论文检索

Jeongwan On, Kyeonghwan Gwak, Gunyoung Kang, Junuk Cha, Soohyun Hwang, Hyein Hwang, Seungryul Baek

Reconstructing 3Ds of hand-object interaction (HOI) is a fundamental problem that can find numerous applications. Despite recent advances, there is no comprehensive pipeline yet for bimanual class-agnostic interaction reconstruction from a monocular RGB video, where two hands and an unknown object are interacting with each other. Previous works tackled the limited hand-object interaction case, where object templates are pre-known or only one hand is involved in the interaction. The bimanual interaction reconstruction exhibits severe occlusions introduced by complex interactions between two hands and an object. To solve this, we first introduce BIGS (Bimanual Interaction 3D Gaussian Splatting), a method that reconstructs 3D Gaussians of hands and an unknown object from a monocular video. To robustly obtain object Gaussians avoiding severe occlusions, we leverage prior knowledge of pre-trained diffusion model with score distillation sampling (SDS) loss, to reconstruct unseen object parts. For hand Gaussians, we exploit the 3D priors of hand model (i.e., MANO) and share a single Gaussian for two hands to effectively accumulate hand 3D information, given limited views. To further consider the 3D alignment between hands and objects, we include the interacting-subjects optimization step during Gaussian optimization. Our method achieves the state-of-the-art accuracy on two challenging datasets, in terms of 3D hand pose estimation (MPJPE), 3D object reconstruction (CDh, CDo, F10), and rendering quality (PSNR, SSIM, LPIPS), respectively.

Yanhao Wu, Haoyang Zhang, Tianwei Lin, Lichao Huang, Shujie Luo, Rui Wu, Congpei Qiu, Wei Ke, Tong Zhang

Generative models in Autonomous Driving (AD) enable diverse scenario creation, yet existing methods fall short by only capturing a limited range of modalities, restricting the capability of generating controllable scenes for comprehensive evaluation of AD systems. In this paper, we introduce a multimodal generation framework that incorporates four major data modalities, including a novel addition of the map modality. With tokenized modalities, our scene sequence generation framework autoregressively predicts each scene while managing computational demands through a two-stage approach. The Temporal AutoRegressive (TAR) component captures inter-frame dynamics for each modality, while the Ordered AutoRegressive (OAR) component aligns modalities within each scene by sequentially predicting tokens in a fixed order. To maintain coherence between map and ego-action modalities, we introduce the Action-aware Map Alignment (AMA) module, which applies a transformation based on the ego-action to maintain coherence between these two modalities. Our framework effectively generates complex, realistic driving scenes over extended sequences, ensuring multimodal consistency and offering fine-grained control over scene elements. Project page: https://yanhaowu.github.io/UMGen/

Jiangyong Huang, Baoxiong Jia, Yan Wang, Ziyu Zhu, Xiongkun Linghu, Qing Li, Song-Chun Zhu, Siyuan Huang

Existing 3D vision-language (3D-VL) benchmarks fall short in evaluating 3D-VL models, creating a "mist" that obscures rigorous insights into model capabilities and 3D-VL tasks. This mist persists due to three key limitations. First, flawed test data, like ambiguous referential text in the grounding task, can yield incorrect and unreliable test results. Second, oversimplified metrics such as simply averaging accuracy per question answering (QA) pair, cannot reveal true model capability due to their vulnerability to language variations. Third, existing benchmarks isolate the grounding and QA tasks, disregarding the underlying coherence that QA should be based on solid grounding capabilities. To unveil the "mist", we propose Beacon3D, a benchmark for 3D-VL grounding and QA tasks, delivering a perspective shift in the evaluation of 3D-VL understanding. Beacon3D features (i) high-quality test data with precise and natural language, (ii) object-centric evaluation with multiple tests per object to ensure robustness, and (iii) a novel chain-of-analysis paradigm to address language robustness and model performance coherence across grounding and QA. Our evaluation of state-of-the-art 3D-VL models on Beacon3D reveals that (i) object-centric evaluation elicits true model performance and particularly weak generalization in QA; (ii) grounding-QA coherence remains fragile in current 3D-VL models, and (iii) incorporating large language models (LLMs) to 3D-VL models, though as a prevalent practice, hinders grounding capabilities and has yet to elevate QA capabilities. We hope Beacon3D and our comprehensive analysis could benefit the 3D-VL community towards faithful developments.

