Point-based interactive colorization techniques allow users to effortlessly colorize grayscale images using user-provided color hints. However, point-based methods often face challenges when different colors are given to semantically similar areas, leading to color intermingling and unsatisfactory results—an issue we refer to as color collapse. The fundamental cause of color collapse is the inadequacy of points for defining the boundaries for each color. To mitigate color collapse, we introduce a lasso tool that can control the scope of each color hint. Additionally, we design a framework that leverages the user-provided lassos to localize the attention masks. The experimental results show that using a single lasso is as effective as applying 4.18 individual color hints and can achieve the desired outcomes in 30% less time than using points alone.
论文检索
输入标题、作者或关键词，从 11,272 篇学术成果中精准定位
Multi-modal transformers are rapidly gaining attention in video captioning tasks. Existing multi-modal video captioning methods extract a fixed number of frames, but this has critical challenges. If a limited number of frames are extracted, important frames with essential information for caption generation may be missed. Conversely, extracting an excessive number of frames includes consecutive frames, potentially causing redundancy in visual tokens extracted from consecutive video frames. To extract an appropriate number of frames for each video, this paper proposes the first model-agnostic module selection framework in video captioning that has two main functions: (1) selecting a caption generation module with an appropriate size based on visual tokens extracted from video frames, and (2) constructing subsets of visual tokens for the selected caption generation module. Furthermore, we propose a new adaptive attention masking scheme that enhances attention on important visual tokens. Our numerical experiments with three different benchmark datasets demonstrate that the proposed framework significantly improves the performances of three recent video captioning models.
Propagation-based video inpainting using optical flow at the pixel or feature level has recently garnered significant attention. However, it has limitations such as the inaccuracy of optical flow prediction and the propagation of noise over time. These issues result in non-uniform noise and time consistency problems throughout the video, which are particularly pronounced when the removed area is large and involves substantial movement. To address these issues, we propose a novel First Frame Filling Video Diffusion Inpainting model (FFF-VDI). We design FFF-VDI inspired by the capabilities of pre-trained image-to-video diffusion models that can transform the first frame image into a highly natural video. To apply this to the video inpainting task, we propagate the noise latent information of future frames to fill the masked areas of the first frame's noise latent code. Next, we fine-tune the pre-trained image-to-video diffusion model to generate the inpainted video. The proposed model addresses the limitations of existing methods that rely on optical flow quality, producing much more natural and temporally consistent videos. This proposed approach is the first to effectively integrate image-to-video diffusion models into video inpainting tasks. Through various comparative experiments, we demonstrate that the proposed model can robustly handle diverse inpainting types with high quality.
Facial expression recognition (FER) remains a challenging task due to label ambiguity caused by the subjective nature of facial expressions and noisy samples. Additionally, class imbalance, which is common in real-world datasets, further complicates FER. Although many studies have shown impressive improvements, they typically address only one of these issues, leading to suboptimal results. To tackle both challenges simultaneously, we propose a novel framework called Navigating Label Ambiguity (NLA), which is robust under real-world conditions. The motivation behind NLA is that dynamically estimating and emphasizing ambiguous samples at each iteration helps mitigate noise and class imbalance by reducing the model's bias toward majority classes. To achieve this, NLA consists of two main components: Noise-aware Adaptive Weighting (NAW) and consistency regularization. Specifically, NAW adaptively assigns higher importance to ambiguous samples and lower importance to noisy ones, based on the correlation between the intermediate prediction scores for the ground truth and the nearest negative. Moreover, we incorporate a regularization term to ensure consistent latent distributions. Consequently, NLA enables the model to progressively focus on more challenging ambiguous samples, which primarily belong to the minority class, in the later stages of training. Extensive experiments demonstrate that NLA outperforms existing methods in both overall and mean accuracy, confirming its robustness against noise and class imbalance. To the best of our knowledge, this is the first framework to address both problems simultaneously.
