Search Results for author:
Found 115 papers, 55 papers with code
Text2CAD: Text to 3D CAD Generation via Technical Drawings
The generation of industrial Computer-Aided Design (CAD) models from user requests and specifications is crucial to enhancing efficiency in modern manufacturing.
GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring
To train a deblurring network, an appropriate dataset with paired blurry and sharp images is essential.
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
In this work, we present ODGS, a novel rasterization pipeline for omnidirectional images, with geometric interpretation.
CLOSER: Towards Better Representation Learning for Few-Shot Class-Incremental Learning
Building upon the recent efforts for enhancing transferability, such as promoting the spread of features, we find that trying to secure the spread of features within a more confined feature space enables the learned representation to strike a better balance between transferability and discriminability.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
T2LM: Long-Term 3D Human Motion Generation from Multiple Sentences
To address these issues, we introduce simple yet effective T2LM, a continuous long-term generation framework that can be trained without sequential data.
Grokfast: Accelerated Grokking by Amplifying Slow Gradients
One puzzling artifact in machine learning dubbed grokking is where delayed generalization is achieved tenfolds of iterations after near perfect overfitting to the training data.
DeblurGS: Gaussian Splatting for Camera Motion Blur
Although significant progress has been made in reconstructing sharp 3D scenes from motion-blurred images, a transition to real-world applications remains challenging.
Joint Reconstruction of 3D Human and Object via Contact-Based Refinement Transformer
As a result, our CONTHO achieves state-of-the-art performance in both human-object contact estimation and joint reconstruction of 3D human and object.
Ranked #1 on
Contact Detection
on BEHAVE
AdaBM: On-the-Fly Adaptive Bit Mapping for Image Super-Resolution
Although image super-resolution (SR) problem has experienced unprecedented restoration accuracy with deep neural networks, it has yet limited versatile applications due to the substantial computational costs.
Beyond Image Super-Resolution for Image Recognition with Task-Driven Perceptual Loss
Through extensive experiments, we demonstrate that our SR4IR achieves outstanding task performance by generating SR images useful for a specific image recognition task, including semantic segmentation, object detection, and image classification.
SemanticDraw: Towards Real-Time Interactive Content Creation from Image Diffusion Models
Despite astonishing generation quality from recent diffusion models, we find that existing approaches for regional controllability are very slow (52 seconds for $512 \times 512$ image) while not compatible with acceleration methods such as LCM, blocking their huge potential in interactive content creation.
Rethinking RGB Color Representation for Image Restoration Models
Image restoration models are typically trained with a pixel-wise distance loss defined over the RGB color representation space, which is well known to be a source of blurry and unrealistic textures in the restored images.
RHOBIN Challenge: Reconstruction of Human Object Interaction
Modeling the interaction between humans and objects has been an emerging research direction in recent years.
CNC-Net: Self-Supervised Learning for CNC Machining Operations
CNC manufacturing is a process that employs computer numerical control (CNC) machines to govern the movements of various industrial tools and machinery, encompassing equipment ranging from grinders and lathes to mills and CNC routers.
Depth-Regularized Optimization for 3D Gaussian Splatting in Few-Shot Images
In this paper, we present a method to optimize Gaussian splatting with a limited number of images while avoiding overfitting.
LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes
Specifically, we project a portion of point cloud to the desired view and provide the projection as a guidance for inpainting using the generative model.
3DHR-Co: A Collaborative Test-time Refinement Framework for In-the-Wild 3D Human-Body Reconstruction Task
We answer this challenge by proposing a strategy that complements 3DHR test-time refinement work under a collaborative approach.
Ranked #5 on
3D Human Pose Estimation
on 3DPW
(MPJPE metric)
ExBluRF: Efficient Radiance Fields for Extreme Motion Blurred Images
We minimize the photo-consistency loss on blurred image space and obtain the sharp radiance fields with camera trajectories that explain the blur of all images.