Sébastien Piérard, Anaïs Halin, Anthony Cioppa, Adrien Deliege, Marc Van Droogenbroeck

Ranking entities such as algorithms, devices, methods, or models based on their performances, while accounting for application-specific preferences, is a challenge. To address this challenge, we establish the foundations of a universal theory for performance-based ranking. First, we introduce a rigorous framework built on top of both the probability and order theories. Our new framework encompasses the elements necessary to (1) manipulate performances as mathematical objects, (2) express which performances are worse than or equivalent to others, (3) model tasks through a variable called satisfaction, (4) consider properties of the evaluation, (5) define scores, and (6) specify application-specific preferences through a variable called importance. On top of this framework, we propose the first axiomatic definition of performance orderings and performance-based rankings. Then, we introduce a universal parametric family of scores, called ranking scores, that can be used to establish rankings satisfying our axioms, while considering application-specific preferences. Finally, we show, in the case of two-class classification, that the family of ranking scores encompasses well-known performance scores, including the accuracy, the true positive rate (recall, sensitivity), the true negative rate (specificity), the positive predictive value (precision), and F1. However, we also show that some other scores commonly used to compare classifiers are unsuitable to derive performance orderings satisfying the axioms.

Dongyoon Yang, Jihu Lee, Yongdai Kim

Robust domain adaptation against adversarial attacks is a critical research area that aims to develop models capable of maintaining consistent performance across diverse and challenging domains. In this paper, we derive a new generalization bound for robust risk on the target domain using a novel divergence measure specifically designed for robust domain adaptation. Building upon this, we propose a new algorithm named TAROT, which is designed to enhance both domain adaptability and robustness. Through extensive experiments, TAROT not only surpasses state-of-the-art methods in accuracy and robustness but also significantly enhances domain generalization and scalability by effectively learning domain-invariant features. In particular, TAROT achieves superior performance on the challenging DomainNet dataset, demonstrating its ability to learn domain-invariant representations that generalize well across different domains, including unseen ones. These results highlight the broader applicability of our approach in real-world domain adaptation scenarios.

Weichen Dai, Hexing Wu, Xiaoyang Weng, Yuxin Zheng, Yuhang Ming, Wanzeng Kong

As a fundamental visual task, optical flow estimation has widespread applications in computer vision. However, it faces significant challenges under adverse lighting conditions, where low texture and noise make accurate optical flow estimation particularly difficult.In this paper, we propose an optical flow method that employs implicit image enhancement through multi-modal synergistic training. To supplement the scene information missing in the original low-quality image, we utilize a high-low frequency feature enhancement network. The enhancement network is implicitly guided by multi-modal data and the specific subsequent tasks, enabling the model to learn multi-modal knowledge that enhances feature information suitable for optical flow estimation during inference. By using RGBD multi-modal data, the proposed method avoids the reliance on the images captured from the same view, a common limitation in traditional image enhancement methods.During training, the encoded features extracted from the enhanced images are synergistically supervised by features from the RGBD fusion as well as by the optical flow task.Experiments conducted on both synthetic and real datasets demonstrate that the proposed method significantly improves performance on public datasets.

