arXiv subjects

Takayuki Okatani

Publications and source records attributed to Takayuki Okatani.

At least 19 recordsLinked to original sources

arXiv2026

Cascaded Multi-Scale Attention for Enhanced Multi-Scale Feature Extraction and Interaction with Low-Resolution Images

In real-world applications of image recognition tasks, such as human pose estimation, cameras often capture objects, like human bodies, at low resolutions. This scenario poses a challenge in extracting and leveraging multi-scale features, which is often essential for precise inference. To address this challenge, we propose a new attention mechanism, named cascaded multi-scale attention (CMSA), tailored for use in CNN-ViT hybrid architectures, to handle low-resolution inputs effectively. The design of CMSA enables the extraction and seamless integration of features across various scales without necessitating the downsampling of the input image or feature maps. This is achieved through a novel combination of grouped multi-head self-attention mechanisms with window-based local attention and cascaded fusion of multi-scale features over different scales. This architecture allows for the effective handling of features across different scales, enhancing the model's ability to perform tasks such as human pose estimation, head pose estimation, and more with low-resolution images. Our experimental results show that the proposed method outperforms existing state-of-the-art methods in these areas with fewer parameters, showcasing its potential for broad application in real-world scenarios where capturing high-resolution images is not feasible. Code is available at https://github.com/xyongLu/CMSA.

cs.CV↗

arXiv2026

Medical-Checklist: Assessing the Comprehension of Medical Images by Multimodal Models

This paper introduces a new benchmark test, Medical-Checklist, for assessing medical multimodal models. The recent advancements in multimodal models have demonstrated significant potential in the field of medical vision-language tasks. However, it is becoming increasingly clear that evaluating these models' performance, whether they are applied to natural or medical images, is challenging. The critical question is whether the models can accurately understand an input image while associating it with relevant input text. To address this, Medical-Checklist imposes a binary test on the models: they are given an image and two captions, where one is correct and the other incorrect, and the model must select the correct one. The incorrect caption contains a single medical concept (word or phrase) that is inaccurately substituted from the correct caption. Although the task is simple, this simplicity enables the unified assessment of diverse multimodal models designed and learned on different principles. It also enables us to verify whether models correctly understand a wide range of medical concepts across various medical sub-domains. Medical-Checklist is designed to reduce potential biases in data and to enable evaluation of the models' ability to handle out-of-distribution inputs, which were difficult in existing datasets. When evaluating four state-of-the-art medical multimodal models with Medical-Checklist, it was revealed that despite their excellent performance in specific tasks such as Med-VQA, they may not correctly understand images, suggesting a long journey ahead for clinical application. The dataset and code will be made public upon acceptance.

cs.CV↗

arXiv2026

When Does High-CFG Diffusion Inversion Fail? A Controlled Study of Prompt--Latent Interactions

Text-guided diffusion inversion is central to image editing, where an image is mapped to an initial latent and then edited by replaying the denoising process under a modified prompt. In practice, however, inversion is often performed with a lower classifier-free guidance(CFG) scale than the one used for generation or editing. This mismatch is empirically useful but leaves a basic question unresolved: when a target image is generated by a high-CFG trajectory, when can that trajectory actually be inverted? We study this question in a controlled generation--inversion--reconstruction setting, where the true initial latent and denoising trajectory are known. Using prompts taken from an existing diffusion-editing benchmark, we generate images under high CFG and reconstruct them with fixed-point inversion using the same prompt and guidance setting. The results reveal three types of prompt-level reconstruction behavior: easy prompts that reconstruct for most initial latents, hard prompts that fail for most initial latents, and intermediate prompts whose success depends on the prompt--latent pairing. To analyze the generation side, we define prompt pressure, a step-wise measure of how strongly CFG moves the denoising update away from the unconditional trajectory. Total pressure correlates with reconstruction quality and separates easy from hard prompts, but it does not explain the success or failure of intermediate prompt--latent pairs. Text-side analyses further show that the main visual subject and wording can change inversion difficulty. Finally, we evaluate a compact trajectory-consistency intervention that relaxes guidance only at locally unstable inverse steps. This diagnostic check improves reconstruction and Prompt-to-Prompt editing in our controlled setting, supporting the view that high-CFG inversion failure requires local, trajectory-aware analysis.

