Since a gradient estimation using zeroth-order optimization is quite noisy for a single or a few images in personalization, we propose to denoise the estimated gradient by projecting it onto a subspace that is constructed with the past history of the tokens, dubbed Subspace Gradient. In addition, we investigated the influence of text embedding in image generation, leading to our proposed time steps sampling, dubbed Partial Uniform Timestep Sampling for sampling with effective diffusion timesteps. Our method achieves comparable performance to prior methods in image and text alignment scores for personalizing Stable Diffusion with only forward passes while reducing training memory demand up to 8.2x. Project page: https://ignoww.github.io/ZOODiP_project/

Wei-Jin Huang, Yuan-Ming Li, Zhi-Wei Xia, Yu-Ming Tang, Kun-Yu Lin, Jian-Fang Hu, Wei-Shi Zheng

Error detection in procedural activities is essential for consistent and correct outcomes in AR-assisted and robotic systems. Existing methods often focus on temporal ordering errors or rely on static prototypes to represent normal actions. However, these approaches typically overlook the common scenario where multiple, distinct actions are valid following a given sequence of executed actions. This leads to two issues: (1) the model cannot effectively detect errors using static prototypes when the inference environment or action execution distribution differs from training; and (2) the model may also use the wrong prototypes to detect errors if the ongoing action label is not the same as the predicted one. To address this problem, we propose an Adaptive Multiple Normal Action Representation (AMNAR) framework. AMNAR predicts all valid next actions and reconstructs their corresponding normal action representations, which are compared against the ongoing action to detect errors. Extensive experiments demonstrate that AMNAR achieves state-of-the-art performance, highlighting the effectiveness of AMNAR and the importance of modeling multiple valid next actions in error detection. The code is available at https://github.com/iSEE-Laboratory/AMNAR.

Jiamin Wu, Kenkun Liu, Han Gao, Xiaoke Jiang, Yuan Yao, Lei Zhang

Rencently, Gaussian splatting has demonstrated significant success in novel view synthesis. Current methods often regress Gaussians with pixel or point cloud correspondence, linking each Gaussian with a pixel or a 3D point. This leads to the redundancy of Gaussians being used to overfit the correspondence rather than the objects represented by the 3D Gaussians themselves, consequently wasting resources and lacking accurate geometries or textures.In this paper, we introduce LeanGaussian, a novel approach that treats each query in deformable Transformer as one 3D Gaussian ellipsoid, breaking the pixel or point cloud correspondence constraints. We leverage deformable decoder to iteratively refine the Gaussians layer-by-layer with the image features as keys and values.Notably, the center of each 3D Gaussian is defined as 3D reference points, which are then projected onto the image for deformable attention in 2D space.On both the ShapeNet SRN dataset (category level) and the Google Scanned Objects dataset (open-category level, trained with the Objaverse dataset), our approach, outperforms prior methods by approximately 6.1%, achieving a PSNR of 25.44 and 22.36, respectively. Additionally, our method achieves a 3D reconstruction speed of 7.2 FPS and rendering speed 500 FPS.

Lingen Li, Zhaoyang Zhang, Yaowei Li, Jiale Xu, Wenbo Hu, Xiaoyu Li, Weihao Cheng, Jinwei Gu, Tianfan Xue, Ying Shan

Recent advancements in generative models have significantly improved novel view synthesis (NVS) from multi-view data. However, existing methods depend on external multi-view alignment processes, such as explicit pose estimation or pre-reconstruction, which limits their flexibility and accessibility, especially when alignment is unstable due to insufficient overlap or occlusions between views. In this paper, we propose NVComposer, a novel approach that eliminates the need for explicit external alignment. NVComposer enables the generative model to implicitly infer spatial and geometric relationships between multiple conditional views by introducing two key components: 1) an image-pose dual-stream diffusion model that simultaneously generates target novel views and condition camera poses, and 2) a geometry-aware feature alignment module that distills geometric priors from dense stereo models during training. Extensive experiments demonstrate that NVComposer achieves state-of-the-art performance in generative multi-view NVS tasks, removing the reliance on external alignment and thus improving model accessibility. Our approach shows substantial improvements in synthesis quality as the number of unposed input views increases, highlighting its potential for more flexible and accessible generative NVS systems.

