Search Results for author:
Found 50 papers, 11 papers with code
GeoMan: Temporally Consistent Human Geometry Estimation using Image-to-Video Diffusion
GeoMan addresses two key challenges: the scarcity of high-quality 4D training data and the need for metric depth estimation to accurately model human size.
Convergent Complex Quasi-Newton Proximal Methods for Gradient-Driven Denoisers in Compressed Sensing MRI Reconstruction
To address the complex domain in CS MRI, we propose a modified Hessian estimation method that guarantees Hermitian positive definiteness.
Efficient and robust 3D blind harmonization for large domain gaps
Our framework employs a 3D rectified flow trained on target domain images to reconstruct the original image from an edge map, then yielding a harmonized image from the edge of a source domain image.
On Geometrical Properties of Text Token Embeddings for Strong Semantic Binding in Text-to-Image Generation
Here we investigate the geometrical properties of text token embeddings and their cross-attention (CA) maps.
Efficient Personalization of Quantized Diffusion Model without Backpropagation
Diffusion models have shown remarkable performance in image synthesis, but they demand extensive computational and memory resources for training, fine-tuning and inference.
Localized Concept Erasure for Text-to-Image Diffusion Models Using Training-Free Gated Low-Rank Adaptation
To address these limitations, we first introduce a framework called localized concept erasure, which allows for the deletion of only the specific area containing the target concept in the image while preserving the other regions.
Skrr: Skip and Re-use Text Encoder Layers for Memory Efficient Text-to-Image Generation
Large-scale text encoders in text-to-image (T2I) diffusion models have demonstrated exceptional performance in generating high-quality images from textual prompts.
PersonaCraft: Personalized Full-Body Image Synthesis for Multiple Identities from Single References Using 3D-Model-Conditioned Diffusion
Personalized image generation has been significantly advanced, enabling the creation of highly realistic and customized images.
Adaptive Selection of Sampling-Reconstruction in Fourier Compressed Sensing
Our method outperforms joint optimization of sampling-reconstruction ($\mathcal{H}_1$) and adaptive sampling ($\mathcal{H}_2$) by achieving significant improvements on several Fourier CS problems.
MOST: MR reconstruction Optimization for multiple downStream Tasks via continual learning
To mitigate this issue, downstream task-oriented reconstruction optimization has been proposed for a single downstream task.
INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding
Weakly supervised affordance grounding teaches agents the concept of affordance without costly pixel-level annotations, but with exocentric images.
Contribution-based Low-Rank Adaptation with Pre-training Model for Real Image Restoration
Recently, pre-trained model and efficient parameter tuning have achieved remarkable success in natural language processing and high-level computer vision with the aid of masked modeling and prompt tuning.
Short-term Object Interaction Anticipation with Disentangled Object Detection @ Ego4D Short Term Object Interaction Anticipation Challenge
Short-term object interaction anticipation is an important task in egocentric video analysis, including precise predictions of future interactions and their timings as well as the categories and positions of the involved active objects.
Ranked #2 on
Short-term Object Interaction Anticipation
on Ego4D
BeyondScene: Higher-Resolution Human-Centric Scene Generation With Pretrained Diffusion
We propose BeyondScene, a novel framework that overcomes prior limitations, generating exquisite higher-resolution (over 8K) human-centric scenes with exceptional text-image correspondence and naturalness using existing pretrained diffusion models.
Doubly Perturbed Task Free Continual Learning
Specifically, for input perturbation, we propose an approximate perturbation method that injects noise into the input data as well as the feature vector and then interpolates the two perturbed samples.
Deep Internal Learning: Deep Learning from a Single Input
Yet, in many cases there is value in training a network just from the input at hand.
Fast and accurate sparse-view CBCT reconstruction using meta-learned neural attenuation field and hash-encoding regularization
In the FACT method, we meta-trained a neural network and a hash-encoder using a few scans (= 15), and a new regularization technique is utilized to reconstruct the details of an anatomical structure.
On Exact Inversion of DPM-Solvers
Diffusion probabilistic models (DPMs) are a key component in modern generative models.
Detailed Human-Centric Text Description-Driven Large Scene Synthesis
Text-driven large scene image synthesis has made significant progress with diffusion models, but controlling it is challenging.
Fully Quantized Always-on Face Detector Considering Mobile Image Sensors
In this study, we aim to bridge the gap by exploring extremely low-bit lightweight face detectors, focusing on the always-on face detection scenario for mobile image sensor applications.
Online Continual Learning on Hierarchical Label Expansion
To address this challenge, we propose a novel multi-level hierarchical class incremental task configuration with an online learning constraint, called hierarchical label expansion (HLE).
Efficient Unified Demosaicing for Bayer and Non-Bayer Patterned Image Sensors
Our KLAP and KLAP-M methods achieved state-of-the-art demosaicing performance in both synthetic and real RAW data of Bayer and non-Bayer CFAs.
Neural Diffeomorphic Non-uniform B-spline Flows
In this work, we propose diffeomorphic non-uniform B-spline flows that are at least twice continuously differentiable while bi-Lipschitz continuous, enabling efficient parametrization while retaining analytic inverse transforms based on a sufficient condition for diffeomorphism.
DITTO-NeRF: Diffusion-based Iterative Text To Omni-directional 3D Model
Our DITTO-NeRF consists of constructing high-quality partial 3D object for limited in-boundary (IB) angles using the given or text-generated 2D image from the frontal view and then iteratively reconstructing the remaining 3D NeRF using inpainting latent diffusion model.
