Search Results for author:
Found 52 papers, 12 papers with code
Disparity Estimation Using a Quad-Pixel Sensor
Similar to a dual-pixel (DP) sensor, the phase shifting can be regarded as stereo disparity and utilized for depth estimation.
Diffusion-Based Adaptation for Classification of Unknown Degraded Images
To address the issue of imperfect adapted clean images from diffusion models for the classification of degraded images, we propose a novel Diffusion-based Adaptation for Unknown Degraded images (DiffAUD) method based on robust classifiers trained on a few known degradations.
Ranked #6 on
Domain Generalization
on ImageNet-C
(Top 1 Accuracy metric, using extra
training data)
Neural Radiance Fields for Novel View Synthesis in Monocular Gastroscopy
Enabling the synthesis of arbitrarily novel viewpoint images within a patient's stomach from pre-captured monocular gastroscopic images is a promising topic in stomach diagnosis.
VSRD: Instance-Aware Volumetric Silhouette Rendering for Weakly Supervised 3D Object Detection
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.
Ranked #1 on
Weakly Supervised 3D Detection
on KITTI-360
CFDNet: A Generalizable Foggy Stereo Matching Network with Contrastive Feature Distillation
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.
Digging Into Normal Incorporated Stereo Matching
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.
Self-Supervised Spatially Variant PSF Estimation for Aberration-Aware Depth-from-Defocus
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.
Reflection Removal Using Recurrent Polarization-to-Polarization Network
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.
Global Occlusion-Aware Transformer for Robust Stereo Matching
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.
Polarimetric PatchMatch Multi-View Stereo
PatchMatch Multi-View Stereo (PatchMatch MVS) is one of the popular MVS approaches, owing to its balanced accuracy and efficiency.
EMR-MSF: Self-Supervised Recurrent Monocular Scene Flow Exploiting Ego-Motion Rigidity
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.
Polarimetric Multi-View Inverse Rendering
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.
Dual-Pixel Raindrop Removal
In this paper, we propose the first method using a Dual-Pixel (DP) sensor to better address the raindrop removal.
Two-Step Color-Polarization Demosaicking Network
Polarization information of light in a scene is valuable for various image processing and computer vision tasks.
Deep Hyperspectral-Depth Reconstruction Using Single Color-Dot Projection
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.
Self-Supervised Ego-Motion Estimation Based on Multi-Layer Fusion of RGB and Inferred Depth
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.
Single Image Deraining Network with Rain Embedding Consistency and Layered LSTM
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.
Learning-Based Depth and Pose Estimation for Monocular Endoscope with Loss Generalization
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.
Multi-Modal Pedestrian Detection with Large Misalignment Based on Modal-Wise Regression and Multi-Modal IoU
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.
Geometric Data Augmentation Based on Feature Map Ensemble
The performance of CNN is dramatically degraded by geometric transformation, such as large rotations.
Video-Based Camera Localization Using Anchor View Detection and Recursive 3D Reconstruction
In this paper we introduce a new camera localization strategy designed for image sequences captured in challenging industrial situations such as industrial parts inspection.
Spectral MVIR: Joint Reconstruction of 3D Shape and Spectral Reflectance
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.
VIO-Aided Structure from Motion Under Challenging Environments
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.
Spectral Reflectance Estimation Using Projector with Unknown Spectral Power Distribution
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.
Deep Snapshot HDR Imaging Using Multi-Exposure Color Filter Array
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.
Adaptive Future Frame Prediction with Ensemble Network
A common limitation of the existing learning-based approaches is a mismatch of training data and test data.
Human Segmentation with Dynamic LiDAR Data
It has a two-branch structure, i. e., the spatial segmentation branch and the temporal velocity estimation branch.
Monochrome and Color Polarization Demosaicking Using Edge-Aware Residual Interpolation
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.
Polarimetric Multi-View Inverse Rendering
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.