cs.CV↗

arXiv2026

An Improved Method for Personalizing Diffusion Models

Diffusion models have demonstrated impressive image generation capabilities. Personalized approaches, such as textual inversion and Dreambooth, enhance model individualization using specific images. These methods enable generating images of specific objects based on diverse textual contexts. Our proposed approach aims to retain the model's original knowledge during new information integration, resulting in superior outcomes while necessitating less training time compared to Dreambooth and textual inversion.

cs.CV↗

arXiv2026

Inverting the Generation Process of Denoising Diffusion Implicit Models: Empirical Evaluation and a Novel Method

This paper studies the problem of inverting the DDIM image generation process to recover latent variables, particularly the initial noise map, from a generated image. Existing methods often struggle with accuracy in this task. We propose a novel hybrid approach that combines direct inversion via gradient descent for the first step, followed by a fixed-point method for subsequent steps. Empirical evaluations across three datasets demonstrate that our method significantly improves the prediction of initial latent variables while achieving superior reconstruction accuracy. Additionally, we introduce a new evaluation, called the self-interpolation test, which assesses the quality of images generated from interpolated points between the true and predicted latent maps, offering deeper insights into performance. Our results reveal that while existing methods perform reasonably well in reconstruction, they consistently fail to accurately predict the initial latent variables, resulting in poor performance on the self-interpolation test. In contrast, our method outperforms all others across all metrics, providing valuable insights into diffusion models and enhancing their applications in image generation and editing.

cs.CV↗

arXiv2026

360° Image Perception with MLLMs: A Comprehensive Benchmark and a Training-Free Method

Multimodal Large Language Models (MLLMs) have shown impressive abilities in understanding and reasoning over conventional images. However, their perception of 360° images remains largely underexplored. Unlike conventional images, 360° images capture the entire surrounding environment, enabling holistic spatial reasoning but introducing challenges such as geometric distortion and complex spatial relations. To comprehensively assess MLLMs' capabilities to perceive 360° images, we introduce 360Bench, a Visual Question Answering (VQA) benchmark featuring 7K-resolution 360° images, seven representative (sub)tasks with annotations carefully curated by human annotators. Using 360Bench, we systematically evaluate seven MLLMs and six enhancement methods, revealing their shortcomings in 360° image perception. To address these challenges, we propose Free360, a training-free scene-graph-based framework for high-resolution 360° VQA. Free360 decomposes the reasoning process into modular steps, applies adaptive spherical image transformations to 360° images tailored to each step, and seamlessly integrates the resulting information into a unified graph representation for answer generation. Experiments show that Free360 consistently improves its base MLLM and provides a strong training-free solution for 360° VQA tasks. The source code and dataset will be publicly released upon acceptance.

cs.CV↗

arXiv2026

CoReTab: Improving Multimodal Table Understanding with Code-driven Reasoning

Existing datasets for multimodal table understanding, such as MMTab, primarily provide short factual answers without explicit multi-step reasoning supervision. Models trained on these datasets often generate brief responses that offers insufficient accuracy and limited interpretability into how these models arrive at the final answer. We introduce CoReTab, a code-driven reasoning framework that produces scalable, interpretable, and automatically verifiable annotations by coupling multi-step reasoning with executable Python code. Using the CoReTab framework, we curate a dataset of 115K verified samples averaging 529 tokens per response and fine-tune open-source MLLMs through a three-stage pipeline. We evaluate the resulting model trained on CoReTab across 17 MMTab benchmarks spanning table question answering, fact verification, and table structure understanding. Our model achieves significant gains of +6.2%, +5.7%, and +25.6%, respectively, over MMTab-trained baselines, while producing transparent and verifiable reasoning traces. These results establish CoReTab as a robust and generalizable supervision framework for improving multi-step reasoning in multimodal table understanding.

cs.AI↗

arXiv2026

LAMS-Edit: Latent and Attention Mixing with Schedulers for Improved Content Preservation in Diffusion-Based Image and Style Editing