Mingzhi Pei, Xu Cao, Xiangyi Wang, Heng Guo, Zhanyu Ma

Reflective and textureless surfaces remain a challenge in multi-view 3D reconstruction. Both camera pose calibration and shape reconstruction often fail due to insufficient or unreliable cross-view visual features. To address these issues, we present PMNI (Pose-free Multi-view Normal Integration), a neural surface reconstruction method that incorporates rich geometric information by leveraging surface normal maps instead of RGB images. By enforcing geometric constraints from surface normals and multi-view shape consistency within a neural signed distance function (SDF) optimization framework, PMNI simultaneously recovers accurate camera poses and high-fidelity surface geometry. Experimental results on synthetic and real-world datasets show that our method achieves state-of-the-art performance in the reconstruction of reflective surfaces, even without reliable initial camera poses.

Jingbo Lu, Leheng Zhang, Xingyu Zhou, Mu Li, Wen Li, Shuhang Gu

Learned image compression methods have attracted great research interest and exhibited superior rate-distortion performance to the best classical image compression standards of the present.The entropy model plays a key role in learned image compression, which estimates the probability distribution of the latent representation for further entropy coding.Most existing methods employed hyper-prior and auto-regressive architectures to form their entropy models.However, they only aimed to explore the internal dependencies of latent representation while neglecting the importance of extracting prior from training data.In this work, we propose a novel entropy model named Dictionary-based Cross Attention Entropy model, which introduces a learnable dictionary to summarize the typical structures occurring in the training dataset to enhance the entropy model.Extensive experimental results have demonstrated that the proposed model strikes a better balance between performance and latency, achieving state-of-the-art results on various benchmark datasets.

Chen Chen, Daochang Liu, Mubarak Shah, Chang Xu

Text-to-image diffusion models have demonstrated remarkable capabilities in creating images highly aligned with user prompts, yet their proclivity for memorizing training set images has sparked concerns about the originality of the generated images and privacy issues, potentially leading to legal complications for both model owners and users, particularly when the memorized images contain proprietary content. Although methods to mitigate these issues have been suggested, enhancing privacy often results in a significant decrease in the utility of the outputs, as indicated by text-alignment scores. To bridge the research gap, we introduce a novel method, PRSS, which refines the classifier-free guidance approach in diffusion models by integrating prompt re-anchoring (PR) to improve privacy and incorporating semantic prompt search (SS) to enhance utility. Extensive experiments across various privacy levels demonstrate that our approach consistently improves the privacy-utility trade-off, establishing a new state-of-the-art.

Jungsoo Lee, Debasmit Das, Munawar Hayat, Sungha Choi, Kyuwoong Hwang, Fatih Porikli

We propose a novel knowledge distillation approach, CustomKD, that effectively leverages large vision foundation models (LVFMs) to enhance the performance of edge models (e.g., MobileNetV3). Despite recent advancements in LVFMs, such as DINOv2 and CLIP, their potential in knowledge distillation for enhancing edge models remains underexplored. While knowledge distillation is a promising approach for improving the performance of edge models, the discrepancy in model capacities and heterogeneous architectures between LVFMs and edge models poses a significant challenge. Our observation indicates that although utilizing larger backbones (e.g., ViT-S to ViT-L) in teacher models improves their downstream task performances, the knowledge distillation from the large teacher models fails to bring as much performance gain for student models as for teacher models due to the large model discrepancy. Our simple yet effective CustomKD customizes the well-generalized features inherent in LVFMs to a given student model in order to reduce model discrepancies. Specifically, beyond providing well-generalized original knowledge from teachers, CustomKD aligns the features of teachers to those of students, making it easy for students to understand and overcome the large model discrepancy overall. CustomKD significantly improves the performances of edge models in scenarios with unlabeled data such as unsupervised domain adaptation (e.g., OfficeHome and DomainNet) and semi-supervised learning (e.g., CIFAR-100 with 400 labeled samples and ImageNet with 1% labeled samples), achieving the new state-of-the-art performances.

