Masatoshi Okutomi

Zhuofeng Wu, Doehyung Lee, Zihua Liu et al.

A quad-pixel (QP) sensor is increasingly integrated into commercial mobile cameras. The QP sensor has a unit of 2$\times$2 four photodiodes under a single microlens, generating multi-directional phase shifting when out-focus blurs occur. Similar to a dual-pixel (DP) sensor, the phase shifting can be regarded as stereo disparity and utilized for depth estimation. Based on this, we propose a QP disparity estimation network (QPDNet), which exploits abundant QP information by fusing vertical and horizontal stereo-matching correlations for effective disparity estimation. We also present a synthetic pipeline to generate a training dataset from an existing RGB-Depth dataset. Experimental results demonstrate that our QPDNet outperforms state-of-the-art stereo and DP methods. Our code and synthetic dataset are available at https://github.com/Zhuofeng-Wu/QPDNet.

Jinyu Zhao, Yusuke Monno, Masatoshi Okutomi

A polarization camera has great potential for 3D reconstruction since the angle of polarization (AoP) and the degree of polarization (DoP) of reflected light are related to an object's surface normal. In this paper, we propose a novel 3D reconstruction method called Polarimetric Multi-View Inverse Rendering (Polarimetric MVIR) that effectively exploits geometric, photometric, and polarimetric cues extracted from input multi-view color-polarization images. We first estimate camera poses and an initial 3D model by geometric reconstruction with a standard structure-from-motion and multi-view stereo pipeline. We then refine the initial model by optimizing photometric rendering errors and polarimetric errors using multi-view RGB, AoP, and DoP images, where we propose a novel polarimetric cost function that enables an effective constraint on the estimated surface normal of each vertex, while considering four possible ambiguous azimuth angles revealed from the AoP measurement. The weight for the polarimetric cost is effectively determined based on the DoP measurement, which is regarded as the reliability of polarimetric information. Experimental results using both synthetic and real data demonstrate that our Polarimetric MVIR can reconstruct a detailed 3D shape without assuming a specific surface material and lighting condition.

Vy Nguyen, Masayuki Tanaka, Yusuke Monno et al.

Polarization information of light in a scene is valuable for various image processing and computer vision tasks. A division-of-focal-plane polarimeter is a promising approach to capture the polarization images of different orientations in one shot, while it requires color-polarization demosaicking. In this paper, we propose a two-step color-polarization demosaicking network~(TCPDNet), which consists of two sub-tasks of color demosaicking and polarization demosaicking. We also introduce a reconstruction loss in the YCbCr color space to improve the performance of TCPDNet. Experimental comparisons demonstrate that TCPDNet outperforms existing methods in terms of the image quality of polarization images and the accuracy of Stokes parameters.

Zijie Jiang, Hajime Taira, Naoyuki Miyashita et al.

In existing self-supervised depth and ego-motion estimation methods, ego-motion estimation is usually limited to only leveraging RGB information. Recently, several methods have been proposed to further improve the accuracy of self-supervised ego-motion estimation by fusing information from other modalities, e.g., depth, acceleration, and angular velocity. However, they rarely focus on how different fusion strategies affect performance. In this paper, we investigate the effect of different fusion strategies for ego-motion estimation and propose a new framework for self-supervised learning of depth and ego-motion estimation, which performs ego-motion estimation by leveraging RGB and inferred depth information in a Multi-Layer Fusion manner. As a result, we have achieved state-of-the-art performance among learning-based methods on the KITTI odometry benchmark. Detailed studies on the design choices of leveraging inferred depth information and fusion strategies have also been carried out, which clearly demonstrate the advantages of our proposed framework.

Yizhou Li, Yusuke Monno, Masatoshi Okutomi

Removing raindrops in images has been addressed as a significant task for various computer vision applications. In this paper, we propose the first method using a Dual-Pixel (DP) sensor to better address the raindrop removal. Our key observation is that raindrops attached to a glass window yield noticeable disparities in DP's left-half and right-half images, while almost no disparity exists for in-focus backgrounds. Therefore, DP disparities can be utilized for robust raindrop detection. The DP disparities also brings the advantage that the occluded background regions by raindrops are shifted between the left-half and the right-half images. Therefore, fusing the information from the left-half and the right-half images can lead to more accurate background texture recovery. Based on the above motivation, we propose a DP Raindrop Removal Network (DPRRN) consisting of DP raindrop detection and DP fused raindrop removal. To efficiently generate a large amount of training data, we also propose a novel pipeline to add synthetic raindrops to real-world background DP images. Experimental results on synthetic and real-world datasets demonstrate that our DPRRN outperforms existing state-of-the-art methods, especially showing better robustness to real-world situations. Our source code and datasets are available at http://www.ok.sc.e.titech.ac.jp/res/SIR/.

Chunyu Li, Yusuke Monno, Masatoshi Okutomi

Depth reconstruction and hyperspectral reflectance reconstruction are two active research topics in computer vision and image processing. Conventionally, these two topics have been studied separately using independent imaging setups and there is no existing method which can acquire depth and spectral reflectance simultaneously in one shot without using special hardware. In this paper, we propose a novel single-shot hyperspectral-depth reconstruction method using an off-the-shelf RGB camera and projector. Our method is based on a single color-dot projection, which simultaneously acts as structured light for depth reconstruction and spatially-varying color illuminations for hyperspectral reflectance reconstruction. To jointly reconstruct the depth and the hyperspectral reflectance from a single color-dot image, we propose a novel end-to-end network architecture that effectively incorporates a geometric color-dot pattern loss and a photometric hyperspectral reflectance loss. Through the experiments, we demonstrate that our hyperspectral-depth reconstruction method outperforms the combination of an existing state-of-the-art single-shot hyperspectral reflectance reconstruction method and depth reconstruction method.

Amir Melnikov, Masayuki Tanaka, Yusuke Monno et al.