Extract-and-Adaptation Network for 3D Interacting Hand Mesh Recovery
Our two novel tokens are from a combination of separated two hand features; hence, it is much more robust to the distant token problem.
Ranked #1 on
3D Interacting Hand Pose Estimation
on InterHand2.6M
NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge.
Human Part-wise 3D Motion Context Learning for Sign Language Recognition
In order to utilize part-wise motion context, we propose the alternating combination of a part-wise encoding Transformer (PET) and a whole-body encoding Transformer (WET).
Cyclic Test-Time Adaptation on Monocular Video for 3D Human Mesh Reconstruction
To overcome the above issues, we introduce CycleAdapt, which cyclically adapts two networks: a human mesh reconstruction network (HMRNet) and a human motion denoising network (MDNet), given a test video.
Ranked #8 on
3D Human Pose Estimation
on 3DPW
Overcoming Distribution Mismatch in Quantizing Image Super-Resolution Networks
In contrast, we propose a new quantization-aware training scheme that effectively Overcomes the Distribution Mismatch problem in SR networks without the need for dynamic adaptation.
ICF-SRSR: Invertible scale-Conditional Function for Self-Supervised Real-world Single Image Super-Resolution
Single image super-resolution (SISR) is a challenging ill-posed problem that aims to up-sample a given low-resolution (LR) image to a high-resolution (HR) counterpart.
Recovering 3D Hand Mesh Sequence from a Single Blurry Image: A New Dataset and Temporal Unfolding
In addition to the new dataset, we propose BlurHandNet, a baseline network for accurate 3D hand mesh recovery from a blurry hand image.
Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation
Recently, a few self-supervised representation learning (SSL) methods have outperformed the ImageNet classification pre-training for vision tasks such as object detection.
ACL-SPC: Adaptive Closed-Loop system for Self-Supervised Point Cloud Completion
Point cloud completion addresses filling in the missing parts of a partial point cloud obtained from depth sensors and generating a complete point cloud.
Content-Aware Local GAN for Photo-Realistic Super-Resolution
Recently, GAN has successfully contributed to making single-image super-resolution (SISR) methods produce more realistic images.
MEIL-NeRF: Memory-Efficient Incremental Learning of Neural Radiance Fields
Under such incremental learning scenarios, neural networks are known to suffer catastrophic forgetting: easily forgetting previously seen data after training with new data.
MultiAct: Long-Term 3D Human Motion Generation from Multiple Action Labels
The action-conditioned methods generate a sequence of motion from a single action.
MonoNHR: Monocular Neural Human Renderer
Existing neural human rendering methods struggle with a single image input due to the lack of information in invisible areas and the depth ambiguity of pixels in visible areas.
Extraction of Coronary Vessels in Fluoroscopic X-Ray Sequences Using Vessel Correspondence Optimization
We present a method to extract coronary vessels from fluoroscopic x-ray sequences.
CADyQ: Content-Aware Dynamic Quantization for Image Super-Resolution
In this work, to achieve high average bit-reduction with less accuracy loss, we propose a novel Content-Aware Dynamic Quantization (CADyQ) method for SR networks that allocates optimal bits to local regions and layers adaptively based on the local contents of an input image.
3D Clothed Human Reconstruction in the Wild
Although much progress has been made in 3D clothed human reconstruction, most of the existing methods fail to produce robust results from in-the-wild images, which contain diverse human poses and appearances.
Ranked #5 on
Garment Reconstruction
on 4D-DRESS
(using extra training data)
Controllable Image Enhancement
Specifically, an encoder-decoder framework encodes the retouching skills into latent codes and decodes them into the parameters of image signal processing (ISP) functions.
Attentive Fine-Grained Structured Sparsity for Image Restoration
Image restoration tasks have witnessed great performance improvement in recent years by developing large deep models.
Pay Attention to Hidden States for Video Deblurring: Ping-Pong Recurrent Neural Networks and Selective Non-Local Attention
When motion blur is strong, however, hidden states are hard to deliver proper information due to the displacement between different frames.
