Search Results for author:
Found 211 papers, 143 papers with code
Iterative Prompt Learning for Unsupervised Backlit Image Enhancement
To solve this issue, we devise a prompt learning framework that first learns an initial prompt pair by constraining the text-image similarity between the prompt (negative/positive sample) and the corresponding image (backlit image/well-lit image) in the CLIP latent space.
SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
Since coarse depth maps are not strictly scaled to the ground-truth depth maps, we propose a simple yet effective constraint, a local depth ranking method, on NeRFs such that the expected depth ranking of the NeRF is consistent with that of the coarse depth maps in local patches.
Nighttime Smartphone Reflective Flare Removal Using Optical Center Symmetry Prior
With the dataset, neural networks can be trained to remove the reflective flares effectively.
CelebV-Text: A Large-Scale Facial Text-Video Dataset
This paper presents CelebV-Text, a large-scale, diverse, and high-quality dataset of facial text-video pairs, to facilitate research on facial text-to-video generation tasks.
Learning Generative Structure Prior for Blind Text Image Super-resolution
To restrict the generative space of StyleGAN so that it obeys the structure of characters yet remains flexible in handling different font styles, we store the discrete features for each character in a codebook.
Task-Oriented Human-Object Interactions Generation with Implicit Neural Representations
Generating task-oriented human-object interaction motions in simulation is challenging.
Position-Guided Point Cloud Panoptic Segmentation Transformer
DEtection TRansformer (DETR) started a trend that uses a group of learnable queries for unified visual perception.
Correlational Image Modeling for Self-Supervised Visual Pre-Training
We introduce Correlational Image Modeling (CIM), a novel and surprisingly effective approach to self-supervised visual pre-training.
Tube-Link: A Flexible Cross Tube Baseline for Universal Video Segmentation
Our framework is a near-online approach that takes a short subclip as input and outputs the corresponding spatial-temporal tube masks.
StyleGANEX: StyleGAN-Based Manipulation Beyond Cropped Aligned Faces
Recent advances in face manipulation using StyleGAN have produced impressive results.
Aligning Bag of Regions for Open-Vocabulary Object Detection
The embeddings of regions in a bag are treated as embeddings of words in a sentence, and they are sent to the text encoder of a VLM to obtain the bag-of-regions embedding, which is learned to be aligned to the corresponding features extracted by a frozen VLM.
Ranked #2 on
Open Vocabulary Object Detection
on MSCOCO
(using extra training data)
Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement
Our approach is motivated by a few unique characteristics in the Fourier domain: 1) most luminance information concentrates on amplitudes while noise is closely related to phases, and 2) a high-resolution image and its low-resolution version share similar amplitude patterns. Through embedding Fourier into our network, the amplitude and phase of a low-light image are separately processed to avoid amplifying noise when enhancing luminance.
Betrayed by Captions: Joint Caption Grounding and Generation for Open Vocabulary Instance Segmentation
In this work, we focus on instance-level open vocabulary segmentation, intending to expand a segmenter for instance-wise novel categories without mask annotations.
Reference-based Image and Video Super-Resolution via C2-Matching
To tackle these challenges, we propose C2-Matching in this work, which performs explicit robust matching crossing transformation and resolution.
Correspondence Distillation from NeRF-based GAN
The neural radiance field (NeRF) has shown promising results in preserving the fine details of objects and scenes.
Self-Supervised Geometry-Aware Encoder for Style-Based 3D GAN Inversion
In this paper, we study the challenging problem of 3D GAN inversion where a latent code is predicted given a single face image to faithfully recover its 3D shapes and detailed textures.
DifFace: Blind Face Restoration with Diffused Error Contraction
Moreover, the transition distribution can contract the error of the restoration backbone and thus makes our method more robust to unknown degradations.
Ranked #5 on
Blind Face Restoration
on CelebA-Test
BeautyREC: Robust, Efficient, and Content-preserving Makeup Transfer
The key insights of this study are modeling component-specific correspondence for local makeup transfer, capturing long-range dependencies for global makeup transfer, and enabling efficient makeup transfer via a single-path structure.
AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies
Existing correspondence datasets for two-dimensional (2D) cartoon suffer from simple frame composition and monotonic movements, making them insufficient to simulate real animations.
Unified Vision and Language Prompt Learning
Prompt tuning, a parameter- and data-efficient transfer learning paradigm that tunes only a small number of parameters in a model's input space, has become a trend in the vision community since the emergence of large vision-language models like CLIP.