Accurate interpretation of street-level imagery is essential for large-scale urban mapping and the creation of Spatial Digital Twin (SDT) environments. This work presents a unified framework for joint 2D-3D segmentation and association that integrates visual semantics with multi-view geometric reasoning. Unlike conventional approaches that rely heavily on sequential frames for temporal tracking, our method leverages zero-shot detection and segmentation together with structure-from-motion reconstruction to establish stable cross-view correspondences. A 3D-driven association mechanism replaces traditional 2D multi-object tracking, using geometric consistency to guide identity preservation across wide-baseline viewpoints and varying imaging conditions. By combining 2D texture cues with global 3D context, the proposed pipeline is well-suited for scalable street-level processing and can be used for a variety of object types. Experiments demonstrate substantially improved coverage of ground-truth sequences and more robust identity retention compared to state-of-the-art 2D-only tracking methods, achieving a 22% performance gain in challenging urban scenarios.

Jinyu Zhao, Jumpei Oishi, Yusuke Monno et al.

PatchMatch Multi-View Stereo (PatchMatch MVS) is one of the popular MVS approaches, owing to its balanced accuracy and efficiency. In this paper, we propose Polarimetric PatchMatch multi-view Stereo (PolarPMS), which is the first method exploiting polarization cues to PatchMatch MVS. The key of PatchMatch MVS is to generate depth and normal hypotheses, which form local 3D planes and slanted stereo matching windows, and efficiently search for the best hypothesis based on the consistency among multi-view images. In addition to standard photometric consistency, our PolarPMS evaluates polarimetric consistency to assess the validness of a depth and normal hypothesis, motivated by the physical property that the polarimetric information is related to the object's surface normal. Experimental results demonstrate that our PolarPMS can improve the accuracy and the completeness of reconstructed 3D models, especially for texture-less surfaces, compared with state-of-the-art PatchMatch MVS methods.

Zihua Liu, Hiroki Sakuma, Masatoshi Okutomi

Monocular 3D object detection is a fundamental yet challenging task in 3D scene understanding. Existing approaches heavily depend on supervised learning with extensive 3D annotations, which are often acquired from LiDAR point clouds through labor-intensive labeling processes. To tackle this problem, we propose VSRD++, a novel weakly supervised framework for monocular 3D object detection that eliminates the reliance on 3D annotations and leverages neural-field-based volumetric rendering with weak 2D supervision. VSRD++ consists of a two-stage pipeline: multi-view 3D autolabeling and subsequent monocular 3D detector training. In the multi-view autolabeling stage, object surfaces are represented as signed distance fields (SDFs) and rendered as instance masks via the proposed instance-aware volumetric silhouette rendering. To optimize 3D bounding boxes, we decompose each instance's SDF into a cuboid SDF and a residual distance field (RDF) that captures deviations from the cuboid. To address the geometry inconsistency commonly observed in volume rendering methods applied to dynamic objects, we model the dynamic objects by including velocity into bounding box attributes as well as assigning confidence to each pseudo-label. Moreover, we also employ a 3D attribute initialization module to initialize the dynamic bounding box parameters. In the monocular 3D object detection phase, the optimized 3D bounding boxes serve as pseudo labels for training monocular 3D object detectors. Extensive experiments on the KITTI-360 dataset demonstrate that VSRD++ significantly outperforms existing weakly supervised approaches for monocular 3D object detection on both static and dynamic scenes. Code is available at https://github.com/Magicboomliu/VSRD_plus_plus

Songxiao Yang, Haolin Wang, Yao Fu et al.

Rheumatoid arthritis (RA) assessment from hand radiographs requires multi-level analysis and modeling of anatomical structures and fine-grained local pathological changes. However, existing public resources do not support such unified multi-level analysis, often lacking full-hand coverage, fine-grained annotations, and consistent integration with clinical scoring systems. In particular, annotations that enable quantitative analysis of bone erosion (BE) remain scarce. RAM-H1200 contains 1,200 hand radiographs collected from six medical centers, with multi-level annotations including (i) whole-hand bone structure instance segmentation, (ii) pixel-level BE masks, (iii) SvdH-defined joint regions of interest, and (iv) joint-level SvdH scores for both BE and joint space narrowing (JSN). It is designed to evaluate whether models can jointly capture anatomical structure, localized erosive pathology, and clinically standardized RA severity from hand radiographs. The proposed BE masks enable, for the first time, quantitative BE analysis beyond coarse categorical grading by providing explicit spatial supervision for lesion extent and morphology. To our knowledge, RAM-H1200 is the first public large-scale benchmark that jointly supports whole-hand bone structure instance segmentation, pixel-level BE delineation, and clinically grounded joint-level SvdH scoring for both BE and JSN. Results across benchmark tasks show that anatomical modeling is substantially more mature than quantitative BE analysis: whole-hand bone segmentation achieves strong performance, whereas BE segmentation remains a major open challenge. By unifying anatomical structure modeling, quantitative lesion analysis, and clinically grounded SvdH scoring, RAM-H1200 provides a single benchmark for comprehensive RA analysis on hand radiographs.

Zihua Liu, Hiroki Sakuma, Masatoshi Okutomi

Monocular 3D object detection poses a significant challenge in 3D scene understanding due to its inherently ill-posed nature in monocular depth estimation. Existing methods heavily rely on supervised learning using abundant 3D labels, typically obtained through expensive and labor-intensive annotation on LiDAR point clouds. To tackle this problem, we propose a novel weakly supervised 3D object detection framework named VSRD (Volumetric Silhouette Rendering for Detection) to train 3D object detectors without any 3D supervision but only weak 2D supervision. VSRD consists of multi-view 3D auto-labeling and subsequent training of monocular 3D object detectors using the pseudo labels generated in the auto-labeling stage. In the auto-labeling stage, we represent the surface of each instance as a signed distance field (SDF) and render its silhouette as an instance mask through our proposed instance-aware volumetric silhouette rendering. To directly optimize the 3D bounding boxes through rendering, we decompose the SDF of each instance into the SDF of a cuboid and the residual distance field (RDF) that represents the residual from the cuboid. This mechanism enables us to optimize the 3D bounding boxes in an end-to-end manner by comparing the rendered instance masks with the ground truth instance masks. The optimized 3D bounding boxes serve as effective training data for 3D object detection. We conduct extensive experiments on the KITTI-360 dataset, demonstrating that our method outperforms the existing weakly supervised 3D object detection methods. The code is available at https://github.com/skmhrk1209/VSRD.