Xun Huang, Jinlong Wang, Qiming Xia, Siheng Chen, Bisheng Yang, Xin Li, Cheng Wang, Chenglu Wen

Current Vehicle-to-Everything (V2X) systems have significantly enhanced 3D object detection using LiDAR and camera data. However, they face performance degradation in adverse weather. Weather-robust 4D radar, with Doppler velocity and additional geometric information, offers a promising solution to this challenge. To this end, we present V2X-R, the first simulated V2X dataset incorporating LiDAR, camera, and 4D radar modalities. V2X-R contains 12,079 scenarios with 37,727 frames of LiDAR and 4D radar point clouds, 150,908 images, and 170,859 annotated 3D vehicle bounding boxes. Subsequently, we propose a novel cooperative LiDAR-4D radar fusion pipeline for 3D object detection and implement it with multiple fusion strategies. To achieve weather-robust detection, we additionally propose a Multi-modal Denoising Diffusion (MDD) module in our fusion pipeline. MDD utilizes weather-robust 4D radar feature as a condition to guide the diffusion model in denoising noisy LiDAR features.Experiments show that our LiDAR-4D radar fusion pipeline demonstrates superior performance in the V2X-R dataset. Over and above this, our MDD module further improved the foggy/snowy performance of the basic fusion model by up to 5.73%/6.70% and barely disrupting normal performance. The dataset and code will be publicly available.

Yuting Zhang, Hao Lu, Qingyong Hu, Yin Wang, Kaishen Yuan, Xin Liu, Kaishun Wu

Periodic or quasi-periodic phenomena reveal intrinsic characteristics in various natural processes, such as weather patterns, movement behaviors, traffic flows, and biological signals. Given that these phenomena span multiple modalities, the capabilities of Multimodal Large Language Models (MLLMs) offer promising potential to effectively capture and understand their complex nature. However, current MLLMs struggle with periodic tasks due to limitations in: 1) lack of temporal modelling and 2) conflict between short and long periods. This paper introduces Period-LLM, a multimodal large language model designed to enhance the performance of periodic tasks across various modalities, and constructs a benchmark of various difficulty for evaluating the cross-modal periodic capabilities of large models. Specially, We adopt an "Easy to Hard Generalization" paradigm, starting with relatively simple text-based tasks and progressing to more complex visual and multimodal tasks, ensuring that the model gradually builds robust periodic reasoning capabilities. Additionally, we propose a "Resisting Logical Oblivion" optimization strategy to maintain periodic reasoning abilities during semantic alignment. Extensive experiments demonstrate the superiority of the proposed Period-LLM over existing MLLMs in periodic tasks. The code is available at https://github.com/keke-nice/Period-LLM.

Jona Ballé, Luca Versari, Emilien Dupont, Hyunjik Kim, Matthias Bauer

Inspired by the success of generative image models, recent work on learned image compression increasingly focuses on better probabilistic models of the natural image distribution, leading to excellent image quality. This, however, comes at the expense of a computational complexity that is several orders of magnitude higher than today's commercial codecs, and thus prohibitive for most practical applications. With this paper, we demonstrate that by focusing on modeling visual perception rather than the data distribution, we can achieve a very good trade-off between visual quality and bit rate similar to "generative" compression models such as HiFiC, while requiring less than 1% of the multiply-accumulate operations (MACs) for decompression. We do this by optimizing C3, an overfitted image codec, for Wasserstein Distortion (WD), and evaluating the image reconstructions with a human rater study, showing that WD clearly outperforms LPIPS as an optimization objective. The study also reveals that WD outperforms other perceptual metrics such as LPIPS, DISTS, and MS-SSIM as a predictor of human ratings, remarkably achieving over 94% Pearson correlation with Elo scores.

Long Xing, Qidong Huang, Xiaoyi Dong, Jiajie Lu, Pan Zhang, Yuhang Zang, Yuhang Cao, Conghui He, Jiaqi Wang, Feng Wu 等