Text-to-Image editing using diffusion models faces challenges in balancing content preservation with edit application and handling real-image editing. To address these, we propose LAMS-Edit, leveraging intermediate states from the inversion process--an essential step in real-image editing--during edited image generation. Specifically, latent representations and attention maps from both processes are combined at each step using weighted interpolation, controlled by a scheduler. This technique, Latent and Attention Mixing with Schedulers (LAMS), integrates with Prompt-to-Prompt (P2P) to form LAMS-Edit--an extensible framework that supports precise editing with region masks and enables style transfer via LoRA. Extensive experiments demonstrate that LAMS-Edit effectively balances content preservation and edit application.

cs.CV↗

arXiv2025

Rethinking Open-Set Object Detection: Issues, a New Formulation, and Taxonomy

Open-set object detection (OSOD), a task involving the detection of unknown objects while accurately detecting known objects, has recently gained attention. However, we identify a fundamental issue with the problem formulation employed in current OSOD studies. Inherent to object detection is knowing "what to detect," which contradicts the idea of identifying "unknown" objects. This sets OSOD apart from open-set recognition (OSR). This contradiction complicates a proper evaluation of methods' performance, a fact that previous studies have overlooked. Next, we propose a novel formulation wherein detectors are required to detect both known and unknown classes within specified super-classes of object classes. This new formulation is free from the aforementioned issues and has practical applications. Finally, we design benchmark tests utilizing existing datasets and report the experimental evaluation of existing OSOD methods. The results show that existing methods fail to accurately detect unknown objects due to misclassification of known and unknown classes rather than incorrect bounding box prediction. As a byproduct, we introduce a taxonomy of OSOD, resolving confusion prevalent in the literature. We anticipate that our study will encourage the research community to reconsider OSOD and facilitate progress in the right direction.

cs.CV↗

arXiv2025

MS-DPPs: Multi-Source Determinantal Point Processes for Contextual Diversity Refinement of Composite Attributes in Text to Image Retrieval

Result diversification (RD) is a crucial technique in Text-to-Image Retrieval for enhancing the efficiency of a practical application. Conventional methods focus solely on increasing the diversity metric of image appearances. However, the diversity metric and its desired value vary depending on the application, which limits the applications of RD. This paper proposes a novel task called CDR-CA (Contextual Diversity Refinement of Composite Attributes). CDR-CA aims to refine the diversities of multiple attributes, according to the application's context. To address this task, we propose Multi-Source DPPs, a simple yet strong baseline that extends the Determinantal Point Process (DPP) to multi-sources. We model MS-DPP as a single DPP model with a unified similarity matrix based on a manifold representation. We also introduce Tangent Normalization to reflect contexts. Extensive experiments demonstrate the effectiveness of the proposed method. Our code is publicly available at https://github.com/NEC-N-SOGI/msdpp.

cs.CV↗

arXiv2025

RefVSR++: Exploiting Reference Inputs for Reference-based Video Super-resolution

Smartphones with multi-camera systems, featuring cameras with varying field-of-views (FoVs), are increasingly common. This variation in FoVs results in content differences across videos, paving the way for an innovative approach to video super-resolution (VSR). This method enhances the VSR performance of lower resolution (LR) videos by leveraging higher resolution reference (Ref) videos. Previous works, which operate on this principle, generally expand on traditional VSR models by combining LR and Ref inputs over time into a unified stream. However, we can expect that better results are obtained by independently aggregating these Ref image sequences temporally. Therefore, we introduce an improved method, RefVSR++, which performs the parallel aggregation of LR and Ref images in the temporal direction, aiming to optimize the use of the available data. RefVSR++ also incorporates improved mechanisms for aligning image features over time, crucial for effective VSR. Our experiments demonstrate that RefVSR++ outperforms previous works by over 1dB in PSNR, setting a new benchmark in the field.

cs.CV↗

arXiv2025

TB-Bench: Training and Testing Multi-Modal AI for Understanding Spatio-Temporal Traffic Behaviors from Dashcam Images/Videos