Yizhou Li, Yusuke Monno, Masatoshi Okutomi

Single image deraining is typically addressed as residual learning to predict the rain layer from an input rainy image. For this purpose, an encoder-decoder network draws wide attention, where the encoder is required to encode a high-quality rain embedding which determines the performance of the subsequent decoding stage to reconstruct the rain layer. However, most of existing studies ignore the significance of rain embedding quality, thus leading to limited performance with over/under-deraining. In this paper, with our observation of the high rain layer reconstruction performance by an rain-to-rain autoencoder, we introduce the idea of "Rain Embedding Consistency" by regarding the encoded embedding by the autoencoder as an ideal rain embedding and aim at enhancing the deraining performance by improving the consistency between the ideal rain embedding and the rain embedding derived by the encoder of the deraining network. To achieve this, a Rain Embedding Loss is applied to directly supervise the encoding process, with a Rectified Local Contrast Normalization (RLCN) as the guide that effectively extracts the candidate rain pixels. We also propose Layered LSTM for recurrent deraining and fine-grained encoder feature refinement considering different scales. Qualitative and quantitative experiments demonstrate that our proposed method outperforms previous state-of-the-art methods particularly on a real-world dataset. Our source code is available at http://www.ok.sc.e.titech.ac.jp/res/SIR/.

Zihua Liu, Yizhou Li, Masatoshi Okutomi

Despite the remarkable progress facilitated by learning-based stereo-matching algorithms, the performance in the ill-conditioned regions, such as the occluded regions, remains a bottleneck. Due to the limited receptive field, existing CNN-based methods struggle to handle these ill-conditioned regions effectively. To address this issue, this paper introduces a novel attention-based stereo-matching network called Global Occlusion-Aware Transformer (GOAT) to exploit long-range dependency and occlusion-awareness global context for disparity estimation. In the GOAT architecture, a parallel disparity and occlusion estimation module PDO is proposed to estimate the initial disparity map and the occlusion mask using a parallel attention mechanism. To further enhance the disparity estimates in the occluded regions, an occlusion-aware global aggregation module (OGA) is proposed. This module aims to refine the disparity in the occluded regions by leveraging restricted global correlation within the focus scope of the occluded areas. Extensive experiments were conducted on several public benchmark datasets including SceneFlow, KITTI 2015, and Middlebury. The results show that the proposed GOAT demonstrates outstanding performance among all benchmarks, particularly in the occluded regions.

Zihua Liu, Songyan Zhang, Zhicheng Wang et al.

Despite the remarkable progress facilitated by learning-based stereo-matching algorithms, disparity estimation in low-texture, occluded, and bordered regions still remains a bottleneck that limits the performance. To tackle these challenges, geometric guidance like plane information is necessary as it provides intuitive guidance about disparity consistency and affinity similarity. In this paper, we propose a normal incorporated joint learning framework consisting of two specific modules named non-local disparity propagation(NDP) and affinity-aware residual learning(ARL). The estimated normal map is first utilized for calculating a non-local affinity matrix and a non-local offset to perform spatial propagation at the disparity level. To enhance geometric consistency, especially in low-texture regions, the estimated normal map is then leveraged to calculate a local affinity matrix, providing the residual learning with information about where the correction should refer and thus improving the residual learning efficiency. Extensive experiments on several public datasets including Scene Flow, KITTI 2015, and Middlebury 2014 validate the effectiveness of our proposed method. By the time we finished this work, our approach ranked 1st for stereo matching across foreground pixels on the KITTI 2015 dataset and 3rd on the Scene Flow dataset among all the published works.

Zhuofeng Wu, Yusuke Monno, Masatoshi Okutomi

In this paper, we address the task of aberration-aware depth-from-defocus (DfD), which takes account of spatially variant point spread functions (PSFs) of a real camera. To effectively obtain the spatially variant PSFs of a real camera without requiring any ground-truth PSFs, we propose a novel self-supervised learning method that leverages the pair of real sharp and blurred images, which can be easily captured by changing the aperture setting of the camera. In our PSF estimation, we assume rotationally symmetric PSFs and introduce the polar coordinate system to more accurately learn the PSF estimation network. We also handle the focus breathing phenomenon that occurs in real DfD situations. Experimental results on synthetic and real data demonstrate the effectiveness of our method regarding both the PSF estimation and the depth estimation.

Yizhou Li, Zihua Liu, Yusuke Monno et al.

In this paper, we propose the first diffusion-based all-in-one video restoration method that utilizes the power of a pre-trained Stable Diffusion and a fine-tuned ControlNet. Our method can restore various types of video degradation with a single unified model, overcoming the limitation of standard methods that require specific models for each restoration task. Our contributions include an efficient training strategy with Task Prompt Guidance (TPG) for diverse restoration tasks, an inference strategy that combines Denoising Diffusion Implicit Models~(DDIM) inversion with a novel Sliding Window Cross-Frame Attention (SW-CFA) mechanism for enhanced content preservation and temporal consistency, and a scalable pipeline that makes our method all-in-one to adapt to different video restoration tasks. Through extensive experiments on five video restoration tasks, we demonstrate the superiority of our method in generalization capability to real-world videos and temporal consistency preservation over existing state-of-the-art methods. Our method advances the video restoration task by providing a unified solution that enhances video quality across multiple applications.

