论文检索

Gaojian Wang, Feng Lin, Tong Wu, Zhenguang Liu, Zhongjie Ba, Kui Ren

This work asks: with abundant, unlabeled real faces, how to learn a robust and transferable facial representation that boosts various face security tasks with respect to generalization performance? We make the first attempt and propose a self-supervised pretraining framework to learn fundamental representations of real face images, FSFM, that leverages the synergy between masked image modeling (MIM) and instance discrimination (ID). We explore various facial masking strategies for MIM and present a simple yet powerful CRFR-P masking, which explicitly forces the model to capture meaningful intra-region Consistency and challenging inter-region Coherency. Furthermore, we devise an ID network that naturally couples with MIM to establish underlying local-to-global Correspondence through tailored self-distillation. These three learning objectives, namely 3C, empower encoding both local features and global semantics of real faces. After pretraining, a vanilla ViT serves as a universal vision Foundation Model for downstream Face Security tasks: cross-dataset deepfake detection, cross-domain face anti-spoofing, and unseen diffusion facial forgery detection. Extensive experiments on 10 public datasets demonstrate that our model transfers better than supervised pretraining, visual and facial self-supervised learning arts, and even outperforms task-specialized SOTA methods.

Guillaume Astruc, Nicolas Gonthier, Clément Mallet, Loic Landrieu

Geospatial models must adapt to the diversity of Earth observation data in terms of resolutions, scales, and modalities. However, existing approaches expect fixed input configurations, which limits their practical applicability. We propose AnySat, a multimodal model based on joint embedding predictive architecture (JEPA) and scale-adaptive spatial encoders, allowing us to train a single model on highly heterogeneous data in a self-supervised manner. To demonstrate the advantages of this unified approach, we compile GeoPlex, a collection of 5 multimodal datasets with varying characteristics and 11 distinct sensors. We then train a single powerful model on these diverse datasets simultaneously. Once fine-tuned or probed, we achieve state-of-the-art results on the test sets of GeoPlex and for 6 external datasets across various environment monitoring tasks: land cover mapping, tree species identification, crop type classification, change detection, climate type classification, and segmentation of flood, burn scar, and deforestation. Our code and models are available at https://github.com/gastruc/AnySat.

Trong-Thuan Nguyen, Pha Nguyen, Jackson Cothren, Alper Yilmaz, Khoa Luu

Multimodal LLMs have advanced vision-language tasks but still struggle with understanding video scenes. To bridge this gap, Video Scene Graph Generation (VidSGG) has emerged to capture multi-object relationships across video frames. However, prior methods rely on pairwise connections, limiting their ability to handle complex multi-object interactions and reasoning. To this end, we propose Multimodal LLMs on a Scene HyperGraph (HyperGLM), promoting reasoning about multi-way interactions and higher-order relationships. Our approach uniquely integrates entity scene graphs, which capture spatial relationships between objects, with a procedural graph that models their causal transitions, forming a unified HyperGraph. Significantly, HyperGLM enables reasoning by injecting this unified HyperGraph into LLMs. Additionally, we introduce a new Video Scene Graph Reasoning (VSGR) dataset featuring 1.9M frames from third-person, egocentric, and drone views and supports five tasks: Scene Graph Generation, Scene Graph Anticipation, Video Question Answering, Video Captioning, and Relation Reasoning. Empirically, HyperGLM consistently outperforms state-of-the-art methods across five tasks, effectively modeling and reasoning complex relationships in diverse video scenes.

Aviral Chharia, Wenbo Gou, Haoye Dong

While significant progress has been made in single-view 3D human pose estimation, multi-view 3D human pose estimation remains challenging, particularly in terms of generalizing to new camera configurations. Existing attention-based transformers often struggle to accurately model the spatial arrangement of keypoints, especially in occluded scenarios. Additionally, they tend to overfit specific camera arrangements and visual scenes from training data, resulting in substantial performance drops in new settings. In this study, we introduce a novel Multi-View State Space Modeling framework, named MV-SSM, for robustly estimating 3D human keypoints. We explicitly model the joint spatial sequence at two distinct levels: the feature level from multi-view images and the person keypoint level. We propose a Projective State Space (PSS) block to learn a generalized representation of joint spatial arrangements using state space modeling. Moreover, we modify Mamba's traditional scanning into an effective Grid Token-guided Bidirectional Scanning (GTBS), which is integral to the PSS block. Multiple experiments demonstrate that MV-SSM achieves strong generalization, outperforming state-of-the-art methods: +10.8 on AP25 on the challenging three-camera setting in CMU Panoptic, +7.0 on AP25 on varying camera arrangements, and +15.3 PCP on Campus A1 in cross-dataset evaluations. Project Website: https://aviralchharia.github.io/MV-SSM