Recent research on LiDAR-based 3D object detectors has shown strong performance; however, evaluations typically focus on dominant classes, overlooking rare classes, such as strollers, which could be critical in real autonomous driving scenarios. This oversight is problematic because state-of-the-art 3D object detectors show significantly lower performance on rare classes compared to dominant ones when trained on both. To address this issue and achieve accurate 3D rare object detection using only LiDAR data, we propose the Neighbor-Based confidence Adjustment for 3D rare class predictions (NBA3D). NBA3D utilizes a graph neural network to analyze the surrounding environment of rare class prediction boxes, enabling a more effective distinction between true positives and false positives based on their local context. Our approach utilizes both 3D prediction box characteristics and CLIP-based class semantic information to better contextualize neighboring objects. Various experiments demonstrate that NBA3D effectively improves the detection performance of rare class objects, regardless of the type of 3D object detectors used.
VidChain: Chain-of-Tasks with Metric-based Direct Preference Optimization for Dense Video Captioning
PDF ↗Despite the advancements of Video Large Language Models (VideoLLMs) in various tasks, they struggle with fine-grained temporal understanding, such as Dense Video Captioning (DVC). DVC is a complicated task of describing all events within a video while also temporally localizing them, which integrates multiple fine-grained tasks, including video segmentation, video captioning, and temporal video grounding. Previous VideoLLMs attempt to solve DVC in a single step, failing to utilize their reasoning capability. Moreover, previous training objectives for VideoLLMs do not fully reflect the evaluation metrics, therefore not providing supervision directly aligned to target tasks. To address such a problem, we propose a novel framework named VidChain comprised of Chain-of-Tasks (CoTasks) and Metric-based Direct Preference Optimization (M-DPO). CoTasks decompose a complex task into a sequence of sub-tasks, allowing VideoLLMs to leverage their reasoning capabilities more effectively. M-DPO aligns a VideoLLM with evaluation metrics, providing fine-grained supervision to each task that is well-aligned with metrics. Applied to two different VideoLLMs, VidChain consistently improves their fine-grained video understanding, thereby outperforming previous VideoLLMs on two different DVC benchmarks and also on the temporal video grounding task.
Understanding the 3D semantics of a scene is a fundamental problem for various scenarios such as embodied agents. While NeRFs and 3DGS excel at novel-view synthesis, previous methods for understanding their semantics have been limited to incomplete 3D understanding: their segmentation results are rendered as 2D masks that do not represent the entire 3D space. To address this limitation, we redefine the problem to segment the 3D volume and propose the following methods for better 3D understanding. We directly supervise the 3D points to train the language embedding field, unlike previous methods that anchor supervision at 2D pixels. We transfer the learned language field to 3DGS, achieving the first real-time rendering speed without sacrificing training time or accuracy. Lastly, we introduce a 3D querying and evaluation protocol for assessing the reconstructed geometry and semantics together. Code, checkpoints, and annotations are available at the project page.
Although existing Sparsely Annotated Object Detection (SAOD) approches have made progress in handling sparsely annotated environments in multispectral domain, where only some pedestrians are annotated, they still have the following limitations: (i) they lack considerations for improving the quality of pseudo-labels for missing annotations, and (ii) they rely on fixed ground truth annotations, which leads to learning only a limited range of pedestrian visual appearances in the multispectral domain. To address these issues, we propose a novel framework called Sparsely Annotated Multispectral Pedestrian Detection (SAMPD). For limitation (i), we introduce Multispectral Pedestrian-aware Adaptive Weight (MPAW) and Positive Pseudo-label Enhancement (PPE) module. Utilizing multispectral knowledge, these modules ensure the generation of high-quality pseudo-labels and enable effective learning by increasing weights for high-quality pseudo-labels based on modality characteristics. To address limitation (ii), we propose an Adaptive Pedestrian Retrieval Augmentation (APRA) module, which adaptively incorporates pedestrian patches from ground-truth and dynamically integrates high-quality pseudo-labels with the ground-truth, facilitating a more diverse learning pool of pedestrians. Extensive experimental results demonstrate that our SAMPD significantly enhances performance in sparsely annotated environments within the multispectral domain.