Zihua Liu, Yizhou Li, Masatoshi Okutomi

Stereo matching under foggy scenes remains a challenging task since the scattering effect degrades the visibility and results in less distinctive features for dense correspondence matching. While some previous learning-based methods integrated a physical scattering function for simultaneous stereo-matching and dehazing, simply removing fog might not aid depth estimation because the fog itself can provide crucial depth cues. In this work, we introduce a framework based on contrastive feature distillation (CFD). This strategy combines feature distillation from merged clean-fog features with contrastive learning, ensuring balanced dependence on fog depth hints and clean matching features. This framework helps to enhance model generalization across both clean and foggy environments. Comprehensive experiments on synthetic and real-world datasets affirm the superior strength and adaptability of our method.

Muhamad Daniel Ariff Bin Abdul Rahman, Yusuke Monno, Masayuki Tanaka et al.

A division-of-focal-plane (DoFP) polarimeter enables us to acquire images with multiple polarization orientations in one shot and thus it is valuable for many applications using polarimetric information. The image processing pipeline for a DoFP polarimeter entails two crucial tasks: denoising and demosaicking. While polarization demosaicking for a noise-free case has increasingly been studied, the research for the joint task of polarization denoising and demosaicking is scarce due to the lack of a suitable evaluation dataset and a solid baseline method. In this paper, we propose a novel dataset and method for polarization denoising and demosaicking. Our dataset contains 40 real-world scenes and three noise-level conditions, consisting of pairs of noisy mosaic inputs and noise-free full images. Our method takes a denoising-then-demosaicking approach based on well-accepted signal processing components to offer a reproducible method. Experimental results demonstrate that our method exhibits higher image reconstruction performance than other alternative methods, offering a solid baseline.

Zihua Liu, Yizhou Li, Songyan Zhang et al.

While supervised stereo matching and monocular depth estimation have advanced significantly with learning-based algorithms, self-supervised methods using stereo images as supervision signals have received relatively less focus and require further investigation. A primary challenge arises from ambiguity introduced during photometric reconstruction, particularly due to missing corresponding pixels in ill-posed regions of the target view, such as occlusions and out-of-frame areas. To address this and establish explicit photometric correspondences, we propose DMS, a model-agnostic approach that utilizes geometric priors from diffusion models to synthesize novel views along the epipolar direction, guided by directional prompts. Specifically, we finetune a Stable Diffusion model to simulate perspectives at key positions: left-left view shifted from the left camera, right-right view shifted from the right camera, along with an additional novel view between the left and right cameras. These synthesized views supplement occluded pixels, enabling explicit photometric reconstruction. Our proposed DMS is a cost-free, ''plug-and-play'' method that seamlessly enhances self-supervised stereo matching and monocular depth estimation, and relies solely on unlabeled stereo image pairs for both training and synthesizing. Extensive experiments demonstrate the effectiveness of our approach, with up to 35% outlier reduction and state-of-the-art performance across multiple benchmark datasets.

Songxiao Yang, Haolin Wang, Yao Fu et al.

Rheumatoid arthritis (RA) is a common autoimmune disease that has been the focus of research in computer-aided diagnosis (CAD) and disease monitoring. In clinical settings, conventional radiography (CR) is widely used for the screening and evaluation of RA due to its low cost and accessibility. The wrist is a critical region for the diagnosis of RA. However, CAD research in this area remains limited, primarily due to the challenges in acquiring high-quality instance-level annotations. (i) The wrist comprises numerous small bones with narrow joint spaces, complex structures, and frequent overlaps, requiring detailed anatomical knowledge for accurate annotation. (ii) Disease progression in RA often leads to osteophyte, bone erosion (BE), and even bony ankylosis, which alter bone morphology and increase annotation difficulty, necessitating expertise in rheumatology. This work presents a multi-task dataset for wrist bone in CR, including two tasks: (i) wrist bone instance segmentation and (ii) Sharp/van der Heijde (SvdH) BE scoring, which is the first public resource for wrist bone instance segmentation. This dataset comprises 1048 wrist conventional radiographs of 388 patients from six medical centers, with pixel-level instance segmentation annotations for 618 images and SvdH BE scores for 800 images. This dataset can potentially support a wide range of research tasks related to RA, including joint space narrowing (JSN) progression quantification, BE detection, bone deformity evaluation, and osteophyte detection. It may also be applied to other wrist-related tasks, such as carpal bone fracture localization. We hope this dataset will significantly lower the barrier to research on wrist RA and accelerate progress in CAD research within the RA-related domain.

Yizhou Li, Yusuke Monno, Masatoshi Okutomi et al.

Recent advances in Neural Radiance Fields (NeRF) have shown great potential in 3D reconstruction and novel view synthesis, particularly for indoor and small-scale scenes. However, extending NeRF to large-scale outdoor environments presents challenges such as transient objects, sparse cameras and textures, and varying lighting conditions. In this paper, we propose a segmentation-guided enhancement to NeRF for outdoor street scenes, focusing on complex urban environments. Our approach extends ZipNeRF and utilizes Grounded SAM for segmentation mask generation, enabling effective handling of transient objects, modeling of the sky, and regularization of the ground. We also introduce appearance embeddings to adapt to inconsistent lighting across view sequences. Experimental results demonstrate that our method outperforms the baseline ZipNeRF, improving novel view synthesis quality with fewer artifacts and sharper details.

Wenjiao Bian, Yusuke Monno, Masatoshi Okutomi

This paper addresses reflection removal, which is the task of separating reflection components from a captured image and deriving the image with only transmission components. Considering that the existence of the reflection changes the polarization state of a scene, some existing methods have exploited polarized images for reflection removal. While these methods apply polarized images as the inputs, they predict the reflection and the transmission directly as non-polarized intensity images. In contrast, we propose a polarization-to-polarization approach that applies polarized images as the inputs and predicts "polarized" reflection and transmission images using two sequential networks to facilitate the separation task by utilizing the interrelated polarization information between the reflection and the transmission. We further adopt a recurrent framework, where the predicted reflection and transmission images are used to iteratively refine each other. Experimental results on a public dataset demonstrate that our method outperforms other state-of-the-art methods.