Mingjun Zheng, Long Sun, Jiangxin Dong, Jinshan Pan

Latency is a key driver for real-time rendering applications, making super-resolution techniques increasingly popular to accelerate rendering processes. In contrast to existing methods that directly concatenate low-resolution frames and G-buffers as input without discrimination, we develop an asymmetric UNet-based super-resolution network with decoupled G-buffer guidance, dubbed RDG, to facilitate the spatial and temporal feature exploration for minimizing performance overheads and latency.We first propose a dynamic feature modulator (DFM) to selectively encode the spatial information to capture precise structural information.We then incorporate auxiliary G-buffer information to guide the decoder to generate detail-rich, temporally stable results.Specifically, we adopt a high-frequency feature booster (HFB) to adaptively transfer the high-frequency information from the normal and bidirectional reflectance distribution function (BRDF) components of the G-buffer, enhancing the details of the generated results.To further enhance the temporal stability, we design a cross-frame temporal refiner (CTR) with depth and motion vector constraints to aggregate the previous and current frames.Extensive experimental results reveal that our proposed method is capable of generating high-quality and temporally stable results in real-time rendering.The proposed RDG-s produces 1080P rendering results on a RTX 3090 GPU with a speed of 126 FPS.

Soumya Suvra Ghosal, Souradip Chakraborty, Vaibhav Singh, Tianrui Guan, Mengdi Wang, Ahmad Beirami, Furong Huang, Alvaro Velasquez, Dinesh Manocha, Amrit Singh Bedi

With the widespread deployment of Multimodal Large Language Models (MLLMs) for visual-reasoning tasks, improving their safety has become crucial. Recent research indicates that despite training-time safety alignment, these models remain vulnerable to jailbreak attacks--carefully crafted image-prompt pairs that compel the model to generate harmful content. In this work, we first highlight a critical safety gap, demonstrating that alignment achieved solely through safety training may be insufficient against jailbreak attacks. To address this vulnerability, we propose Immune, an inference-time defense framework that leverages a safe reward model during decoding to defend against jailbreak attacks. Additionally, we provide a mathematical characterization of Immune, offering insights on why it improves safety against jailbreak. Extensive evaluations on diverse jailbreak benchmarks using recent MLLMs reveal that Immune effectively enhances model safety while preserving the model's original capabilities. For instance, against text-based jailbreak attacks on LLaVA-1.6, Immune reduces the attack success rate by 57.82% and 16.78% compared to the base MLLM and state-of-the-art defense strategy, respectively.

Pingyu Wu, Kai Zhu, Yu Liu, Liming Zhao, Wei Zhai, Yang Cao, Zheng-Jun Zha

Variational Autoencoder (VAE) aims to compress pixel data into low-dimensional latent space, playing an important role in OpenAI's Sora and other latent video diffusion generation models. While most existing video VAEs inflate a pre-trained image VAE into the 3D causal structure for temporal-spatial compression, this paper presents two astonishing findings: (1) The initialization from a well-trained image VAE with the same latent dimensions is not an optimal scheme. (2) The adoption of causal reasoning leads to unequal information interactions and unbalanced performance between frames. To alleviate these problems, we propose a keyframe-based temporal compression (KTC) architecture and a group causal convolution (GCConv) module to further improve video VAE (IV-VAE). Specifically, the KTC architecture divides the latent space into two branches, in which one half completely inherits the compression prior of keyframes from a lower-dimension image VAE while the other half involves temporal compression through 3D group causal convolution, reducing temporal-spatial conflicts and accelerating the convergence speed of video VAE. The GCConv in the above 3D half uses standard convolution within each frame group to ensure inter-frame equivalence, and employs causal logical padding between groups to maintain flexibility in processing variable frame video. Extensive experiments on five benchmarks demonstrate the SOTA video reconstruction and generation abilities of our IV-VAE.

Katrin Renz, Long Chen, Elahe Arani, Oleg Sinavski

Integrating large language models (LLMs) into autonomous driving has attracted significant attention with the hope of improving generalization and explainability. However, existing methods often focus on either driving or vision-language understanding but achieving both high driving performance and extensive language understanding remains challenging. In addition, the dominant approach to tackle vision-language understanding is using visual question answering. However, for autonomous driving, this is only useful if it is aligned with the action space. Otherwise, the model's answers could be inconsistent with its behavior. Therefore, we propose a model that can handle three different tasks: (1) closed-loop driving, (2) vision-language understanding, and (3) language-action alignment. Our model SimLingo is based on a vision language model (VLM) and works using only camera, excluding expensive sensors like LiDAR. SimLingo obtains state-of-the-art performance on the widely used CARLA simulator on the Bench2Drive benchmark and is the winning entry at the CARLA challenge 2024. Additionally, we achieve strong results in a wide variety of language-related tasks while maintaining high driving performance.