Flare7K: A Phenomenological Nighttime Flare Removal Dataset
In this paper, we introduce, Flare7K, the first nighttime flare removal dataset, which is generated based on the observation and statistics of real-world nighttime lens flares.
Ranked #1 on
Flare Removal
on Flare7K
Deep Fourier Up-Sampling
Existing convolutional neural networks widely adopt spatial down-/up-sampling for multi-scale modeling.
VToonify: Controllable High-Resolution Portrait Video Style Transfer
Although a series of successful portrait image toonification models built upon the powerful StyleGAN have been proposed, these image-oriented methods have obvious limitations when applied to videos, such as the fixed frame size, the requirement of face alignment, missing non-facial details and temporal inconsistency.
MIPI 2022 Challenge on Quad-Bayer Re-mosaic: Dataset and Report
A detailed description of all models developed in this challenge is provided in this paper.
MIPI 2022 Challenge on RGBW Sensor Re-mosaic: Dataset and Report
A detailed description of all models developed in this challenge is provided in this paper.
MIPI 2022 Challenge on RGBW Sensor Fusion: Dataset and Report
A detailed description of all models developed in this challenge is provided in this paper.
MIPI 2022 Challenge on Under-Display Camera Image Restoration: Methods and Results
In this paper, we summarize and review the Under-Display Camera (UDC) Image Restoration track on MIPI 2022.
MIPI 2022 Challenge on RGB+ToF Depth Completion: Dataset and Report
A detailed description of all models developed in this challenge is provided in this paper.
On-Device Domain Generalization
Another interesting observation is that the teacher-student gap on out-of-distribution data is bigger than that on in-distribution data, which highlights the capacity mismatch issue as well as the shortcoming of KD.
Mind the Gap in Distilling StyleGANs
To further enhance the semantic consistency between the teacher and student model, we present a latent-direction-based distillation loss that preserves the semantic relations in latent space.
StyleLight: HDR Panorama Generation for Lighting Estimation and Editing
To tackle this problem, we propose a coupled dual-StyleGAN panorama synthesis network (StyleLight) that integrates LDR and HDR panorama synthesis into a unified framework.
GLEAN: Generative Latent Bank for Image Super-Resolution and Beyond
While most existing perceptual-oriented approaches attempt to generate realistic outputs through learning with adversarial loss, our method, Generative LatEnt bANk (GLEAN), goes beyond existing practices by directly leveraging rich and diverse priors encapsulated in a pre-trained GAN.
CuDi: Curve Distillation for Efficient and Controllable Exposure Adjustment
Our method inherits the zero-reference learning and curve-based framework from an effective low-light image enhancement method, Zero-DCE, with further speed up in its inference speed, reduction in its model size, and extension to controllable exposure adjustment.
CelebV-HQ: A Large-Scale Video Facial Attributes Dataset
Large-scale datasets have played indispensable roles in the recent success of face generation/editing and significantly facilitated the advances of emerging research fields.
Ranked #1 on
Unconditional Video Generation
on CelebV-HQ
Exploring CLIP for Assessing the Look and Feel of Images
Measuring the perception of visual content is a long-standing problem in computer vision.
Transformer with Implicit Edges for Particle-based Physics Simulation
Consequently, in this paper we propose a novel Transformer-based method, dubbed as Transformer with Implicit Edges (TIE), to capture the rich semantics of particle interactions in an edge-free manner.
BRACE: The Breakdancing Competition Dataset for Dance Motion Synthesis
Estimating human keypoints from these videos is difficult due to the complexity of the dance, as well as the multiple moving cameras recording setup.
Monocular 3D Object Reconstruction with GAN Inversion
Reconstruction is achieved by searching for a latent space in the 3D GAN that best resembles the target mesh in accordance with the single view observation.
Towards Robust Blind Face Restoration with Codebook Lookup Transformer
In this paper, we demonstrate that a learned discrete codebook prior in a small proxy space largely reduces the uncertainty and ambiguity of restoration mapping by casting blind face restoration as a code prediction task, while providing rich visual atoms for generating high-quality faces.
Ranked #1 on
Blind Face Restoration
on WIDER
Masked Frequency Modeling for Self-Supervised Visual Pre-Training
We present Masked Frequency Modeling (MFM), a unified frequency-domain-based approach for self-supervised pre-training of visual models.
Point-to-Voxel Knowledge Distillation for LiDAR Semantic Segmentation
This article addresses the problem of distilling knowledge from a large teacher model to a slim student network for LiDAR semantic segmentation.