Zijie Jiang, Masatoshi Okutomi

Self-supervised monocular scene flow estimation, aiming to understand both 3D structures and 3D motions from two temporally consecutive monocular images, has received increasing attention for its simple and economical sensor setup. However, the accuracy of current methods suffers from the bottleneck of less-efficient network architecture and lack of motion rigidity for regularization. In this paper, we propose a superior model named EMR-MSF by borrowing the advantages of network architecture design under the scope of supervised learning. We further impose explicit and robust geometric constraints with an elaborately constructed ego-motion aggregation module where a rigidity soft mask is proposed to filter out dynamic regions for stable ego-motion estimation using static regions. Moreover, we propose a motion consistency loss along with a mask regularization loss to fully exploit static regions. Several efficient training strategies are integrated including a gradient detachment technique and an enhanced view synthesis process for better performance. Our proposed method outperforms the previous self-supervised works by a large margin and catches up to the performance of supervised methods. On the KITTI scene flow benchmark, our approach improves the SF-all metric of the state-of-the-art self-supervised monocular method by 44% and demonstrates superior performance across sub-tasks including depth and visual odometry, amongst other self-supervised single-task or multi-task methods.

Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi et al.

Gastroendoscopy has been a clinical standard for diagnosing and treating conditions that affect a part of a patient's digestive system, such as the stomach. Despite the fact that gastroendoscopy has a lot of advantages for patients, there exist some challenges for practitioners, such as the lack of 3D perception, including the depth and the endoscope pose information. Such challenges make navigating the endoscope and localizing any found lesion in a digestive tract difficult. To tackle these problems, deep learning-based approaches have been proposed to provide monocular gastroendoscopy with additional yet important depth and pose information. In this paper, we propose a novel supervised approach to train depth and pose estimation networks using consecutive endoscopy images to assist the endoscope navigation in the stomach. We firstly generate real depth and pose training data using our previously proposed whole stomach 3D reconstruction pipeline to avoid poor generalization ability between computer-generated (CG) models and real data for the stomach. In addition, we propose a novel generalized photometric loss function to avoid the complicated process of finding proper weights for balancing the depth and the pose loss terms, which is required for existing direct depth and pose supervision approaches. We then experimentally show that our proposed generalized loss performs better than existing direct supervision losses.

Napat Wanchaitanawong, Masayuki Tanaka, Takashi Shibata et al.

The combined use of multiple modalities enables accurate pedestrian detection under poor lighting conditions by using the high visibility areas from these modalities together. The vital assumption for the combination use is that there is no or only a weak misalignment between the two modalities. In general, however, this assumption often breaks in actual situations. Due to this assumption's breakdown, the position of the bounding boxes does not match between the two modalities, resulting in a significant decrease in detection accuracy, especially in regions where the amount of misalignment is large. In this paper, we propose a multi-modal Faster-RCNN that is robust against large misalignment. The keys are 1) modal-wise regression and 2) multi-modal IoU for mini-batch sampling. To deal with large misalignment, we perform bounding box regression for both the RPN and detection-head with both modalities. We also propose a new sampling strategy called "multi-modal mini-batch sampling" that integrates the IoU for both modalities. We demonstrate that the proposed method's performance is much better than that of the state-of-the-art methods for data with large misalignment through actual image experiments.

Takashi Shibata, Masayuki Tanaka, Masatoshi Okutomi

Deep convolutional networks have become the mainstream in computer vision applications. Although CNNs have been successful in many computer vision tasks, it is not free from drawbacks. The performance of CNN is dramatically degraded by geometric transformation, such as large rotations. In this paper, we propose a novel CNN architecture that can improve the robustness against geometric transformations without modifying the existing backbones of their CNNs. The key is to enclose the existing backbone with a geometric transformation (and the corresponding reverse transformation) and a feature map ensemble. The proposed method can inherit the strengths of existing CNNs that have been presented so far. Furthermore, the proposed method can be employed in combination with state-of-the-art data augmentation algorithms to improve their performance. We demonstrate the effectiveness of the proposed method using standard datasets such as CIFAR, CUB-200, and Mnist-rot-12k.

Hajime Taira, Koki Onbe, Naoyuki Miyashita et al.

In this paper we introduce a new camera localization strategy designed for image sequences captured in challenging industrial situations such as industrial parts inspection. To deal with peculiar appearances that hurt standard 3D reconstruction pipeline, we exploit pre-knowledge of the scene by selecting key frames in the sequence (called as anchors) which are roughly connected to a certain location. Our method then seek the location of each frame in time-order, while recursively updating an augmented 3D model which can provide current camera location and surrounding 3D structure. In an experiment on a practical industrial situation, our method can localize over 99% frames in the input sequence, whereas standard localization methods fail to reconstruct a complete camera trajectory.

Chunyu Li, Yusuke Monno, Masatoshi Okutomi

Reconstructing an object's high-quality 3D shape with inherent spectral reflectance property, beyond typical device-dependent RGB albedos, opens the door to applications requiring a high-fidelity 3D model in terms of both geometry and photometry. In this paper, we propose a novel Multi-View Inverse Rendering (MVIR) method called Spectral MVIR for jointly reconstructing the 3D shape and the spectral reflectance for each point of object surfaces from multi-view images captured using a standard RGB camera and low-cost lighting equipment such as an LED bulb or an LED projector. Our main contributions are twofold: (i) We present a rendering model that considers both geometric and photometric principles in the image formation by explicitly considering camera spectral sensitivity, light's spectral power distribution, and light source positions. (ii) Based on the derived model, we build a cost-optimization MVIR framework for the joint reconstruction of the 3D shape and the per-vertex spectral reflectance while estimating the light source positions and the shadows. Different from most existing spectral-3D acquisition methods, our method does not require expensive special equipment and cumbersome geometric calibration. Experimental results using both synthetic and real-world data demonstrate that our Spectral MVIR can acquire a high-quality 3D model with accurate spectral reflectance property.

Zijie Jiang, Hajime Taira, Naoyuki Miyashita et al.