The application of Multi-modal Large Language Models (MLLMs) in Autonomous Driving (AD) faces significant challenges due to their limited training on traffic-specific data and the absence of dedicated benchmarks for spatiotemporal understanding. This study addresses these issues by proposing TB-Bench, a comprehensive benchmark designed to evaluate MLLMs on understanding traffic behaviors across eight perception tasks from ego-centric views. We also introduce vision-language instruction tuning datasets, TB-100k and TB-250k, along with simple yet effective baselines for the tasks. Through extensive experiments, we show that existing MLLMs underperform in these tasks, with even a powerful model like GPT-4o achieving less than 35% accuracy on average. In contrast, when fine-tuned with TB-100k or TB-250k, our baseline models achieve average accuracy up to 85%, significantly enhancing performance on the tasks. Additionally, we demonstrate performance transfer by co-training TB-100k with another traffic dataset, leading to improved performance on the latter. Overall, this study represents a step forward by introducing a comprehensive benchmark, high-quality datasets, and baselines, thus supporting the gradual integration of MLLMs into the perception, prediction, and planning stages of AD.

cs.CV↗

arXiv2024

Action-Agnostic Point-Level Supervision for Temporal Action Detection

We propose action-agnostic point-level (AAPL) supervision for temporal action detection to achieve accurate action instance detection with a lightly annotated dataset. In the proposed scheme, a small portion of video frames is sampled in an unsupervised manner and presented to human annotators, who then label the frames with action categories. Unlike point-level supervision, which requires annotators to search for every action instance in an untrimmed video, frames to annotate are selected without human intervention in AAPL supervision. We also propose a detection model and learning method to effectively utilize the AAPL labels. Extensive experiments on the variety of datasets (THUMOS '14, FineAction, GTEA, BEOID, and ActivityNet 1.3) demonstrate that the proposed approach is competitive with or outperforms prior methods for video-level and point-level supervision in terms of the trade-off between the annotation cost and detection performance.

cs.CV↗

arXiv2024

A Simple Channel Compression Method for Brain Signal Decoding on Classification Task

In the application of brain-computer interface (BCI), while pursuing accurate decoding of brain signals, we also need consider the computational efficiency of BCI devices. ECoG signals are multi-channel temporal signals which is collected using a high-density electrode array at a high sampling frequency. The data between channels has a high similarity or redundancy in the temporal domain. The redundancy of data not only reduces the computational efficiency of the model, but also overwhelms the extraction of effective features, resulting in a decrease in performance. How to efficiently utilize ECoG multi-channel signals is one of the research topics. Effective channel screening or compression can greatly reduce the model size, thereby improving computational efficiency, this would be a good direction to solve the problem. Based on previous work [1], this paper proposes a very simple channel compression method, which uses a learnable matrix to perform matrix multiplication on the original channels, that is, assigning weights to the channels and then linearly add them up. This effectively reduces the number of final channels. In the experiment, we used the vision-based ECoG multi-classification dataset owned by our laboratory to test the proposed channel selection (compression) method. We found that the new method can compress the original 128-channel ECoG signal to 32 channels (of which subject MonJ is compressed to 8 channels), greatly reducing the size of the model. The demand for GPU memory resources during model training is reduced by about 68.57%, 84.33% for each subject respectively; the model training speed also increased up around 3.82, 4.65 times of the original speed for each subject respectively. More importantly, the performance of the model has improved by about 1.10% compared with our previous work, reached the SOTA level of our unique visual based ECoG dataset