HandOccNet: Occlusion-Robust 3D Hand Mesh Estimation Network
However, we argue that occluded regions have strong correlations with hands so that they can provide highly beneficial information for complete 3D hand mesh estimation.
Ranked #5 on
3D Hand Pose Estimation
on DexYCB
CVF-SID: Cyclic multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise from Image
The CVF module can output multiple decomposed variables of the input and take a combination of the outputs back as an input in a cyclic manner.
AP-BSN: Self-Supervised Denoising for Real-World Images via Asymmetric PD and Blind-Spot Network
Extensive studies demonstrate that our method outperforms the other self-supervised and even unpaired denoising methods by a large margin, without using any additional knowledge, e. g., noise level, regarding the underlying unknown noise.
Recurrence-in-Recurrence Networks for Video Deblurring
State-of-the-art video deblurring methods often adopt recurrent neural networks to model the temporal dependency between the frames.
C2N: Practical Generative Noise Modeling for Real-World Denoising
In a practical scenario, a noise generator should learn to simulate the general and complex noise distribution without using paired noisy and clean images.
Batch Normalization Tells You Which Filter is Important
The goal of filter pruning is to search for unimportant filters to remove in order to make convolutional neural networks (CNNs) efficient without sacrificing the performance in the process.
Generative Residual Attention Network for Disease Detection
Accurate identification and localization of abnormalities from radiology images serve as a critical role in computer-aided diagnosis (CAD) systems.
PolyNet: Polynomial Neural Network for 3D Shape Recognition with PolyShape Representation
3D shape representation and its processing have substantial effects on 3D shape recognition.
Ranked #1 on
3D Object Classification
on ModelNet10
Meta-Learning with Task-Adaptive Loss Function for Few-Shot Learning
The problem lies in that each application and task may require different auxiliary loss function, especially when tasks are diverse and distinct.
Toward Real-World Super-Resolution via Adaptive Downsampling Models
Most image super-resolution (SR) methods are developed on synthetic low-resolution (LR) and high-resolution (HR) image pairs that are constructed by a predetermined operation, e. g., bicubic downsampling.
3DIAS: 3D Shape Reconstruction with Implicit Algebraic Surfaces
Our experiments demonstrate the superiorities of our method in terms of representation power compared to the state-of-the-art methods in single RGB image 3D shape reconstruction.
Real-Time Video Super-Resolution on Smartphones with Deep Learning, Mobile AI 2021 Challenge: Report
Video super-resolution has recently become one of the most important mobile-related problems due to the rise of video communication and streaming services.
NTIRE 2021 Challenge on Video Super-Resolution
Super-Resolution (SR) is a fundamental computer vision task that aims to obtain a high-resolution clean image from the given low-resolution counterpart.
NTIRE 2021 Challenge on Image Deblurring
In this challenge report, we describe the challenge specifics and the evaluation results from the 2 competition tracks with the proposed solutions.
Clean Images are Hard to Reblur: Exploiting the Ill-Posed Inverse Task for Dynamic Scene Deblurring
The supervised reblurring loss at training stage compares the amplified blur between the deblurred and the sharp images.
SRWarp: Generalized Image Super-Resolution under Arbitrary Transformation
Deep CNNs have achieved significant successes in image processing and its applications, including single image super-resolution (SR).
Learning to Estimate Robust 3D Human Mesh from In-the-Wild Crowded Scenes
Second, we propose a joint-based regressor that distinguishes a target person's feature from others.
Ranked #10 on
3D Multi-Person Pose Estimation
on MuPoTS-3D
2D Human Pose Estimation
3D Multi-Person Human Pose Estimation
+1
Adaptive Dataset Sampling by Deep Policy Gradient
Mini-batch SGD is a predominant optimization method in deep learning.
Motion-Aware Dynamic Architecture for Efficient Frame Interpolation
Video frame interpolation aims to synthesize accurate intermediate frames given a low-frame-rate video.