In this paper, we present a robust and efficient Structure from Motion pipeline for accurate 3D reconstruction under challenging environments by leveraging the camera pose information from a visual-inertial odometry. Specifically, we propose a geometric verification method to filter out mismatches by considering the prior geometric configuration of candidate image pairs. Furthermore, we introduce an efficient and scalable reconstruction approach that relies on batched image registration and robust bundle adjustment, both leveraging the reliable local odometry estimation. Extensive experimental results show that our pipeline performs better than the state-of-the-art SfM approaches in terms of reconstruction accuracy and robustness for challenging sequential image collections.

Hironori Hidaka, Yusuke Monno, Masatoshi Okutomi

A lighting-based multispectral imaging system using an RGB camera and a projector is one of the most practical and low-cost systems to acquire multispectral observations for estimating the scene's spectral reflectance information. However, existing projector-based systems assume that the spectral power distribution (SPD) of each projector primary is known, which requires additional equipment such as a spectrometer to measure the SPD. In this paper, we present a method for jointly estimating the spectral reflectance and the SPD of each projector primary. In addition to adopting a common spectral reflectance basis model, we model the projector's SPD by a low-dimensional model using basis functions obtained by a newly collected projector's SPD database. Then, the spectral reflectances and the projector's SPDs are alternatively estimated based on the basis models. We experimentally show the performance of our joint estimation using a different number of projected illuminations and investigate the potential of the spectral reflectance estimation using a projector with unknown SPD.

Takeru Suda, Masayuki Tanaka, Yusuke Monno et al.

In this paper, we propose a deep snapshot high dynamic range (HDR) imaging framework that can effectively reconstruct an HDR image from the RAW data captured using a multi-exposure color filter array (ME-CFA), which consists of a mosaic pattern of RGB filters with different exposure levels. To effectively learn the HDR image reconstruction network, we introduce the idea of luminance normalization that simultaneously enables effective loss computation and input data normalization by considering relative local contrasts in the "normalized-by-luminance" HDR domain. This idea makes it possible to equally handle the errors in both bright and dark areas regardless of absolute luminance levels, which significantly improves the visual image quality in a tone-mapped domain. Experimental results using two public HDR image datasets demonstrate that our framework outperforms other snapshot methods and produces high-quality HDR images with fewer visual artifacts.

Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi et al.

Future frame prediction in videos is a challenging problem because videos include complicated movements and large appearance changes. Learning-based future frame prediction approaches have been proposed in kinds of literature. A common limitation of the existing learning-based approaches is a mismatch of training data and test data. In the future frame prediction task, we can obtain the ground truth data by just waiting for a few frames. It means we can update the prediction model online in the test phase. Then, we propose an adaptive update framework for the future frame prediction task. The proposed adaptive updating framework consists of a pre-trained prediction network, a continuous-updating prediction network, and a weight estimation network. We also show that our pre-trained prediction model achieves comparable performance to the existing state-of-the-art approaches. We demonstrate that our approach outperforms existing methods especially for dynamically changing scenes.

Tao Zhong, Wonjik Kim, Masayuki Tanaka et al.

Consecutive LiDAR scans compose dynamic 3D sequences, which contain more abundant information than a single frame. Similar to the development history of image and video perception, dynamic 3D sequence perception starts to come into sight after inspiring research on static 3D data perception. This work proposes a spatio-temporal neural network for human segmentation with the dynamic LiDAR point clouds. It takes a sequence of depth images as input. It has a two-branch structure, i.e., the spatial segmentation branch and the temporal velocity estimation branch. The velocity estimation branch is designed to capture motion cues from the input sequence and then propagates them to the other branch. So that the segmentation branch segments humans according to both spatial and temporal features. These two branches are jointly learned on a generated dynamic point cloud dataset for human recognition. Our works fill in the blank of dynamic point cloud perception with the spherical representation of point cloud and achieves high accuracy. The experiments indicate that the introduction of temporal feature benefits the segmentation of dynamic point cloud.

Miki Morimatsu, Yusuke Monno, Masayuki Tanaka et al.

A division-of-focal-plane or microgrid image polarimeter enables us to acquire a set of polarization images in one shot. Since the polarimeter consists of an image sensor equipped with a monochrome or color polarization filter array (MPFA or CPFA), the demosaicking process to interpolate missing pixel values plays a crucial role in obtaining high-quality polarization images. In this paper, we propose a novel MPFA demosaicking method based on edge-aware residual interpolation (EARI) and also extend it to CPFA demosaicking. The key of EARI is a new edge detector for generating an effective guide image used to interpolate the missing pixel values. We also present a newly constructed full color-polarization image dataset captured using a 3-CCD camera and a rotating polarizer. Using the dataset, we experimentally demonstrate that our EARI-based method outperforms existing methods in MPFA and CPFA demosaicking.

Jinyu Zhao, Yusuke Monno, Masatoshi Okutomi

A polarization camera has great potential for 3D reconstruction since the angle of polarization (AoP) of reflected light is related to an object's surface normal. In this paper, we propose a novel 3D reconstruction method called Polarimetric Multi-View Inverse Rendering (Polarimetric MVIR) that effectively exploits geometric, photometric, and polarimetric cues extracted from input multi-view color polarization images. We first estimate camera poses and an initial 3D model by geometric reconstruction with a standard structure-from-motion and multi-view stereo pipeline. We then refine the initial model by optimizing photometric and polarimetric rendering errors using multi-view RGB and AoP images, where we propose a novel polarimetric rendering cost function that enables us to effectively constrain each estimated surface vertex's normal while considering four possible ambiguous azimuth angles revealed from the AoP measurement. Experimental results using both synthetic and real data demonstrate that our Polarimetric MVIR can reconstruct a detailed 3D shape without assuming a specific polarized reflection depending on the material.

Sho kagami, Hajime Taira, Naoyuki Miyashita et al.