Existing Large Vision-Language Models (LVLMs) excel at matching concepts across multi-modal inputs but struggle with compositional concepts and high-level relationships between entities. This paper introduces Progressive multi-granular Vision-Language alignments (PromViL), a novel framework to enhance LVLMs' ability in performing grounded compositional visual reasoning tasks. Our approach constructs a hierarchical structure of multi-modal alignments, ranging from simple to complex concepts. By progressively aligning textual descriptions with corresponding visual regions, our model learns to leverage contextual information from lower levels to inform higher-level reasoning. To facilitate this learning process, we introduce a data generation process that creates a novel dataset derived from Visual Genome, providing a wide range of nested compositional vision-language pairs. Experimental results demonstrate that our PromViL framework significantly outperforms baselines on various visual grounding and compositional question answering tasks.
In this work, we introduce Modulated Flows (ModFlows), a novel approach for color transfer between images based on rectified flows. The primary goal of the color transfer is to adjust the colors of a target image to match the color distribution of a reference image. Our technique is based on optimal transport and executes color transfer as an invertible transformation within the RGB color space. The ModFlows utilizes the bijective property of flows, enabling us to introduce a common intermediate color distribution and build a dataset of rectified flows. We train an encoder on this dataset to predict the weights of a rectified model for new images. After training on a set of optimal transport plans, our approach can generate plans for new pairs of distributions without additional fine-tuning. We additionally show that the trained encoder provides an image embedding, associated only with its color style. The presented method is capable of processing 4K images and achieves the state-of-the-art performance in terms of content and style similarity.
Unpaired training has been verified as one of the most effective paradigms for real scene dehazing by learning from unpaired real-world hazy and clear images. Although numerous studies have been proposed, current methods demonstrate limited generalization for various real scenes due to limited feature representation and insufficient use of real-world prior. Inspired by the strong generative capabilities of diffusion models in producing both hazy and clear images, we exploit diffusion prior for real-world image dehazing, and propose an unpaired framework named Diff-Dehazer. Specifically, we leverage diffusion prior as bijective mapping learners within the CycleGAN, a classic unpaired learning framework. Considering that physical priors contain pivotal statistics information of real-world data, we further excavate real-world knowledge by integrating physical priors into our framework. Furthermore, we introduce a new perspective for adequately leveraging the representation ability of diffusion models by removing degradation in image and text modalities, so as to improve the dehazing effect. Extensive experiments on multiple real-world datasets demonstrate the superior performance of our method.
Mind the Uncertainty in Human Disagreement: Evaluating Discrepancies Between Model Predictions and Human Responses in VQA
PDF ↗Large vision-language models struggle to accurately predict responses provided by multiple human annotators, particularly when those responses exhibit high uncertainty. In this study, we focus on a Visual Question Answering (VQA) task and comprehensively evaluate how well the output of the state-of-the-art vision-language model correlates with the distribution of human responses. To do so, we categorize our samples based on their levels (low, medium, high) of human uncertainty in disagreement (HUD) and employ, not only accuracy, but also three new human-correlated metrics for the first time in VQA, to investigate the impact of HUD. We also verify the effect of common calibration and human calibration (Baan et al. 2022) on the alignment of models and humans. Our results show that even BEiT3, currently the best model for this task, struggles to capture the multi-label distribution inherent in diverse human responses. Additionally, we observe that the commonly used accuracy-oriented calibration technique adversely affects BEiT3’s ability to capture HUD, further widening the gap between model predictions and human distributions. In contrast, we show the benefits of calibrating models towards human distributions for VQA, to better align model confidence with human uncertainty. Our findings highlight that for VQA, the alignment between human responses and model predictions is understudied and is an important target for future studies.