Zeyi Xu, Jinfan Liu, Kuangxu Chen, Ye Chen, Zhangli Hu, Bingbing Ni

Accurately and efficiently simulating complex fluid dynamics is a challenging task that has traditionally relied on computationally intensive methods. Neural network-based approaches, such as convolutional and graph neural networks, have partially alleviated this burden by enabling efficient local feature extraction. However, they struggle to capture long-range dependencies due to limited receptive fields, and Transformer-based models, while providing global context, incur prohibitive computational costs. To tackle these challenges, we propose AMR-Transformer, an efficient and accurate neural CFD-solving pipeline that integrates a novel adaptive mesh refinement scheme with a Navier-Stokes constraint-aware fast pruning module. This design encourages long-range interactions between simulation cells and facilitates the modeling of global fluid wave patterns, such as turbulence and shockwaves. Experiments show that our approach achieves significant gains in efficiency while preserving critical details, making it suitable for high-resolution physical simulations with long-range dependencies. On CFDBench, PDEBench and a new shockwave dataset, our pipeline demonstrates up to an order-of-magnitude improvement in accuracy over baseline models. Additionally, compared to ViT, our approach achieves a reduction in FLOPs of up to 60 times.

Taha Koleilat, Hojat Asgariandehkordi, Hassan Rivaz, Yiming Xiao

Recent advancements in vision-language models (VLMs), such as CLIP, have demonstrated substantial success in self-supervised representation learning for vision tasks. However, effectively adapting VLMs to downstream applications remains challenging, as their accuracy often depends on time-intensive and expertise-demanding prompt engineering, while full model fine-tuning is costly. This is particularly true for biomedical images, which, unlike natural images, typically suffer from limited annotated datasets, unintuitive image contrasts, and nuanced visual features. Recent prompt learning techniques, such as Context Optimization (CoOp) intend to tackle these issues, but still fall short in generalizability. Meanwhile, explorations in prompt learning for biomedical image analysis are still highly limited. In this work, we propose BiomedCoOp, a novel prompt learning framework that enables efficient adaptation of BiomedCLIP for accurate and highly generalizable few-shot biomedical image classification. Our approach achieves effective prompt context learning by leveraging semantic consistency with average prompt ensembles from Large Language Models (LLMs) and knowledge distillation with a statistics-based prompt selection strategy. We conducted comprehensive validation of our proposed framework on 11 medical datasets across 9 modalities and 10 organs against existing state-of-the-art methods, demonstrating significant improvements in both accuracy and generalizability. The code is publicly available at https://github.com/HealthX-Lab/BiomedCoOp.

Eric Kee, Adam Pikielny, Kevin Blackburn-Matzen, Marc Levoy

We describe a system to remove real-world reflections from images for consumer photography. Our system operates on linear (RAW) photos, and accepts an optional contextual photo looking in the opposite direction (e.g., the "selfie" camera on a mobile device). This optional photo disambiguates what should be considered the reflection. The system is trained solely on synthetic mixtures of real RAW photos, which we combine using a reflection simulation that is photometrically and geometrically accurate. Our system comprises a base model that accepts the captured photo and optional context photo as input, and runs at 256p, followed by an up-sampling model that transforms 256p images to full resolution. The system produces preview images at 1K in 4.5-6.5s on a MacBook or iPhone 14 Pro. We show SOTA results on RAW photos that were captured in the field to embody typical consumer photos, and show that training on RAW simulation data improves performance more than the architectural variations among prior works.

Yuhong Zhang, Guanlin Wu, Ling-Hao Chen, Zhuokai Zhao, Jing Lin, Xiaoke Jiang, Jiamin Wu, Zhuoheng Li, Hao Frank Yang, Haoqian Wang 等

In this paper, we present a novel framework designed to reconstruct long-sequence 3D human motion in the world coordinates from in-the-wild videos with multiple shot transitions. Such long-sequence in-the-wild motions are highly valuable to applications such as motion generation and motion understanding, but are of great challenge to be recovered due to abrupt shot transitions, partial occlusions, and dynamic backgrounds presented in such videos. Existing methods primarily focus on single-shot videos, where continuity is maintained within a single camera view, or simplify multi-shot alignment in camera space only. In this work, we tackle the challenges by integrating an enhanced camera pose estimation with Human Motion Recovery (HMR) by incorporating a shot transition detector and a robust alignment module for accurate pose and orientation continuity across shots. By leveraging a custom motion integrator, we effectively mitigate the problem of foot sliding and ensure temporal consistency in human pose. Extensive evaluations on our created multi-shot dataset from public 3D human datasets demonstrate the robustness of our method in reconstructing realistic human motion in world coordinates.