Searching for Controllable Image Restoration Networks
Diverse user preferences over images have recently led to a great amount of interest in controlling the imagery effects for image restoration tasks.
DAQ: Channel-Wise Distribution-Aware Quantization for Deep Image Super-Resolution Networks
Quantizing deep convolutional neural networks for image super-resolution substantially reduces their computational costs.
Accurate 3D Hand Pose Estimation for Whole-Body 3D Human Mesh Estimation
Using Pose2Pose, Hand4Whole utilizes hand MCP joint features to predict 3D wrists as MCP joints largely contribute to 3D wrist rotations in the human kinematic chain.
NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets
Assuming no 3D pseudo-GTs are available, NeuralAnnot is weakly supervised with GT 2D/3D joint coordinates of training sets.
Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video
Our TCMR significantly outperforms previous video-based methods in temporal consistency with better per-frame 3D pose and shape accuracy.
Ranked #65 on
3D Human Pose Estimation
on MPI-INF-3DHP
DynaVSR: Dynamic Adaptive Blind Video Super-Resolution
Most conventional supervised super-resolution (SR) algorithms assume that low-resolution (LR) data is obtained by downscaling high-resolution (HR) data with a fixed known kernel, but such an assumption often does not hold in real scenarios.
Ranked #7 on
Video Super-Resolution
on MSU Video Upscalers: Quality Enhancement
(VMAF metric)
Meta-Learning with Adaptive Hyperparameters
Despite its popularity, several recent works question the effectiveness of MAML when test tasks are different from training tasks, thus suggesting various task-conditioned methodology to improve the initialization.
AIM 2020 Challenge on Video Temporal Super-Resolution
Videos in the real-world contain various dynamics and motions that may look unnaturally discontinuous in time when the recordedframe rate is low.
Domain Adaptation of Learned Features for Visual Localization
We tackle the problem of visual localization under changing conditions, such as time of day, weather, and seasons.
InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image
Therefore, we firstly propose (1) a large-scale dataset, InterHand2. 6M, and (2) a baseline network, InterNet, for 3D interacting hand pose estimation from a single RGB image.
Ranked #8 on
3D Interacting Hand Pose Estimation
on InterHand2.6M
Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose
Most of the recent deep learning-based 3D human pose and mesh estimation methods regress the pose and shape parameters of human mesh models, such as SMPL and MANO, from an input image.
Ranked #21 on
3D Hand Pose Estimation
on FreiHAND
DeepHandMesh: A Weakly-supervised Deep Encoder-Decoder Framework for High-fidelity Hand Mesh Modeling
We design our system to be trained in an end-to-end and weakly-supervised manner; therefore, it does not require groundtruth meshes.
I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image
Most of the previous image-based 3D human pose and mesh estimation methods estimate parameters of the human mesh model from an input image.
Ranked #18 on
3D Hand Pose Estimation
on HO-3D v2
Visual Tracking by TridentAlign and Context Embedding
However, extensive scale variations of the target object and distractor objects with similar categories have consistently posed challenges in visual tracking.
IntegralAction: Pose-driven Feature Integration for Robust Human Action Recognition in Videos
Most current action recognition methods heavily rely on appearance information by taking an RGB sequence of entire image regions as input.
AIM 2019 Challenge on Video Temporal Super-Resolution: Methods and Results
Videos contain various types and strengths of motions that may look unnaturally discontinuous in time when the recorded frame rate is low.
NTIRE 2020 Challenge on Image and Video Deblurring
This paper reviews the NTIRE 2020 Challenge on Image and Video Deblurring.
Channel Attention Is All You Need for Video Frame Interpolation
Prevailing video frame interpolation techniques rely heavily on optical flow estimation and require additional model complexity and computational cost; it is also susceptible to error propagation in challenging scenarios with large motion and heavy occlusion.
Scene-Adaptive Video Frame Interpolation via Meta-Learning
Finally, we show that our meta-learning framework can be easily employed to any video frame interpolation network and can consistently improve its performance on multiple benchmark datasets.