In large vision-language models (LVLMs), images serve as inputs that carry a wealth of information. As the idiom "A picture is worth a thousand words" implies, representing a single image in current LVLMs can require hundreds or even thousands of tokens. This results in significant computational costs, which grow quadratically as input image resolution increases, thereby severely impacting the efficiency. Previous approaches have attempted to reduce the number of image tokens either before or within the early layers of LVLMs. However, these strategies inevitably result in the loss of crucial image information. To address this challenge, we conduct an empirical study revealing that all visual tokens are necessary for LVLMs in the shallow layers, and token redundancy progressively increases in the deeper layers.To this end, we propose ViCo, a conical-style visual concentration strategy for LVLMs to boost their efficiency in both training and inference with neglectable performance loss. Specifically, we partition the LVLM into several stages and drop part of the image tokens at the end of each stage with a pre-defined ratio. The dropping is based on a lightweight similarity calculation with a negligible time overhead. Extensive experiments demonstrate that ViCo can achieve over 40% training time reduction and 55% inference FLOPs acceleration on leading LVLMs like LLaVA-NeXT, maintaining comparable multi-modal performance. Besides, ViCo can also serve as a plug-and-play strategy to accelerate inference in a free way, with better performance and lower inference cost than counterparts.

Khanh Nguyen, Ghulam Mubashar Hassan, Ajmal Mian

Recent open-world representation learning approaches have leveraged CLIP to enable zero-shot 3D object recognition. However, performance on real point clouds with occlusions still falls short due to unrealistic pretraining settings. Additionally, these methods incur high inference costs because they rely on Transformer's attention modules. In this paper, we make two contributions to address these limitations. First, we propose occlusion-aware text-image-point cloud pretraining to reduce the training-testing domain gap. From 52K synthetic 3D objects, our framework generates nearly 630K partial point clouds for pretraining, consistently improving real-world recognition performances of existing popular 3D networks. Second, to reduce computational requirements, we introduce DuoMamba, a two-stream linear state space model tailored for point clouds. By integrating two space-filling curves with 1D convolutions, DuoMamba effectively models spatial dependencies between point tokens, offering a powerful alternative to Transformer. When pretrained with our framework, DuoMamba surpasses current state-of-the-art methods while reducing latency and FLOPs, highlighting the potential of our approach for real-world applications. Our code and data are available at ndkhanh360.github.io/project_occtip.

Zhenglin Zhou, Fan Ma, Hehe Fan, Tat-Seng Chua

Animatable head avatar generation typically requires extensive data for training. To reduce the data requirements, a natural solution is to leverage existing data-free static avatar generation methods, such as pre-trained diffusion models with score distillation sampling (SDS), which align avatars with pseudo ground-truth outputs from the diffusion model. However, directly distilling 4D avatars from video diffusion often leads to over-smooth results due to spatial and temporal inconsistencies in the generated video. To address this issue, we propose Zero-1-to-A, a robust method that synthesizes a spatial and temporal consistency dataset for 4D avatar reconstruction using the video diffusion model. Specifically, Zero-1-to-A iteratively constructs video datasets and optimizes animatable avatars in a progressive manner, ensuring that avatar quality increases smoothly and consistently throughout the learning process. This progressive learning involves two stages: (1) Spatial Consistency Learning fixes expressions and learns from front-to-side views, and (2) Temporal Consistency Learning fixes views and learns from relaxed to exaggerated expressions, generating 4D avatars in a simple-to-complex manner. Extensive experiments demonstrate that Zero-1-to-A improves fidelity, animation quality, and rendering speed compared to existing diffusion-based methods, providing a solution for lifelike avatar creation. Code is publicly available at: https://github.com/ZhenglinZhou/Zero-1-to-A.

Yifan Yu, Shaohui Liu, Rémi Pautrat, Marc Pollefeys, Viktor Larsson

Monocular depth estimation (MDE) models have undergone significant advancements over recent years. Many MDE models aim to predict affine-invariant relative depth from monocular images, while recent developments in large-scale training and vision foundation models enable reasonable estimation of metric (absolute) depth. However, effectively leveraging these predictions for geometric vision tasks, in particular relative pose estimation, remains relatively under explored. While depths provide rich constraints for cross-view image alignment, the intrinsic noise and ambiguity from the monocular depth priors present practical challenges to improving upon classic keypoint-based solutions. In this paper, we develop three solvers for relative pose estimation that explicitly account for independent affine (scale and shift) ambiguities, covering both calibrated and uncalibrated conditions. We further propose a hybrid estimation pipeline that combines our proposed solvers with classic point-based solvers and epipolar constraints. We find that the affine correction modeling is beneficial to not only the relative depth priors but also, surprisingly, the "metric" ones. Results across multiple datasets demonstrate large improvements of our approach over classic keypoint-based baselines and PnP-based solutions, under both calibrated and uncalibrated setups. We also show that our method improves consistently with different feature matchers and MDE models, and can further benefit from very recent advances on both modules.