Rolandos Alexandros Potamias, Jinglei Zhang, Jiankang Deng, Stefanos Zafeiriou

In recent years, 3D hand pose estimation methods have garnered significant attention due to their extensive applications in human-computer interaction, virtual reality, and robotics. In contrast, there has been a notable gap in hand detection pipelines, posing significant challenges in constructing effective real-world multi-hand reconstruction systems. In this work, we present a data-driven pipeline for efficient multi-hand reconstruction in the wild. The proposed pipeline is composed of two components: a real-time fully convolutional hand localization and a high-fidelity transformer-based 3D hand reconstruction model. To tackle the limitations of previous methods and build a robust and stable detection network, we introduce a large-scale dataset with over than 2M in-the-wild hand images with diverse lighting, illumination, and occlusion conditions. Our approach outperforms previous methods in both efficiency and accuracy on popular 2D and 3D benchmarks. Finally, we showcase the effectiveness of our pipeline to achieve smooth 3D hand tracking from monocular videos, without utilizing any temporal components. Code, models, and dataset are available at https://rolpotamias.github.io/WiLoR

Sotiris Anagnostidis, Gregor Bachmann, Yeongmin Kim, Jonas Kohler, Markos Georgopoulos, Artsiom Sanakoyeu, Yuming Du, Albert Pumarola, Ali Thabet, Edgar Schönfeld

Despite their remarkable performance, modern Diffusion Transformers (DiTs) are hindered by substantial resource requirements during inference, stemming from the fixed and large amount of compute needed for each denoising step. In this work, we revisit the conventional static paradigm that allocates a fixed compute budget per denoising iteration and propose a dynamic strategy instead. Our simple and sample-efficient framework enables pre-trained DiT models to be converted into flexible ones --- dubbed FlexiDiT --- allowing them to process inputs at varying compute budgets. We demonstrate how a single flexible model can generate images without any drop in quality, while reducing the required FLOPs by more than 40% compared to their static counterparts, for both class-conditioned and text-conditioned image generation. Our method is general and agnostic to input and conditioning modalities. We show how our approach can be readily extended for video generation, where FlexiDiT models generate samples with up to 75% less compute without compromising performance.

Yassine Ouali, Adrian Bulat, Alexandros Xenos, Anestis Zaganidis, Ioannis Maniadis Metaxas, Brais Martinez, Georgios Tzimiropoulos

Contrastively-trained Vision-Language Models (VLMs) like CLIP have become the de facto approach for discriminative vision-language representation learning. However, these models have limited language understanding, often exhibiting a "bag of words" behavior. At the same time, Large Vision-Language Models (LVLMs), which combine vision encoders with LLMs, have been shown to be capable of detailed vision-language reasoning, yet their autoregressive nature renders them less suitable for discriminative tasks. In this work, we propose to combine "the best of both worlds": a new training approach for discriminative fine-tuning of LVLMs that results in strong discriminative and compositional capabilities. Essentially, our approach converts a generative LVLM into a discriminative one, unlocking its capability for powerful image-text discrimination combined with enhanced language understanding. Our contributions include (1) A carefully designed training/optimization framework that utilizes image-text pairs of variable length and granularity for training the model with both contrastive and next-token prediction losses. This is accompanied by ablation studies that justify the necessity of our framework's components. (2) A parameter-efficient adaptation method using a combination of soft prompting and LoRA adapters. (3) Significant improvements over state-of-the-art CLIP-like models of similar size, including standard image-text retrieval benchmarks and notable gains in compositionality.

Wei Long, Xingyu Zhou, Leheng Zhang, Shuhang Gu

Transformer-based methods have achieved remarkable results in image super-resolution tasks because they can capture non-local dependencies in low-quality input images. However, this feature-intensive modeling approach is computationally expensive because it calculates the similarities between numerous features that are irrelevant to the query features when obtaining attention weights. These unnecessary similarity calculations not only degrade the reconstruction performance but also introduce significant computational overhead. How to accurately identify the features that are important to the current query features and avoid similarity calculations between irrelevant features remains an urgent problem. To address this issue, we propose a novel and effective Progressive Focused Transformer (PFT) that links all isolated attention maps in the network through Progressive Focused Attention (PFA) to focus attention on the most important tokens. PFA not only enables the network to capture more critical similar features, but also significantly reduces the computational cost of the overall network by filtering out irrelevant features before calculating similarities. Extensive experiments demonstrate the effectiveness of the proposed method, achieving state-of-the-art performance on various single image super-resolution benchmarks.