Fine-Grained Neural Architecture Search
We present an elegant framework of fine-grained neural architecture search (FGNAS), which allows to employ multiple heterogeneous operations within a single layer and can even generate compositional feature maps using several different base operations.
PoseLifter: Absolute 3D human pose lifting network from a single noisy 2D human pose
This study presents a new network (i. e., PoseLifter) that can lift a 2D human pose to an absolute 3D pose in a camera coordinate system.
Ranked #51 on
3D Human Pose Estimation
on MPI-INF-3DHP
(PCK metric)
Continual Learning by Asymmetric Loss Approximation with Single-Side Overestimation
Catastrophic forgetting is a critical challenge in training deep neural networks.
Camera Distance-aware Top-down Approach for 3D Multi-person Pose Estimation from a Single RGB Image
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case.
Ranked #1 on
Monocular 3D Human Pose Estimation
on Human3.6M
(Use Video Sequence metric)
Learning to Forget for Meta-Learning
Model-agnostic meta-learning (MAML) tackles the problem by formulating prior knowledge as a common initialization across tasks, which is then used to quickly adapt to unseen tasks.
Multi-scale Aggregation R-CNN for 2D Multi-person Pose Estimation
Multi-person pose estimation from a 2D image is challenging because it requires not only keypoint localization but also human detection.
PoseFix: Model-agnostic General Human Pose Refinement Network
In this paper, we propose a human pose refinement network that estimates a refined pose from a tuple of an input image and input pose.
Ranked #2 on
Multi-Person Pose Estimation
on MS COCO
(Validation AP metric)
SPNet: Deep 3D Object Classification and Retrieval using Stereographic Projection
We propose an efficient Stereographic Projection Neural Network (SPNet) for learning representations of 3D objects.
Task-Aware Image Downscaling
Our framework is efficient, and it can be generalized to handle an arbitrary image resizing operation.
Clustering Convolutional Kernels to Compress Deep Neural Networks
In this paper, we propose a novel method to compress CNNs by reconstructing the network from a small set of spatial convolution kernels.
Deep Vessel Segmentation By Learning Graphical Connectivity
We propose a novel deep-learning-based system for vessel segmentation.
Ranked #1 on
Retinal Vessel Segmentation
on HRF
SeedNet: Automatic Seed Generation With Deep Reinforcement Learning for Robust Interactive Segmentation
In this paper, we propose an automatic seed generation technique with deep reinforcement learning to solve the interactive segmentation problem.
Part-Aligned Bilinear Representations for Person Re-identification
We propose a novel network that learns a part-aligned representation for person re-identification.
Ranked #4 on
Person Re-Identification
on UAV-Human
Deep Meta Learning for Real-Time Target-Aware Visual Tracking
In this paper, we propose a novel on-line visual tracking framework based on the Siamese matching network and meta-learner network, which run at real-time speeds.
Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals
Official Torch7 implementation of "V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map", CVPR 2018
Ranked #5 on
Hand Pose Estimation
on HANDS 2017
Joint Blind Motion Deblurring and Depth Estimation of Light Field
Removing camera motion blur from a single light field is a challenging task since it is highly ill-posed inverse problem.
V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map
To overcome these weaknesses, we firstly cast the 3D hand and human pose estimation problem from a single depth map into a voxel-to-voxel prediction that uses a 3D voxelized grid and estimates the per-voxel likelihood for each keypoint.
Ranked #3 on
Pose Estimation
on ITOP top-view
Joint Weakly and Semi-Supervised Deep Learning for Localization and Classification of Masses in Breast Ultrasound Images
The results trained with only 10 strongly annotated images along with weakly annotated images were comparable to results trained from 800 strongly annotated images, with the 95% confidence interval of difference -3. 00%--5. 00%, in terms of the correct localization (CorLoc) measure, which is the ratio of images with intersection over union with ground truth higher than 0. 5.
Look Wider to Match Image Patches with Convolutional Neural Networks
When a human matches two images, the viewer has a natural tendency to view the wide area around the target pixel to obtain clues of right correspondence.