Ranked #16 on
LIDAR Semantic Segmentation
on nuScenes
Text2Human: Text-Driven Controllable Human Image Generation
In this work, we present a text-driven controllable framework, Text2Human, for a high-quality and diverse human generation.
Delving into High-Quality Synthetic Face Occlusion Segmentation Datasets
This paper performs comprehensive analysis on datasets for occlusion-aware face segmentation, a task that is crucial for many downstream applications.
HuMMan: Multi-Modal 4D Human Dataset for Versatile Sensing and Modeling
4D human sensing and modeling are fundamental tasks in vision and graphics with numerous applications.
StyleGAN-Human: A Data-Centric Odyssey of Human Generation
In addition, a model zoo and human editing applications are demonstrated to facilitate future research in the community.
On the Generalization of BasicVSR++ to Video Deblurring and Denoising
The exploitation of long-term information has been a long-standing problem in video restoration.
Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation
We hope this simple, yet effective method can serve as a new, flexible baseline in unified video segmentation design.
Ranked #11 on
Video Instance Segmentation
on YouTube-VIS validation
Unsupervised Image-to-Image Translation with Generative Prior
In this work, we present a novel framework, Generative Prior-guided UNsupervised Image-to-image Translation (GP-UNIT), to improve the overall quality and applicability of the translation algorithm.
TransEditor: Transformer-Based Dual-Space GAN for Highly Controllable Facial Editing
In this study, we highlight the importance of interaction in a dual-space GAN for more controllable editing.
Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory
With the learned choreographic memory, dance generation is realized on the quantized units that meet high choreography standards, such that the generated dancing sequences are confined within the spatial constraints.
Pastiche Master: Exemplar-Based High-Resolution Portrait Style Transfer
Recent studies on StyleGAN show high performance on artistic portrait generation by transfer learning with limited data.
Open-Vocabulary DETR with Conditional Matching
To this end, we propose a novel open-vocabulary detector based on DETR -- hence the name OV-DETR -- which, once trained, can detect any object given its class name or an exemplar image.
Ranked #10 on
Open Vocabulary Object Detection
on MSCOCO
Dense Siamese Network for Dense Unsupervised Learning
It also extracts a batch of region embeddings that correspond to some sub-regions in the overlapped area to be contrasted for region consistency.
Ranked #1 on
Unsupervised Semantic Segmentation
on COCO-All
Conditional Prompt Learning for Vision-Language Models
With the rise of powerful pre-trained vision-language models like CLIP, it becomes essential to investigate ways to adapt these models to downstream datasets.
Ranked #1 on
Prompt Engineering
on ImageNet V2
LEDNet: Joint Low-light Enhancement and Deblurring in the Dark
With the pipeline, we present the first large-scale dataset for joint low-light enhancement and deblurring.
MoCaNet: Motion Retargeting in-the-wild via Canonicalization Networks
Trained with the canonicalization operations and the derived regularizations, our method learns to factorize a skeleton sequence into three independent semantic subspaces, i. e., motion, structure, and view angle.
Extract Free Dense Labels from CLIP
Contrastive Language-Image Pre-training (CLIP) has made a remarkable breakthrough in open-vocabulary zero-shot image recognition.
Investigating Tradeoffs in Real-World Video Super-Resolution
The diversity and complexity of degradations in real-world video super-resolution (VSR) pose non-trivial challenges in inference and training.
Deceive D: Adaptive Pseudo Augmentation for GAN Training with Limited Data
Generative adversarial networks (GANs) typically require ample data for training in order to synthesize high-fidelity images.
Monocular 3D Reconstruction of Interacting Hands via Collision-Aware Factorized Refinements
In this paper, we make the first attempt to reconstruct 3D interacting hands from monocular single RGB images.
A Shading-Guided Generative Implicit Model for Shape-Accurate 3D-Aware Image Synthesis
Motivated by the observation that a 3D object should look realistic from multiple viewpoints, these methods introduce a multi-view constraint as regularization to learn valid 3D radiance fields from 2D images.
The Nuts and Bolts of Adopting Transformer in GANs
Transformer becomes prevalent in computer vision, especially for high-level vision tasks.
Self-Supervised Representation Learning: Introduction, Advances and Challenges
Self-supervised representation learning methods aim to provide powerful deep feature learning without the requirement of large annotated datasets, thus alleviating the annotation bottleneck that is one of the main barriers to practical deployment of deep learning today.