math.NA↗

arXiv2024

RP-SLAM: Real-time Photorealistic SLAM with Efficient 3D Gaussian Splatting

3D Gaussian Splatting has emerged as a promising technique for high-quality 3D rendering, leading to increasing interest in integrating 3DGS into realism SLAM systems. However, existing methods face challenges such as Gaussian primitives redundancy, forgetting problem during continuous optimization, and difficulty in initializing primitives in monocular case due to lack of depth information. In order to achieve efficient and photorealistic mapping, we propose RP-SLAM, a 3D Gaussian splatting-based vision SLAM method for monocular and RGB-D cameras. RP-SLAM decouples camera poses estimation from Gaussian primitives optimization and consists of three key components. Firstly, we propose an efficient incremental mapping approach to achieve a compact and accurate representation of the scene through adaptive sampling and Gaussian primitives filtering. Secondly, a dynamic window optimization method is proposed to mitigate the forgetting problem and improve map consistency. Finally, for the monocular case, a monocular keyframe initialization method based on sparse point cloud is proposed to improve the initialization accuracy of Gaussian primitives, which provides a geometric basis for subsequent optimization. The results of numerous experiments demonstrate that RP-SLAM achieves state-of-the-art map rendering accuracy while ensuring real-time performance and model compactness.

cs.RO↗

arXiv2024

Rethinking Annotation for Object Detection: Is Annotating Small-size Instances Worth Its Cost?

Detecting objects occupying only small areas in an image is difficult, even for humans. Therefore, annotating small-size object instances is hard and thus costly. This study questions common sense by asking the following: is annotating small-size instances worth its cost? We restate it as the following verifiable question: can we detect small-size instances with a detector trained using training data free of small-size instances? We evaluate a method that upscales input images at test time and a method that downscales images at training time. The experiments conducted using the COCO dataset show the following. The first method, together with a remedy to narrow the domain gap between training and test inputs, achieves at least comparable performance to the baseline detector trained using complete training data. Although the method needs to apply the same detector twice to an input image with different scaling, we show that its distillation yields a single-path detector that performs equally well to the same baseline detector. These results point to the necessity of rethinking the annotation of training data for object detection.

cs.CV↗

arXiv2024

Open-vocabulary vs. Closed-set: Best Practice for Few-shot Object Detection Considering Text Describability

Open-vocabulary object detection (OVD), detecting specific classes of objects using only their linguistic descriptions (e.g., class names) without any image samples, has garnered significant attention. However, in real-world applications, the target class concepts is often hard to describe in text and the only way to specify target objects is to provide their image examples, yet it is often challenging to obtain a good number of samples. Thus, there is a high demand from practitioners for few-shot object detection (FSOD). A natural question arises: Can the benefits of OVD extend to FSOD for object classes that are difficult to describe in text? Compared to traditional methods that learn only predefined classes (referred to in this paper as closed-set object detection, COD), can the extra cost of OVD be justified? To answer these questions, we propose a method to quantify the ``text-describability'' of object detection datasets using the zero-shot image classification accuracy with CLIP. This allows us to categorize various OD datasets with different text-describability and emprically evaluate the FSOD performance of OVD and COD methods within each category. Our findings reveal that: i) there is little difference between OVD and COD for object classes with low text-describability under equal conditions in OD pretraining; and ii) although OVD can learn from more diverse data than OD-specific data, thereby increasing the volume of training data, it can be counterproductive for classes with low-text-describability. These findings provide practitioners with valuable guidance amidst the recent advancements of OVD methods.

cs.CV↗

arXiv2024

Exploring the Potential of Multi-Modal AI for Driving Hazard Prediction

This paper addresses the problem of predicting hazards that drivers may encounter while driving a car. We formulate it as a task of anticipating impending accidents using a single input image captured by car dashcams. Unlike existing approaches to driving hazard prediction that rely on computational simulations or anomaly detection from videos, this study focuses on high-level inference from static images. The problem needs predicting and reasoning about future events based on uncertain observations, which falls under visual abductive reasoning. To enable research in this understudied area, a new dataset named the DHPR (Driving Hazard Prediction and Reasoning) dataset is created. The dataset consists of 15K dashcam images of street scenes, and each image is associated with a tuple containing car speed, a hypothesized hazard description, and visual entities present in the scene. These are annotated by human annotators, who identify risky scenes and provide descriptions of potential accidents that could occur a few seconds later. We present several baseline methods and evaluate their performance on our dataset, identifying remaining issues and discussing future directions. This study contributes to the field by introducing a novel problem formulation and dataset, enabling researchers to explore the potential of multi-modal AI for driving hazard prediction.

cs.CV↗