3D Pipe Network Reconstruction Based on Structure from Motion with Incremental Conic Shape Detection and Cylindrical Constraint
Pipe inspection is a critical task for many industries and infrastructure of a city.
Classifying degraded images over various levels of degradation
Classification for degraded images having various levels of degradation is very important in practical applications.
Stomach 3D Reconstruction Based on Virtual Chromoendoscopic Image Generation
Gastric endoscopy is a standard clinical process that enables medical practitioners to diagnose various lesions inside a patient's stomach.
Learning-Based Human Segmentation and Velocity Estimation Using Automatic Labeled LiDAR Sequence for Training
In this paper, we propose an automatic labeled sequential data generation pipeline for human segmentation and velocity estimation with point clouds.
Pro-Cam SSfM: Projector-Camera System for Structure and Spectral Reflectance from Motion
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.
Is This The Right Place? Geometric-Semantic Pose Verification for Indoor Visual Localization
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.
3D Reconstruction of Whole Stomach from Endoscope Video Using Structure-from-Motion
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.
Improving Transparency of Deep Neural Inference Process
However, the inference process of deep learning is black-box, and not very suitable to safety-critical systems which must exhibit high transparency.
Automatic Labeled LiDAR Data Generation based on Precise Human Model
We present 500k+ data generated by the proposed pipeline.
Estimation and Restoration of Compositional Degradation Using Convolutional Neural Networks
However, image degradations in practice are often a mixture of several types of degradation.
Gradient-Based Low-Light Image Enhancement
A low-light image enhancement is a highly demanded image processing technique, especially for consumer digital cameras and cameras on mobile phones.
Non-blind Image Restoration Based on Convolutional Neural Network
Blind image restoration processors based on convolutional neural network (CNN) are intensively researched because of their high performance.
Joint optimization for compressive video sensing and reconstruction under hardware constraints
Compressive video sensing is the process of encoding multiple sub-frames into a single frame with controlled sensor exposures and reconstructing the sub-frames from the single compressed frame.
Structure-from-Motion using Dense CNN Features with Keypoint Relocalization
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.
InLoc: Indoor Visual Localization with Dense Matching and View Synthesis
We seek to predict the 6 degree-of-freedom (6DoF) pose of a query photograph with respect to a large indoor 3D map.
Misalignment-Robust Joint Filter for Cross-Modal Image Pairs
Next, the joint-filter cost volume and a set of filtered images are computed from the target image and the set of the translated guidances.
Benchmarking 6DOF Outdoor Visual Localization in Changing Conditions
Visual localization enables autonomous vehicles to navigate in their surroundings and augmented reality applications to link virtual to real worlds.
Are Large-Scale 3D Models Really Necessary for Accurate Visual Localization?
3D structure-based methods employ 3D models of the scene to estimate the full 6DOF pose of a camera very accurately.
Gradient-Domain Image Reconstruction Framework With Intensity-Range and Base-Structure Constraints
To generate detail-preserving and artifact-free output images, we combine the benefits of the two approaches into the proposed framework by introducing the intensity-range constraint and the base-structure constraint.
24/7 Place Recognition by View Synthesis
We address the problem of large-scale visual place recognition for situations where the scene undergoes a major change in appearance, for example, due to illumination (day/night), change of seasons, aging, or structural modifications over time such as buildings built or destroyed.
A General and Simple Method for Camera Pose and Focal Length Determination
In this paper, we revisit the pose determination problem of a partially calibrated camera with unknown focal length, hereafter referred to as the PnPf problem, by using n (n ≥ 4) 3D-to-2D point correspondences.
A Practical Rank-Constrained Eight-Point Algorithm for Fundamental Matrix Estimation
Due to its simplicity, the eight-point algorithm has been widely used in fundamental matrix estimation.
Visual Place Recognition with Repetitive Structures
Even more importantly, they violate the feature independence assumed in the bag-of-visual-words representation which often leads to over-counting evidence and significant degradation of retrieval performance.