PODIA-3D: Domain Adaptation of 3D Generative Model Across Large Domain Gap Using Pose-Preserved Text-to-Image Diffusion
However, adapting 3D generators to domains with significant domain gaps from the source domain still remains challenging due to issues in current text-to-image diffusion models as following: 1) shape-pose trade-off in diffusion-based translation, 2) pose bias, and 3) instance bias in the target domain, resulting in inferior 3D shapes, low text-image correspondence, and low intra-domain diversity in the generated samples.
All-in-One Image Restoration for Unknown Degradations Using Adaptive Discriminative Filters for Specific Degradations
Image restorations for single degradations have been widely studied, demonstrating excellent performance for each degradation, but can not reflect unpredictable realistic environments with unknown multiple degradations, which may change over time.
On the Robustness of Normalizing Flows for Inverse Problems in Imaging
Most normalizing flows for inverse problems in imaging employ the conditional affine coupling layer that can generate diverse images quickly.
DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model
Here we propose DATID-3D, a domain adaptation method tailored for 3D generative models using text-to-image diffusion models that can synthesize diverse images per text prompt without collecting additional images and camera information for the target domain.
Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report
Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks.
Efficient and Accurate Quantized Image Super-Resolution on Mobile NPUs, Mobile AI & AIM 2022 challenge: Report
While numerous solutions have been proposed for this problem in the past, they are usually not compatible with low-power mobile NPUs having many computational and memory constraints.
Self-supervised training of deep denoisers in multi-coil MRI considering noise correlations
Deep learning-based denoising methods have shown powerful results for improving the signal-to-noise ratio of magnetic resonance (MR) images, mostly by leveraging supervised learning with clean ground truth.
Adaptive GLCM sampling for transformer-based COVID-19 detection on CT
The experimental results show that the proposed method improve the detection performance with large margin without much difficult modification to the model.
Self-supervised regression learning using domain knowledge: Applications to improving self-supervised denoising in imaging
Regression that predicts continuous quantity is a central part of applications using computational imaging and computer vision technologies.
Self-supervised regression learning using domain knowledge: Applications to improving self-supervised image denoising
Regression that predicts continuous quantity is a central part of applications using computational imaging and computer vision technologies.
Rethinking Deep Image Prior for Denoising
Deep image prior (DIP) serves as a good inductive bias for diverse inverse problems.
Image Restoration by Deep Projected GSURE
In the first one, where no explicit prior is used, we show that the proposed approach outperforms other internal learning methods, such as DIP.
Blur More To Deblur Better: Multi-Blur2Deblur For Efficient Video Deblurring
Secondly, we propose multi-blurring recurrent neural network (MBRNN) that can synthesize more blurred images from neighboring frames, yielding substantially improved performance with existing video deblurring methods.
Ranked #7 on
Deblurring
on DVD
(using extra training data)
Task-Aware Variational Adversarial Active Learning
Often, labeling large amount of data is challenging due to high labeling cost limiting the application domain of deep learning techniques.
Multi-Temporal Recurrent Neural Networks For Progressive Non-Uniform Single Image Deblurring With Incremental Temporal Training
Multi-scale (MS) approaches have been widely investigated for blind single image / video deblurring that sequentially recovers deblurred images in low spatial scale first and then in high spatial scale later with the output of lower scales.
Ranked #21 on
Deblurring
on HIDE (trained on GOPRO)
A Single Multi-Task Deep Neural Network with Post-Processing for Object Detection with Reasoning and Robotic Grasp Detection
Recently, robotic grasp detection (GD) and object detection (OD) with reasoning have been investigated using deep neural networks (DNNs).
Down-Scaling with Learned Kernels in Multi-Scale Deep Neural Networks for Non-Uniform Single Image Deblurring
Our proposed CNN-based down-scaling was the key factor for this excellent performance since the performance of our network without it was decreased by 1. 98dB.
Extending Stein's unbiased risk estimator to train deep denoisers with correlated pairs of noisy images
Here, we propose an extended SURE (eSURE) to train deep denoisers with correlated pairs of noise realizations per image and applied it to the case with two uncorrelated realizations per image to achieve better performance than SURE based method and comparable results to Noise2Noise.
Empirically Accelerating Scaled Gradient Projection Using Deep Neural Network For Inverse Problems In Image Processing
Recently, deep neural networks (DNNs) have shown advantages in accelerating optimization algorithms.
Real-Time, Highly Accurate Robotic Grasp Detection using Fully Convolutional Neural Network with Rotation Ensemble Module
However, rotation-invariance in robotic grasp detection has been only recently studied by using rotation anchor box that are often time-consuming and unreliable for multiple objects.
SREdgeNet: Edge Enhanced Single Image Super Resolution using Dense Edge Detection Network and Feature Merge Network
Recently, SRGAN was proposed to avoid this average effect by minimizing perceptual losses instead of l1 loss and it yielded perceptually better SR images (or images with sharp edges) at the price of lowering PSNR.
Real-Time, Highly Accurate Robotic Grasp Detection using Fully Convolutional Neural Networks with High-Resolution Images
Our methods also achieved state-of-the-art detection accuracy (up to 96. 6%) with state-of- the-art real-time computation time for high-resolution images (6-20ms per 360x360 image) on Cornell dataset.
Training deep learning based image denoisers from undersampled measurements without ground truth and without image prior
Our proposed methods were able to train deep learning based image denoisers from undersampled measurements without ground truth images and without image priors, and to recover images with state-of-the-art qualities from undersampled data.
Classification based Grasp Detection using Spatial Transformer Network
Typically, regression based grasp detection methods have outperformed classification based detection methods in computation complexity with excellent accuracy.
Training Deep Learning Based Denoisers without Ground Truth Data
Our quick refining method outperformed conventional BM3D, deep image prior, and often the networks trained with ground truth.