SeonHwa Kim, Jiwon Kim, Soobin Park, Donghoon Ahn, Jiwon Kang, Seungryong Kim, Kyong Hwan Jin, Eunju Cha

Score distillation sampling (SDS) demonstrates a powerful capability for text-conditioned 2D image and 3D object generation by distilling the knowledge from learned score functions. However, SDS often suffers from blurriness caused by noisy gradients. When SDS meets the image editing, such degradations can be reduced by adjusting bias shifts using reference pairs, but the de-biasing techniques are still corrupted by erroneous gradients. To this end, we introduce Identity-preserving Distillation Sampling (IDS), which compensates for the gradient leading to undesired changes in the results. Based on the analysis that these errors come from the text-conditioned scores, a new regularization technique, called fixed-point iterative regularization (FPR), is proposed to modify the score itself, driving the preservation of the identity even including poses and structures. Thanks to a self-correction by FPR, the proposed method provides clear and unambiguous representations corresponding to the given prompts in image-to-image editing and editable neural radiance field (NeRF). The structural consistency between the source and the edited data is obviously maintained compared to other state-of-the-art methods.

Joya Chen, Ziyun Zeng, Yiqi Lin, Wei Li, Zejun Ma, Mike Zheng Shou

Recent video large language models (Video LLMs) often depend on costly human annotations or proprietary APIs (e.g., GPT-4o) to produce training data, which limits their training at scale. In this paper, we explore large-scale training for Video LLM with cheap automatic speech recognition (ASR) transcripts. Specifically, we propose a novel streaming training approach that densely interleaves the ASR words and video frames according to their timestamps. Compared to previous studies in vision-language representation with ASR, our method naturally fits the streaming characteristics of ASR, thus enabling the model to learn temporally-aligned, fine-grained vision-language modeling. To support the training algorithm, we introduce a data pipeline for YouTube videos and their closed captions (CC), resulting in \texttt Live-CC-10M pre-training set and \texttt Live-WhisperX-408K high-quality supervised fine-tuning (SFT) set. Remarkably, even without SFT, the pre-trained model \texttt LiveCC-7B demonstrates significant improvements in general video QA and exhibits a new capability in real-time video commentary. To evaluate this, we carefully design a new benchmark \texttt LiveSports-3K , using LLM-as-a-judge to measure the free-form commentary. Experiments show our final model \texttt LiveCC-7B can surpass LLaVA-Video-72B in commentary quality even working in a real-time mode. Meanwhile, it achieves state-of-the-art results at the 7B scale on popular benchmarks such as VideoMME, demonstrating its broad generalizability. All resources of this paper have been released at \href https://showlab.github.io/livecc showlab.github.io/livecc .

David T. Hoffmann, Syed Haseeb Raza, Hanqiu Jiang, Denis Tananaev, Steffen Klingenhoefer, Martin Meinke

Scene flow estimation is a foundational task for many robotic applications, including robust dynamic object detection, automatic labeling, and sensor synchronization. Two types of approaches to the problem have evolved: 1) Supervised and 2) optimization-based methods. Supervised methods are fast during inference and achieve high-quality results, however, they are limited by the need for large amounts of labeled training data and are susceptible to domain gaps. In contrast, unsupervised test-time optimization methods do not face the problem of domain gaps but usually suffer from substantial runtime, exhibit artifacts, or fail to converge to the right solution. In this work, we mitigate several limitations of existing optimization-based methods. To this end, we 1) introduce a simple voxel grid-based model that improves over the standard MLP-based formulation in multiple dimensions and 2) introduce a new multi-frame loss formulation. 3) We combine both contributions in our new method, termed Floxels. On the Argoverse 2 benchmark, Floxels is surpassed only by EulerFlow among unsupervised methods while achieving comparable performance at a fraction of the computational cost. Floxels achieves a massive speedup of more than 60-140x over EulerFlow, reducing the runtime from a day to 10 minutes per sequence. Over the faster but low-quality baseline, NSFP, Floxels achieves a speedup of 14x.

