Search Results for author:
Found 41 papers, 30 papers with code
Learning Deep Face Representation
Our basic network is capable of achieving high recognition accuracy ($85. 8\%$ on LFW benchmark) with only 8 dimension representation.
A Point Set Generation Network for 3D Object Reconstruction from a Single Image
Our final solution is a conditional shape sampler, capable of predicting multiple plausible 3D point clouds from an input image.
Ranked #2 on
3D Reconstruction
on Data3D−R2N2
(using extra training data)
3D Object Reconstruction From A Single Image
3D Reconstruction
DFANet: Deep Feature Aggregation for Real-Time Semantic Segmentation
This paper introduces an extremely efficient CNN architecture named DFANet for semantic segmentation under resource constraints.
Ranked #7 on
SMAC+
on Def_Infantry_parallel
Deep Fusion Network for Image Completion
The fusion block not only provides a smooth fusion between restored and existing content, but also provides an attention map to make network focus more on the unknown pixels.
Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation
In this paper, we present new data pre-processing and augmentation techniques for DNN-based raw image denoising.
Disentangled Image Matting
Most previous image matting methods require a roughly-specificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap.
PVN3D: A Deep Point-wise 3D Keypoints Voting Network for 6DoF Pose Estimation
Our method is a natural extension of 2D-keypoint approaches that successfully work on RGB based 6DoF estimation.
Ranked #1 on
6D Pose Estimation using RGBD
on YCB-Video
(Mean ADD-S metric)
UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
By integrating these two components together, our method achieves the best performance for unsupervised optical flow learning on multiple leading benchmarks, including MPI-SIntel, KITTI 2012 and KITTI 2015.
Ranked #1 on
Optical Flow Estimation
on Sintel Final unsupervised
NBNet: Noise Basis Learning for Image Denoising with Subspace Projection
Subsequently, image denosing can be achieved by selecting corresponding basis of the signal subspace and projecting the input into such space.
Ranked #1 on
Image Denoising
on SIDD
(SSIM (sRGB) metric)
FFB6D: A Full Flow Bidirectional Fusion Network for 6D Pose Estimation
Moreover, at the output representation stage, we designed a simple but effective 3D keypoints selection algorithm considering the texture and geometry information of objects, which simplifies keypoint localization for precise pose estimation.
Ranked #1 on
6D Pose Estimation
on LineMOD
D2C-SR: A Divergence to Convergence Approach for Real-World Image Super-Resolution
Rethinking both, we learn the distribution of underlying high-frequency details in a discrete form and propose a two-stage pipeline: divergence stage to convergence stage.
Motion Basis Learning for Unsupervised Deep Homography Estimation with Subspace Projection
Last, we propose a Feature Identity Loss (FIL) to enforce the learned image feature warp-equivariant, meaning that the result should be identical if the order of warp operation and feature extraction is swapped.
ASFlow: Unsupervised Optical Flow Learning with Adaptive Pyramid Sampling
Equipped with these two modules, our method achieves the best performance for unsupervised optical flow estimation on multiple leading benchmarks, including MPI-SIntel, KITTI 2012 and KITTI 2015.
Practical Wide-Angle Portraits Correction with Deep Structured Models
Wide-angle portraits often enjoy expanded views.
Fast Camera Image Denoising on Mobile GPUs with Deep Learning, Mobile AI 2021 Challenge: Report
A detailed description of all models developed in the challenge is provided in this paper.
ADNet: Attention-guided Deformable Convolutional Network for High Dynamic Range Imaging
In this paper, we present an attention-guided deformable convolutional network for hand-held multi-frame high dynamic range (HDR) imaging, namely ADNet.
Ranked #5 on
Face Alignment
on WFW (Extra Data)
NTIRE 2021 Challenge on Burst Super-Resolution: Methods and Results
This paper reviews the NTIRE2021 challenge on burst super-resolution.
EBSR: Feature Enhanced Burst Super-Resolution With Deformable Alignment
We propose a novel architecture to handle the problem of multi-frame super-resolution (MFSR).
Ranked #2 on
Burst Image Super-Resolution
on SyntheticBurst
iShape: A First Step Towards Irregular Shape Instance Segmentation
In this paper, we introduce a brand new dataset to promote the study of instance segmentation for objects with irregular shapes.
Ranked #1 on
Instance Segmentation
on iShape
Learning Optical Flow with Adaptive Graph Reasoning
Our key idea is to decouple the context reasoning from the matching procedure, and exploit scene information to effectively assist motion estimation by learning to reason over the adaptive graph.