Pipe inspection is a critical task for many industries and infrastructure of a city. The 3D information of a pipe can be used for revealing the deformation of the pipe surface and position of the camera during the inspection. In this paper, we propose a 3D pipe reconstruction system using sequential images captured by a monocular endoscopic camera. Our work extends a state-of-the-art incremental Structure-from-Motion (SfM) method to incorporate prior constraints given by the target shape into bundle adjustment (BA). Using this constraint, we can minimize the scale-drift that is the general problem in SfM. Moreover, our method can reconstruct a pipe network composed of multiple parts including straight pipes, elbows, and tees. In the experiments, we show that the proposed system enables more accurate and robust pipe mapping from a monocular camera in comparison with existing state-of-the-art methods.

Kazuki Endo, Masayuki Tanaka, Masatoshi Okutomi

Classification for degraded images having various levels of degradation is very important in practical applications. This paper proposes a convolutional neural network to classify degraded images by using a restoration network and an ensemble learning. The results demonstrate that the proposed network can classify degraded images over various levels of degradation well. This paper also reveals how the image-quality of training data for a classification network affects the classification performance of degraded images.

Aji Resindra Widya, Yusuke Monno, Masatoshi Okutomi et al.

Gastric endoscopy is a standard clinical process that enables medical practitioners to diagnose various lesions inside a patient's stomach. If any lesion is found, it is very important to perceive the location of the lesion relative to the global view of the stomach. Our previous research showed that this could be addressed by reconstructing the whole stomach shape from chromoendoscopic images using a structure-from-motion (SfM) pipeline, in which indigo carmine (IC) blue dye sprayed images were used to increase feature matches for SfM by enhancing stomach surface's textures. However, spraying the IC dye to the whole stomach requires additional time, labor, and cost, which is not desirable for patients and practitioners. In this paper, we propose an alternative way to achieve whole stomach 3D reconstruction without the need of the IC dye by generating virtual IC-sprayed (VIC) images based on image-to-image style translation trained on unpaired real no-IC and IC-sprayed images. We have specifically investigated the effect of input and output color channel selection for generating the VIC images and found that translating no-IC green-channel images to IC-sprayed red-channel images gives the best SfM reconstruction result.

Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi et al.

In this paper, we propose an automatic labeled sequential data generation pipeline for human segmentation and velocity estimation with point clouds. Considering the impact of deep neural networks, state-of-the-art network architectures have been proposed for human recognition using point clouds captured by Light Detection and Ranging (LiDAR). However, one disadvantage is that legacy datasets may only cover the image domain without providing important label information and this limitation has disturbed the progress of research to date. Therefore, we develop an automatic labeled sequential data generation pipeline, in which we can control any parameter or data generation environment with pixel-wise and per-frame ground truth segmentation and pixel-wise velocity information for human recognition. Our approach uses a precise human model and reproduces a precise motion to generate realistic artificial data. We present more than 7K video sequences which consist of 32 frames generated by the proposed pipeline. With the proposed sequence generator, we confirm that human segmentation performance is improved when using the video domain compared to when using the image domain. We also evaluate our data by comparing with data generated under different conditions. In addition, we estimate pedestrian velocity with LiDAR by only utilizing data generated by the proposed pipeline.

Chunyu Li, Yusuke Monno, Hironori Hidaka et al.

In this paper, we propose a novel projector-camera system for practical and low-cost acquisition of a dense object 3D model with the spectral reflectance property. In our system, we use a standard RGB camera and leverage an off-the-shelf projector as active illumination for both the 3D reconstruction and the spectral reflectance estimation. We first reconstruct the 3D points while estimating the poses of the camera and the projector, which are alternately moved around the object, by combining multi-view structured light and structure-from-motion (SfM) techniques. We then exploit the projector for multispectral imaging and estimate the spectral reflectance of each 3D point based on a novel spectral reflectance estimation model considering the geometric relationship between the reconstructed 3D points and the estimated projector positions. Experimental results on several real objects demonstrate that our system can precisely acquire a dense 3D model with the full spectral reflectance property using off-the-shelf devices.

Hajime Taira, Ignacio Rocco, Jiri Sedlar et al.

Visual localization in large and complex indoor scenes, dominated by weakly textured rooms and repeating geometric patterns, is a challenging problem with high practical relevance for applications such as Augmented Reality and robotics. To handle the ambiguities arising in this scenario, a common strategy is, first, to generate multiple estimates for the camera pose from which a given query image was taken. The pose with the largest geometric consistency with the query image, e.g., in the form of an inlier count, is then selected in a second stage. While a significant amount of research has concentrated on the first stage, there is considerably less work on the second stage. In this paper, we thus focus on pose verification. We show that combining different modalities, namely appearance, geometry, and semantics, considerably boosts pose verification and consequently pose accuracy. We develop multiple hand-crafted as well as a trainable approach to join into the geometric-semantic verification and show significant improvements over state-of-the-art on a very challenging indoor dataset.

Aji Resindra Widya, Yusuke Monno, Kosuke Imahori et al.

Gastric endoscopy is a common clinical practice that enables medical doctors to diagnose the stomach inside a body. In order to identify a gastric lesion's location such as early gastric cancer within the stomach, this work addressed to reconstruct the 3D shape of a whole stomach with color texture information generated from a standard monocular endoscope video. Previous works have tried to reconstruct the 3D structures of various organs from endoscope images. However, they are mainly focused on a partial surface. In this work, we investigated how to enable structure-from-motion (SfM) to reconstruct the whole shape of a stomach from a standard endoscope video. We specifically investigated the combined effect of chromo-endoscopy and color channel selection on SfM. Our study found that 3D reconstruction of the whole stomach can be achieved by using red channel images captured under chromo-endoscopy by spreading indigo carmine (IC) dye on the stomach surface.