Joint Estimation of Camera Pose, Depth, Deblurring, and Super-Resolution from a Blurred Image Sequence
The conventional methods for estimating camera poses and scene structures from severely blurry or low resolution images often result in failure.
Palettenet: Image recolorization with given color palette
PaletteNet is then designed to change the color concept of a source image so that the palette of the output image is close to the target palette.
Enhanced Deep Residual Networks for Single Image Super-Resolution
Recent research on super-resolution has progressed with the development of deep convolutional neural networks (DCNN).
Ranked #1 on
Image Super-Resolution
on DIV2K val - 4x upscaling
(PSNR metric)
Holistic Planimetric prediction to Local Volumetric prediction for 3D Human Pose Estimation
We propose a novel approach to 3D human pose estimation from a single depth map.
2D-3D Pose Consistency-based Conditional Random Fields for 3D Human Pose Estimation
The unary term of the proposed CRF model is defined based on a powerful heat-map regression network, which has been proposed for 2D human pose estimation.
Online Video Deblurring via Dynamic Temporal Blending Network
We show the superiority of the proposed method in an extensive experimental evaluation.
Real-time visual tracking by deep reinforced decision making
In this paper, we introduce a novel real-time visual tracking algorithm based on a template selection strategy constructed by deep reinforcement learning methods.
Deep Multi-scale Convolutional Neural Network for Dynamic Scene Deblurring
To remove these complicated motion blurs, conventional energy optimization based methods rely on simple assumptions such that blur kernel is partially uniform or locally linear.
Ranked #18 on
Deblurring
on RealBlur-R (trained on GoPro)
(SSIM (sRGB) metric)
Occlusion-Aware Video Deblurring with a New Layered Blur Model
We also provide a novel analysis on the blur kernel at object boundaries, which shows the distinctive characteristics of the blur kernel that cannot be captured by conventional blur models.
Dynamic Scene Deblurring using a Locally Adaptive Linear Blur Model
We infer bidirectional optical flows to handle motion blurs, and also estimate Gaussian blur maps to remove optical blur from defocus in our new blur model.
Deeply-Recursive Convolutional Network for Image Super-Resolution
We propose an image super-resolution method (SR) using a deeply-recursive convolutional network (DRCN).
Ranked #25 on
Image Super-Resolution
on Urban100 - 2x upscaling
Accurate Image Super-Resolution Using Very Deep Convolutional Networks
We present a highly accurate single-image super-resolution (SR) method.
Ranked #4 on
Image Super-Resolution
on WebFace - 8x upscaling
Generalized Video Deblurring for Dynamic Scenes
We propose a video deblurring method to deal with general blurs inherent in dynamic scenes, contrary to other methods.
Subgraph Matching Using Compactness Prior for Robust Feature Correspondence
By constructing Markov chain on the restricted search space instead of the original solution space, our method approximates the solution effectively.
MRF Optimization by Graph Approximation
However, not much research efforts has been done on the generation of "good" proposals, especially for non-metric energy functions.
Interval Tracker: Tracking by Interval Analysis
By minimizing the interval of the posterior, our method can reduce the modeling uncertainty in the posterior.
Scanline Sampler without Detailed Balance: An Efficient MCMC for MRF Optimization
To come up with faster sampling method, we investigate two ideas: breaking detailed balance and updating multiple nodes at a time.
Segmentation-Free Dynamic Scene Deblurring
Thus, we propose a new energy model simultaneously estimating motion flow and the latent image based on robust total variation (TV)-L1 model.
Minimum Uncertainty Gap for Robust Visual Tracking
The uncertainty of the likelihood is estimated by obtaining the gap between the lower and upper bounds of the likelihood.
Tensor-Based High-Order Semantic Relation Transfer for Semantic Scene Segmentation
In this paper, we propose semantic relation transfer, a method to transfer high-order semantic relations of objects from annotated images to unlabeled images analogous to label transfer techniques where label information are transferred.