Most techniques approach the problem of image forgery localization as a binary segmentation task, training neural networks to label original areas as 0 and forged areas as 1. In contrast, we tackle this issue from a more fundamental perspective by partitioning images according to their originating sources. To this end, we propose Segment Any Forged Image Region (SAFIRE), which solves forgery localization using point prompting. Each point on an image is used to segment the source region containing itself. This allows us to partition images into multiple source regions, a capability achieved for the first time. Additionally, rather than memorizing certain forgery traces, SAFIRE naturally focuses on uniform characteristics within each source region. This approach leads to more stable and effective learning, achieving superior performance in both the new task and the traditional binary forgery localization.
Medical image segmentation often faces the dual challenges of limited annotations and domain shifts, further complicated by degraded images in practical scenarios. Traditional methods tend to underperform when these issues occur simultaneously, as they are typically designed for specific tasks. To address this, we propose a unified framework that effectively handles limited annotations and domain shifts while also managing both clean and degraded images during inference. Overcoming these challenges requires focusing on three critical aspects: First, the model must be robust to various noise conditions. Second, it should excel at capturing domain-invariant features. Third, it should effectively utilize unlabeled data. We propose three major components in our approach to tackle these challenges. First, the Wavelet-based Cross-Component Exchange (WCCE) swaps high-frequency wavelet components between labeled and unlabeled images to enhance robustness. Second, we employ a diffusion VNet architecture with a reweighting mechanism to capture domain-invariant features. Finally, we utilize Cross-Decoder Pseudo (CDP) training to effectively leverage unlabeled data. Evaluations on three publicly available medical datasets and across four types of degraded image scenarios demonstrate that our method outperforms state-of-the-art (SOTA) techniques, consistently delivering superior performance across varying image qualities. Our approach not only addresses annotation scarcity and domain shift but also effectively manages noisy and blurred conditions, setting a new benchmark in medical image segmentation.
In this work, we focus on semi-supervised learning for video action detection. Video action detection requires spatio-temporal localization in addition to classification, and a limited amount of labels makes the model prone to unreliable predictions. We present Stable Mean Teacher, a simple end-to-end student-teacher-based framework that benefits from improved and temporally consistent pseudo labels. It relies on a novel ErrOr Recovery (EoR) module, which learns from students' mistakes on labeled samples and transfers this to the teacher to improve pseudo labels for unlabeled samples. Moreover, existing spatio-temporal losses do not take temporal coherency into account and are prone to temporal inconsistencies. To overcome this, we present Difference of Pixels (DoP), a simple and novel constraint focused on temporal consistency, which leads to coherent temporal detections. We evaluate our approach on four different spatio-temporal detection benchmarks: UCF101-24, JHMDB21, AVA, and Youtube-VOS. Our approach outperforms the supervised baselines for action detection by an average margin of 23.5% on UCF101-24, 16% on JHMDB21, and 3.3% on AVA. Using merely 10% and 20% of data, it provides a competitive performance compared to the supervised baseline trained on 100% annotations on UCF101-24 and JHMDB21 respectively. We further evaluate its effectiveness on AVA for scaling to large-scale datasets and Youtube-VOS for video object segmentation, demonstrating its generalization capability to other tasks in the video domain.
While visual question-answering (VQA) benchmarks have catalyzed the development of reasoning techniques, they have focused on vertical thinking. Effective problem-solving also necessitates lateral thinking, which remains understudied in AI and has not been used to test visual perception systems. To bridge this gap, we formulate visual lateral thinking as a multiple-choice question-answering task and describe a three-step taxonomy-driven methodology for instantiating task examples. Then, we develop COLUMBUS, a synthetic benchmark that applies the task pipeline to create QA sets with text and icon rebus puzzles based on publicly available collections of compounds and common phrases. COLUMBUS comprises over 1,000 puzzles, each with four answer candidates. While the SotA vision language models (VLMs) achieve decent performance, our evaluation demonstrates a substantial gap between humans and models. VLMs benefit from human-curated descriptions but struggle to self-generate such representations at the right level of abstraction.