Deep Constrained Least Squares for Blind Image Super-Resolution
In this paper, we tackle the problem of blind image super-resolution(SR) with a reformulated degradation model and two novel modules.
Ranked #1 on
Blind Super-Resolution
on DIV2KRK - 2x upscaling
Towards Self-Supervised Category-Level Object Pose and Size Estimation
Instead, we propose a label-free method that learns to enforce the geometric consistency between category template mesh and observed object point cloud under a self-supervision manner.
Practical Stereo Matching via Cascaded Recurrent Network with Adaptive Correlation
With the advent of convolutional neural networks, stereo matching algorithms have recently gained tremendous progress.
FS6D: Few-Shot 6D Pose Estimation of Novel Objects
6D object pose estimation networks are limited in their capability to scale to large numbers of object instances due to the close-set assumption and their reliance on high-fidelity object CAD models.
BSRT: Improving Burst Super-Resolution with Swin Transformer and Flow-Guided Deformable Alignment
To overcome the challenges in BurstSR, we propose a Burst Super-Resolution Transformer (BSRT), which can significantly improve the capability of extracting inter-frame information and reconstruction.
Ranked #1 on
Burst Image Super-Resolution
on BurstSR
NTIRE 2022 Challenge on Efficient Super-Resolution: Methods and Results
The aim was to design a network for single image super-resolution that achieved improvement of efficiency measured according to several metrics including runtime, parameters, FLOPs, activations, and memory consumption while at least maintaining the PSNR of 29. 00dB on DIV2K validation set.
NTIRE 2022 Challenge on High Dynamic Range Imaging: Methods and Results
The challenge is composed of two tracks with an emphasis on fidelity and complexity constraints: In Track 1, participants are asked to optimize objective fidelity scores while imposing a low-complexity constraint (i. e. solutions can not exceed a given number of operations).
Explaining Deepfake Detection by Analysing Image Matching
Besides the supervision of binary labels, deepfake detection models implicitly learn artifact-relevant visual concepts through the FST-Matching (i. e. the matching fake, source, target images) in the training set.
RealFlow: EM-based Realistic Optical Flow Dataset Generation from Videos
Specifically, we first estimate optical flow between a pair of video frames, and then synthesize a new image from this pair based on the predicted flow.
Efficient One Pass Self-distillation with Zipf's Label Smoothing
This paper proposes an efficient self-distillation method named Zipf's Label Smoothing (Zipf's LS), which uses the on-the-fly prediction of a network to generate soft supervision that conforms to Zipf distribution without using any contrastive samples or auxiliary parameters.
Fast Nearest Convolution for Real-Time Efficient Image Super-Resolution
The proposed nearest convolution has the same performance as the nearest upsampling but is much faster and more suitable for Android NNAPI.
Implicit Identity Leakage: The Stumbling Block to Improving Deepfake Detection Generalization
In this paper, we analyse the generalization ability of binary classifiers for the task of deepfake detection.
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.
DIPNet: Efficiency Distillation and Iterative Pruning for Image Super-Resolution
To address this issue, we propose a novel multi-stage lightweight network boosting method, which can enable lightweight networks to achieve outstanding performance.
Realistic Noise Synthesis with Diffusion Models
Deep image denoising models often rely on large amount of training data for the high quality performance.
Low-Light Image Enhancement with Wavelet-based Diffusion Models
Diffusion models have achieved promising results in image restoration tasks, yet suffer from time-consuming, excessive computational resource consumption, and unstable restoration.
Ranked #1 on
Low-Light Image Enhancement
on LOLv2
SAM-IQA: Can Segment Anything Boost Image Quality Assessment?
Our experiments confirm the powerful feature extraction capabilities of Segment Anything and highlight the value of combining spatial-domain and frequency-domain features in IQA tasks.
Supervised Homography Learning with Realistic Dataset Generation
In this paper, we propose an iterative framework, which consists of two phases: a generation phase and a training phase, to generate realistic training data and yield a supervised homography network.
MEFLUT: Unsupervised 1D Lookup Tables for Multi-exposure Image Fusion
In this paper, we introduce a new approach for high-quality multi-exposure image fusion (MEF).
GAFlow: Incorporating Gaussian Attention into Optical Flow
Moreover, for reliable motion analysis, we provide a new Gaussian-Guided Attention Module (GGAM) which not only inherits properties from Gaussian distribution to instinctively revolve around the neighbor fields of each point but also is empowered to put the emphasis on contextually related regions during matching.
Sparse Beats Dense: Rethinking Supervision in Radar-Camera Depth Completion
In this paper, we find that the challenge of using sparse supervision for training Radar-Camera depth prediction models is the Projection Transformation Collapse (PTC).