Zelin Peng, Zhengqin Xu, Zhilin Zeng, Yu Huang, Yaoming Wang, Wei Shen

Open-vocabulary semantic segmentation seeks to label each pixel in an image with arbitrary text descriptions. Vision-language foundation models, especially CLIP, have recently emerged as powerful tools for acquiring open-vocabulary capabilities. However, fine-tuning CLIP to equip it with pixel-level prediction ability often suffers three issues: 1) high computational cost, 2) misalignment between the two inherent modalities of CLIP, and 3) degraded generalization ability on unseen categories. To address these issues, we propose \alg, a symmetrical parameter-efficient fine-tuning (PEFT) strategy conducted in hyperspherical space for both of the two CLIP modalities. Specifically, the PEFT strategy is achieved by a series of efficient block-diagonal learnable transformation matrices and a dual cross-relation communication module among all learnable matrices. Since the PEFT strategy is conducted symmetrically to the two CLIP modalities, the misalignment between them is mitigated. Furthermore, we apply an additional constraint to PEFT on the CLIP text encoder according to the hyperspherical energy principle, i.e., minimizing hyperspherical energy during fine-tuning preserves the intrinsic structure of the original parameter space, to prevent the destruction of the generalization ability offered by the CLIP text encoder. Extensive evaluations across various benchmarks show that H-CLIP achieves new SOTA open-vocabulary semantic segmentation results while only requiring updating approximately 4% of the total parameters of CLIP.

Yufan Wu, Xuanhong Chen, Wen Li, Shunran Jia, Hualiang Wei, Kairui Feng, Jialiang Chen, Yuhan Li, Ang He, Weimin Zhang 等

Despite significant advances in accurately estimating geometry in contemporary single-image 3D human reconstruction, creating a high-quality, efficient, and animatable 3D avatar remains an open challenge. Two key obstacles persist: incomplete observation and inconsistent 3D priors. To address these challenges, we propose SinGS, aiming to achieve high-quality and efficient animatable 3D avatar reconstruction. At the heart of SinGS are two key components: Kinematic Human Diffusion and Geometry-Preserving 3D Gaussain Splatting. The former is a foundational human model that samples within pose space to generate a highly 3D-consistent and high-quality sequence of human images, inferring unseen viewpoints and providing kinematic priors. The latter is a system that reconstructs a compact, high-quality 3D avatar even under imperfect priors, achieved through a novel semantic Laplacian regularization and a geometry-preserving density control strategy that enable precise and compact assembly of 3D primitives. Extensive experiments demonstrate that SinGS enables lifelike, animatable human reconstructions, maintaining both high quality and inference efficiency (up to 70FPS).

Hyeokjun Kweon, Kuk-Jin Yoon

Instance segmentation traditionally relies on dense pixel-level annotations, making it costly and labor-intensive. To alleviate this burden, weakly supervised instance segmentation utilizes cost-effective weak labels, such as image-level tags, points, and bounding boxes. However, existing approaches typically focus on a single type of weak label, overlooking the cost-efficiency potential of combining multiple types. In this paper, we introduce WISH, a novel heterogeneous framework for weakly supervised instance segmentation that integrates diverse weak label types within a single model. WISH unifies heterogeneous labels by leveraging SAM's prompt latent space through a multi-stage matching strategy, effectively compensating for the lack of spatial information in class tags. Extensive experiments on Pascal VOC and COCO demonstrate that our framework not only surpasses existing homogeneous weak supervision methods but also achieves superior results in heterogeneous settings with equivalent annotation costs.