Similar to Language or Image LLMs, VideoLLMs are also plagued by hallucination issues. Hallucinations in videos not only manifest in the spatial dimension regarding the perception of the existence of visual objects (static) but also the temporal dimension influencing the perception of actions and events (dynamic). This paper introduces the concept of Motion Hallucination for the first time, exploring the hallucination phenomena caused by insufficient motion perception capabilities in VideoLMMs, as well as how to detect, evaluate, and mitigate the hallucination. To this end, we propose the first benchmark for assessing motion hallucination MHBench, which consists of 1,200 videos of 20 different action categories. By constructing a collection of adversarial triplet types of videos (original/antonym/incomplete), we achieve a comprehensive evaluation of motion hallucination. Furthermore, we present a Motion Contrastive Decoding (MotionCD) method, which employs bidirectional motion elimination between the original video and its reverse playback to construct an amateur model that removes the influence of motion while preserving visual information, thereby effectively suppressing motion hallucination. Extensive experiments on MHBench reveal that current state-of-the-art VideoLLMs significantly suffer from motion hallucination, while the introduction of MotionCD can effectively mitigate this issue, achieving up to a 15.1% performance improvement. We hope this work will guide future efforts in avoiding and mitigating hallucinations in VideoLLMs.
Real-time Monte Carlo (MC) ray tracing with low sampling rates demands a denoising algorithm that adeptly balances the trade-off between quality and efficiency. Previous works have paid much attention on designing delicate denoising architecture while ignoring model compression. In this work, we present a render-aware knowledge distillation (RAKD) framework, specifically designed for Monte Carlo denoising. We meticulously delineate the Knowledge Distillation (KD) process within RAKD, emphasizing three pivotal techniques: the strategic incorporation of an auxiliary unlabeled dataset, the integration of adversarial learning through generative adversarial network (GAN), and the application of parameter transfer for robust model initialization. These approaches are harmoniously combined to distill knowledge effectively, enabling our student model to adeptly strike a balance between preserving high-frequency details and reducing low-frequency noise. Finally, our results demonstrate that RAKD achieves state-of-the-art quality while upholding real-time performance, successfully tackling the computational constraints faced by resource-limited devices.
While 3D head reconstruction is widely used for modeling, existing neural reconstruction approaches rely on high-resolution multi-view images, posing notable privacy issues. Individuals are particularly sensitive to facial features, and facial image leakage can lead to many malicious activities, such as unauthorized tracking and deepfake. In contrast, geometric data is less susceptible to misuse due to its complex processing requirements, and absence of facial texture features. In this paper, we propose a novel two-stage 3D facial reconstruction method aimed at avoiding exposure to sensitive facial information while preserving detailed geometric accuracy. Our approach first uses non-sensitive rear-head images for initial geometry and then refines this geometry using processed privacy-removed gradient images. Extensive experiments show that the resulting geometry is comparable to methods using full images, while the process is resistant to DeepFake applications and facial recognition (FR) systems, thereby proving its effectiveness in privacy protection.
Efficient Gaussian Splatting for Monocular Dynamic Scene Rendering via Sparse Time-Variant Attribute Modeling
PDF ↗Rendering dynamic scenes from monocular videos is a crucial yet challenging task. The recent deformable Gaussian Splatting has emerged as a robust solution to represent real-world dynamic scenes. However, it often leads to heavily redundant Gaussians, attempting to fit every training view at various time steps, leading to slower rendering speeds. Additionally, the attributes of Gaussians in static areas are time-invariant, making it unnecessary to model every Gaussian, which can cause jittering in static regions. In practice, the primary bottleneck in rendering speed for dynamic scenes is the number of Gaussians. In response, we introduce Efficient Dynamic Gaussian Splatting (EDGS), which represents dynamic scenes via sparse time-variant attribute modeling. Our approach formulates dynamic scenes using a sparse anchor-grid representation, with the motion flow of dense Gaussians calculated via a classical kernel representation. Furthermore, we propose an unsupervised strategy to efficiently filter out anchors corresponding to static areas. Only anchors associated with deformable objects are input into MLPs to query time-variant attributes. Experiments on two real-world datasets demonstrate that our EDGS significantly improves the rendering speed with superior rendering quality compared to previous state-of-the-art methods.