Kyujin Shim, Kangwook Ko, Yujin Yang, Changick Kim

Multi-object tracking (MOT) is a critical task in computer vision, requiring the accurate identification and continuous tracking of multiple objects across video frames. However, current state-of-the-art methods mainly rely on a global optimization technique and multi-stage cascade association strategy, and those approaches often overlook the specific characteristics of assignment task in MOT and useful detection results that may represent occluded objects. To address these challenges, we propose a novel Track-Focused Online Multi-Object Tracker (TrackTrack) with two key strategies: Track-Perspective-Based Association (TPA) and Track-Aware Initialization (TAI). The TPA strategy associates each track with the most suitable detection result by choosing the one with the minimum distance from all available detection results in a track-perspective manner. On the other hand, TAI precludes the generation of spurious tracks in the track-aware aspect by suppressing track initialization of detection results that heavily overlap with current active tracks and more confident detection results. Extensive experiments on MOT17, MOT20, and DanceTrack demonstrate that our TrackTrack outperforms current state-of-the-art trackers, offering improved robustness and accuracy across diverse and challenging tracking scenarios.

Atharv Mahesh Mane, Dulanga Weerakoon, Vigneshwaran Subbaraju, Sougata Sen, Sanjay E. Sarma, Archan Misra

3-Dimensional Embodied Reference Understanding (3DERU) combines a language description and an accompanying pointing gesture to identify the most relevant target object in a 3D scene. Although prior work has explored pure language-based 3D grounding, there has been limited exploration of 3D-ERU, which also incorporates human pointing gestures. To address this gap, we introduce a data augmentation framework-Imputer, and use it to curate a new benchmark dataset-ImputeRefer for 3D-ERU, by incorporating human pointing gestures into existing 3D scene datasets that only contain language instructions. We also propose Ges3ViG, a novel model for 3D-ERU that achieves 30% improvement in accuracy as compared to other 3DERU models and 9% compared to other purely language-based 3D grounding models. Our code and dataset are available at https://github.com/AtharvMane/Ges3ViG.

Zhonghang Liu, Kun Zhou, Changshuo Wang, Wen-Yan Lin, Jiangbo Lu

How many outliers are within an unlabeled and contaminated dataset? Despite a series of unsupervised outlier detection (UOD) approaches have been proposed, they cannot correctly answer this critical question, resulting in their performance instability across various real-world (varying contamination factor) scenarios. To address this problem, we propose FlexUOD, with a novel contamination factor estimation perspective. FlexUOD not only achieves its remarkable robustness but also is a general and plug-and-play framework, which can significantly improve the performance of existing UOD methods. Extensive experiments demonstrate that FlexUOD achieves state-of-the-art results as well as high efficacy on diverse evaluation benchmarks.

Seil Kang, Jinyeong Kim, Junhyeok Kim, Seong Jae Hwang

Visual grounding seeks to localize the image region corresponding to a free-form text description. Recently, the strong multimodal capabilities of Large Vision-Language Models (LVLMs) have driven substantial improvements in visual grounding, though they inevitably require fine-tuning and additional model components to explicitly generate bounding boxes or segmentation masks. However, we discover that a few attention heads in frozen LVLMs demonstrate strong visual grounding capabilities. We refer to these heads, which consistently capture object locations related to text semantics, as localization heads. Using localization heads, we introduce a straightforward and effective training-free visual grounding framework that utilizes text-to-image attention maps from localization heads to identify the target objects. Surprisingly, only three out of thousands of attention heads are sufficient to achieve competitive localization performance compared to existing LVLM-based visual grounding methods that require fine-tuning. Our findings suggest that LVLMs can innately ground objects based on a deep comprehension of the text-image relationship, as they implicitly focus on relevant image regions to generate informative text outputs.

Sheng-Yu Huang, Zi-Ting Chou, Yu-Chiang Frank Wang

When performing 3D inpainting using novel-view rendering methods like Neural Radiance Field (NeRF) or 3D Gussian Splatting (3DGS), how to achieve texture and geometry consistency across camera views has been a challenge. In this paper, we propose a framework of 3D Gaussian Inpainting with Depth-Guided Cross-View Consistency (3DGIC) for cross-view consistent 3D inpainting. Guided by the rendered depth information from each training view, our 3DGIC exploits background pixels visible across different views for updating the inpainting mask, allowing us to refine the 3DGS for inpainting purposes. Through extensive experiments on benchmark datasets, we confirm that our 3DGIC outperforms current state-of-the-art 3D inpainting methods quantitatively and qualitatively.