Tobia Poppi, Tejaswi Kasarla, Pascal Mettes, Lorenzo Baraldi, Rita Cucchiara

Addressing the retrieval of unsafe content from vision-language models such as CLIP is an important step towards real-world integration. Current efforts have relied on unlearning techniques that try to erase the model's knowledge of unsafe concepts. While effective in reducing unwanted outputs, unlearning limits the model's capacity to discern between safe and unsafe content. In this work, we introduce a novel approach that shifts from unlearning to an awareness paradigm by leveraging the inherent hierarchical properties of the hyperbolic space. We propose to encode safe and unsafe content as an entailment hierarchy, where both are placed in different regions of hyperbolic space. Our HySAC, Hyperbolic Safety-Aware CLIP, employs entailment loss functions to model the hierarchical and asymmetrical relations between safe and unsafe image-text pairs. This modelling - ineffective in standard vision-language models due to their reliance on Euclidean embeddings - endows the model with awareness of unsafe content, enabling it to serve as both a multimodal unsafe classifier and a flexible content retriever, with the option to dynamically redirect unsafe queries toward safer alternatives or retain the original output. Extensive experiments show that our approach not only enhances safety recognition, but also establishes a more adaptable and interpretable framework for content moderation in vision-language models. Our source code is available at: https://github.com/aimagelab/HySAC

Xinyu Zhao, Jun Xie, Shengzhe Chen, Jun Liu

Multi-center star shape is a prevalent object shape feature, which has proven effective in model-based image segmentation methods. However, the shape field function induced by the multi-center star shape is non-smooth, and directly applying it to the data-driven image segmentation network architecture design may lead to instability in backpropagation. This paper proposes a convex combination star (CCS) shape, possessing multi-center star shape properties, and has the advantage of effectively controlling the shape of the region through a smooth field function. The sufficient condition of the proposed CCS shape can be combined into the image segmentation neural network structure design through the bridge between the variational segmentation model and the activation function of the data-driven method. Taking Segment Anything Model (SAM) and its improved version as backbone networks, we have shown that the segmentation network architecture with CCS shape properties can greatly improve the accuracy of segmentation results.

Xiaohan Zou, Wenchao Ma, Shu Zhao

Recent advancements in prompt-based learning have significantly advanced image and video class-incremental learning. However, the prompts learned by these methods often fail to capture the diverse and informative characteristics of videos, and struggle to generalize effectively to future tasks and classes. To address these challenges, this paper proposes modeling the distribution of space-time prompts conditioned on the input video using a diffusion model. This generative approach allows the proposed model to naturally handle the diverse characteristics of videos, leading to more robust prompt learning and enhanced generalization capabilities. Additionally, we develop a simple yet effective mechanism to transfer the token relationship modeling capabilities of pre-trained image transformers to spatio-temporal modeling in videos. Our approach has been thoroughly evaluated across four established benchmarks, showing remarkable improvements over existing state-of-the-art methods in video class-incremental learning.

Shoufa Chen, Chongjian Ge, Yuqi Zhang, Yida Zhang, Fengda Zhu, Hao Yang, Hongxiang Hao, Hui Wu, Zhichao Lai, Yifei Hu 等

This paper introduces Goku, a state-of-the-art family of joint image-and-video generation models leveraging rectified flow Transformers to achieve industry-leading performance. We detail the foundational elements enabling high-quality visual generation, including the data curation pipeline, model architecture design, flow formulation, and advanced infrastructure for efficient and robust large-scale training. The Goku models demonstrate superior performance in both qualitative and quantitative evaluations, setting new benchmarks across major tasks. Specifically, Goku achieves 0.76 on GenEval and 83.65 on DPG-Bench for text-to-image generation, and 84.85 on VBench for text-to-video tasks. We believe that this work provides valuable insights and practical advancements for the research community in developing joint image-and-video generation models.