Jiayuan Rao, Haoning Wu, Hao Jiang, Ya Zhang, Yanfeng Wang, Weidi Xie

As a globally celebrated sport, soccer has attracted widespread interest from fans over the world. This paper aims to develop a comprehensive multi-modal framework for soccer video understanding.Specifically, we make the following contributions in this paper:(i) we introduce **SoccerReplay-1988**, the largest multi-modal soccer dataset to date, featuring videos and detailed annotations from 1,988 complete matches, with an automated annotation pipeline;(ii) we present the first visual-language foundation model in the soccer domain, **MatchVision**, which leverages spatiotemporal information across soccer videos and excels in various downstream tasks;(iii) we conduct extensive experiments and ablation studies on action classification, commentary generation, and multi-view foul recognition,and demonstrate state-of-the-art performance on all of them, substantially outperforming existing models, which has demonstrated the superiority of our proposed data and model. We believe that this work will offer a standard paradigm for sports understanding research. The code and model will be publicly available for reproduction.

Shanglin Liu, Jianming Lv, Jingdan Kang, Huaidong Zhang, Zequan Liang, Shengfeng He

Multimodal unsupervised domain adaptation leverages unlabeled data in the target domain to enhance multimodal systems continuously. While current state-of-the-art methods encourage interaction between sub-models of different modalities through pseudo-labeling and feature-level exchange, varying sample quality across modalities can lead to the propagation of inaccurate information, resulting in error accumulation. To address this, we propose Modal-Affinity Multimodal Domain Adaptation (MODfinity), a method that dynamically manages multimodal information flow through fine-grained control over teacher model selection, guiding information intertwining at both feature and label levels. By treating labels as an independent modality, MODfinity enables balanced performance assessment across modalities, employing a novel modal-affinity measurement to evaluate information quality. Additionally, we introduce a modal-affinity distillation technique to control sample-level information exchange, ensuring reliable multimodal interaction based on affinity evaluations within the feature space. Extensive experiments on three multimodal datasets demonstrate that our framework consistently outperforms state-of-the-art methods, particularly in high-noise environments.

Jeong Ryong Lee, Yejee Shin, Geonhui Son, Dosik Hwang

The modality gap between vision and text embeddings in CLIP presents a significant challenge for zero-shot image captioning, limiting effective cross-modal representation. Traditional approaches, such as noise injection and memory-based similarity matching, attempt to address this gap, yet these methods either rely on indirect alignment or relatively naive solutions with heavy computation. Diffusion Bridge introduces a novel approach to directly reduce this modality gap by leveraging Denoising Diffusion Probabilistic Models (DDPM), trained exclusively on text embeddings to model their distribution. Our approach is motivated by the observation that, while paired vision and text embeddings are relatively close, a modality gap still exists due to stable regions created by the contrastive loss. This gap can be interpreted as noise in cross-modal mappings, which we approximate as Gaussian noise. To bridge this gap, we employ a reverse diffusion process, where image embeddings are strategically introduced at an intermediate step in the reverse process, allowing them to be refined progressively toward the text embedding distribution. This process transforms vision embeddings into text-like representations closely aligned with paired text embeddings, effectively minimizing discrepancies between modalities. Experimental results demonstrate that these text-like vision embeddings significantly enhance alignment with their paired text embeddings, leading to improved zero-shot captioning performance on MSCOCO and Flickr30K. Diffusion Bridge achieves competitive results without reliance on memory banks or entity-driven methods, offering a novel pathway for cross-modal alignment and opening new possibilities for the application of diffusion models in multi-modal tasks. The source code is available at: https://github.com/mongeoroo/diffusion-bridge

Stefan Andreas Baumann, Felix Krause, Michael Neumayr, Nick Stracke, Melvin Sevi, Vincent Tao Hu, Björn Ommer