Hiroshi Kuwajima, Masayuki Tanaka, Masatoshi Okutomi

Deep learning techniques are rapidly advanced recently, and becoming a necessity component for widespread systems. However, the inference process of deep learning is black-box, and not very suitable to safety-critical systems which must exhibit high transparency. In this paper, to address this black-box limitation, we develop a simple analysis method which consists of 1) structural feature analysis: lists of the features contributing to inference process, 2) linguistic feature analysis: lists of the natural language labels describing the visual attributes for each feature contributing to inference process, and 3) consistency analysis: measuring consistency among input data, inference (label), and the result of our structural and linguistic feature analysis. Our analysis is simplified to reflect the actual inference process for high transparency, whereas it does not include any additional black-box mechanisms such as LSTM for highly human readable results. We conduct experiments and discuss the results of our analysis qualitatively and quantitatively, and come to believe that our work improves the transparency of neural networks. Evaluated through 12,800 human tasks, 75% workers answer that input data and result of our feature analysis are consistent, and 70% workers answer that inference (label) and result of our feature analysis are consistent. In addition to the evaluation of the proposed analysis, we find that our analysis also provide suggestions, or possible next actions such as expanding neural network complexity or collecting training data to improve a neural network.

Wonjik Kim, Masayuki Tanaka, Masatoshi Okutomi et al.

Following improvements in deep neural networks, state-of-the-art networks have been proposed for human recognition using point clouds captured by LiDAR. However, the performance of these networks strongly depends on the training data. An issue with collecting training data is labeling. Labeling by humans is necessary to obtain the ground truth label; however, labeling requires huge costs. Therefore, we propose an automatic labeled data generation pipeline, for which we can change any parameters or data generation environments. Our approach uses a human model named Dhaiba and a background of Miraikan and consequently generated realistic artificial data. We present 500k+ data generated by the proposed pipeline. This paper also describes the specification of the pipeline and data details with evaluations of various approaches.

Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

Image restoration from a single image degradation type, such as blurring, hazing, random noise, and compression has been investigated for decades. However, image degradations in practice are often a mixture of several types of degradation. Such compositional degradations complicate restoration because they require the differentiation of different degradation types and levels. In this paper, we propose a convolutional neural network (CNN) model for estimating the degradation properties of a given degraded image. Furthermore, we introduce an image restoration CNN model that adopts the estimated degradation properties as its input. Experimental results show that the proposed degradation estimation model can successfully infer the degradation properties of compositionally degraded images. The proposed restoration model can restore degraded images by exploiting the estimated degradation properties and can achieve both blind and nonblind image restorations.

Masayuki Tanaka, Takashi Shibata, Masatoshi Okutomi

A low-light image enhancement is a highly demanded image processing technique, especially for consumer digital cameras and cameras on mobile phones. In this paper, a gradient-based low-light image enhancement algorithm is proposed. The key is to enhance the gradients of dark region, because the gradients are more sensitive for human visual system than absolute values. In addition, we involve the intensity-range constraints for the image integration. By using the intensity-range constraints, we can integrate the output image with enhanced gradients preserving the given gradient information while enforcing the intensity range of the output image within a certain intensity range. Experiments demonstrate that the proposed gradient-based low-light image enhancement can effectively enhance the low-light images.

Kazutaka Uchida, Masayuki Tanaka, Masatoshi Okutomi

Blind image restoration processors based on convolutional neural network (CNN) are intensively researched because of their high performance. However, they are too sensitive to the perturbation of the degradation model. They easily fail to restore the image whose degradation model is slightly different from the trained degradation model. In this paper, we propose a non-blind CNN-based image restoration processor, aiming to be robust against a perturbation of the degradation model compared to the blind restoration processor. Experimental comparisons demonstrate that the proposed non-blind CNN-based image restoration processor can robustly restore images compared to existing blind CNN-based image restoration processors.

Aji Resindra Widya, Akihiko Torii, Masatoshi Okutomi

Structure from Motion (SfM) using imagery that involves extreme appearance changes is yet a challenging task due to a loss of feature repeatability. Using feature correspondences obtained by matching densely extracted convolutional neural network (CNN) features significantly improves the SfM reconstruction capability. However, the reconstruction accuracy is limited by the spatial resolution of the extracted CNN features which is not even pixel-level accuracy in the existing approach. Providing dense feature matches with precise keypoint positions is not trivial because of memory limitation and computational burden of dense features. To achieve accurate SfM reconstruction with highly repeatable dense features, we propose an SfM pipeline that uses dense CNN features with relocalization of keypoint position that can efficiently and accurately provide pixel-level feature correspondences. Then, we demonstrate on the Aachen Day-Night dataset that the proposed SfM using dense CNN features with the keypoint relocalization outperforms a state-of-the-art SfM (COLMAP using RootSIFT) by a large margin.

Hajime Taira, Masatoshi Okutomi, Torsten Sattler et al.

We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photograph with respect to a large indoor 3D map. The contributions of this work are three-fold. First, we develop a new large-scale visual localization method targeted for indoor environments. The method proceeds along three steps: (i) efficient retrieval of candidate poses that ensures scalability to large-scale environments, (ii) pose estimation using dense matching rather than local features to deal with textureless indoor scenes, and (iii) pose verification by virtual view synthesis to cope with significant changes in viewpoint, scene layout, and occluders. Second, we collect a new dataset with reference 6DoF poses for large-scale indoor localization. Query photographs are captured by mobile phones at a different time than the reference 3D map, thus presenting a realistic indoor localization scenario. Third, we demonstrate that our method significantly outperforms current state-of-the-art indoor localization approaches on this new challenging data.

Torsten Sattler, Will Maddern, Carl Toft et al.

Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds. Practical visual localization approaches need to be robust to a wide variety of viewing condition, including day-night changes, as well as weather and seasonal variations, while providing highly accurate 6 degree-of-freedom (6DOF) camera pose estimates. In this paper, we introduce the first benchmark datasets specifically designed for analyzing the impact of such factors on visual localization. Using carefully created ground truth poses for query images taken under a wide variety of conditions, we evaluate the impact of various factors on 6DOF camera pose estimation accuracy through extensive experiments with state-of-the-art localization approaches. Based on our results, we draw conclusions about the difficulty of different conditions, showing that long-term localization is far from solved, and propose promising avenues for future work, including sequence-based localization approaches and the need for better local features. Our benchmark is available at visuallocalization.net.