Recent advances in text-to-image (T2I) diffusion models have significantly improved the quality of generated images. However, providing efficient control over individual subjects, particularly the attributes characterizing them, remains a key challenge. While existing methods have introduced mechanisms to modulate attribute expression, they typically provide either detailed, object-specific localization of such a modification or full-scale fine-grained, nuanced control of attributes. No current approach offers both simultaneously, resulting in a gap when trying to achieve precise continuous and subject-specific attribute modulation in image generation. In this work, we demonstrate that token-level directions exist within commonly used CLIP text embeddings that enable fine-grained, subject-specific control of high-level attributes in T2I models. We introduce two methods to identify these directions: a simple, optimization-free technique and a learning-based approach that utilizes the T2I model to characterize semantic concepts more specifically. Our methods allow the augmentation of the prompt text input, enabling fine-grained control over multiple attributes of individual subjects simultaneously, without requiring any modifications to the diffusion model itself. This approach offers a unified solution that fills the gap between global and localized control, providing competitive flexibility and precision in text-guided image generation.

Junyi Chai, Shenyu Lu, Xiaoqian Wang

Multi-task learning (MTL) is a paradigm that aims to improve the generalization of models by simultaneously learning multiple related tasks, leveraging shared representations and task-specific information to enhance performance on individual tasks. However, existing work has shown that MTL can potentially hinder generalization, with one key factor being spurious correlations between tasks. Owing to the knowledge-sharing property, the per-task predictors are more likely to develop reliance on spurious features. Most existing approaches address this issue through distributional robustness, aiming to maintain consistent performance across different distributions under unknown covariate shifts. However, this formulation lacks theoretical guarantees and can be sensitive to the construction of covariate shifts. In this work, we propose a novel perspective, where we seek to identify spurious correlations between tasks. Drawing inspirations from conventional formulations on spurious correlation, for each task, we propose to distinguish its spurious tasks using the difference in correlation coefficients between the empirical distribution and class-wise resampled distributions, thereby capturing the correlations between task labels w.r.t. each class. We prove theoretically the feasibility of the resampling strategy in characterizing spurious correlations between tasks. Furthermore, we propose a simple fine-tuning strategy, debiased adversarial training, where the per-task predictors are adversarially trained to disregard information associated with their spurious tasks. Experimental results on six benchmark datasets show that our method effectively mitigates spurious correlations and outperforms state-of-the-art methods in improving generalization.

Soumyaratna Debnath, Ashish Tiwari, Kaustubh Sadekar, Shanmuganathan Raman

Recent advancements in learning-based methods have opened new avenues for exploring and interpreting art forms, such as shadow art, origami, and sketch art, through computational models. One notable visual art form is 3D Anamorphic Art in which an ensemble of arbitrarily shaped 3D objects creates a realistic and meaningful expression when observed from a particular viewpoint and loses its coherence over the other viewpoints. In this work, we build on insights from 3D Anamorphic Art to perform 3D object arrangement. We introduce RASP, a differentiable-rendering-based framework to arrange arbitrarily shaped 3D objects within a bounded volume via shadow (or silhouette)-guided optimization with an aim of minimal inter-object spacing and near-maximal occupancy. Furthermore, we propose a novel SDF-based formulation to handle inter-object intersection and container extrusion. We demonstrate that RASP can be extended to part assembly alongside object packing considering 3D objects to be "parts" of another 3D object. Finally, we present artistic illustrations of multi-view anamorphic art, achieving meaningful expressions from multiple viewpoints within a single ensemble.

Jie Huang, Haorui Chen, Jiaxuan Ren, Siran Peng, Liangjian Deng

Currently, deep learning-based methods for remote sensing pansharpening have advanced rapidly. However, many existing methods struggle to fully leverage feature heterogeneity and redundancy, thereby limiting their effectiveness. To address these challenges across two key dimensions, we introduce a general adaptive dual-level weighting mechanism (ADWM), designed to enhance a wide range of existing deep-learning methods. First, Intra-Feature Weighting (IFW) evaluates correlations among channels within each feature and selectively weighs to reduce redundancy and enhance unique information. Second, Cross-Feature Weighting (CFW) adjusts contributions across layers based on inter-layer correlations, refining the final output by preserving key distinctions across feature depths. This dual-level weighting is efficiently implemented through our proposed Correlation-Aware Covariance Weighting (CACW), which generates weights by utilizing the correlations captured within the covariance matrix. Extensive experiments demonstrate the superior performance of ADWM compared to recent state-of-the-art (SOTA) methods. Furthermore, we validate the effectiveness of our approach through generality experiments, ablation studies, comparison experiments, and detailed visual analysis.