Playing for 3D Human Recovery
Specifically, we contribute GTA-Human, a large-scale 3D human dataset generated with the GTA-V game engine, featuring a highly diverse set of subjects, actions, and scenarios.
Temporally Consistent Video Colorization with Deep Feature Propagation and Self-regularization Learning
We address this problem from a new perspective, by jointly considering colorization and temporal consistency in a unified framework.
A Comprehensive Overhaul of Distilling Unconditional GANs
To further enhance the semantic consistency between the teacher and student model, we present another latent-direction-based distillation loss that preserves the semantic relations in latent space.
MeshInversion: 3D textured mesh reconstruction with generative prior
Reconstruction is achieved by searching for a latent space in the 3D GAN that best resembles the target mesh in accordance with the single view observation.
SiT: Simulation Transformer for Particle-based Physics Simulation
However, they force particles to interact with all neighbors without selection, and they fall short in capturing material semantics for different particles, leading to unsatisfactory performance, especially in generalization.
ReconfigISP: Reconfigurable Camera Image Processing Pipeline
Image Signal Processor (ISP) is a crucial component in digital cameras that transforms sensor signals into images for us to perceive and understand.
Talk-to-Edit: Fine-Grained Facial Editing via Dialog
In this work, we propose Talk-to-Edit, an interactive facial editing framework that performs fine-grained attribute manipulation through dialog between the user and the system.
Ranked #1 on
Fine-Grained Facial Editing
on CelebA-Dialog
3D Human Texture Estimation from a Single Image with Transformers
We propose a Transformer-based framework for 3D human texture estimation from a single image.
Learning to Prompt for Vision-Language Models
Large pre-trained vision-language models like CLIP have shown great potential in learning representations that are transferable across a wide range of downstream tasks.
K-Net: Towards Unified Image Segmentation
The framework, named K-Net, segments both instances and semantic categories consistently by a group of learnable kernels, where each kernel is responsible for generating a mask for either a potential instance or a stuff class.
Ranked #7 on
Panoptic Segmentation
on COCO test-dev
Unsupervised Object-Level Representation Learning from Scene Images
Extensive experiments on COCO show that ORL significantly improves the performance of self-supervised learning on scene images, even surpassing supervised ImageNet pre-training on several downstream tasks.
Pareidolia Face Reenactment
We present a new application direction named Pareidolia Face Reenactment, which is defined as animating a static illusory face to move in tandem with a human face in the video.
Robust Reference-based Super-Resolution via C2-Matching
However, performing local transfer is difficult because of two gaps between input and reference images: the transformation gap (e. g. scale and rotation) and the resolution gap (e. g. HR and LR).
Semi-Supervised Domain Generalization with Stochastic StyleMatch
We find that the DG methods, which by design are unable to handle unlabeled data, perform poorly with limited labels in SSDG; the SSL methods, especially FixMatch, obtain much better results but are still far away from the basic vanilla model trained using full labels.
Unsupervised 3D Shape Completion through GAN Inversion
In contrast to previous fully supervised approaches, in this paper we present ShapeInversion, which introduces Generative Adversarial Network (GAN) inversion to shape completion for the first time.
BasicVSR++: Improving Video Super-Resolution with Enhanced Propagation and Alignment
We show that by empowering the recurrent framework with the enhanced propagation and alignment, one can exploit spatiotemporal information across misaligned video frames more effectively.
Ranked #1 on
Video Enhancement
on MFQE v2
Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation
While speech content information can be defined by learning the intrinsic synchronization between audio-visual modalities, we identify that a pose code will be complementarily learned in a modulated convolution-based reconstruction framework.
Low-Light Image and Video Enhancement Using Deep Learning: A Survey
Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination.
NTIRE 2021 Challenge on Quality Enhancement of Compressed Video: Methods and Results
This paper reviews the first NTIRE challenge on quality enhancement of compressed video, with a focus on the proposed methods and results.
Removing Diffraction Image Artifacts in Under-Display Camera via Dynamic Skip Connection Network
Recent development of Under-Display Camera (UDC) systems provides a true bezel-less and notch-free viewing experience on smartphones (and TV, laptops, tablets), while allowing images to be captured from the selfie camera embedded underneath.
Audio-Driven Emotional Video Portraits
In this work, we present Emotional Video Portraits (EVP), a system for synthesizing high-quality video portraits with vivid emotional dynamics driven by audios.
Everything's Talkin': Pareidolia Face Reenactment
We present a new application direction named Pareidolia Face Reenactment, which is defined as animating a static illusory face to move in tandem with a human face in the video.
Deep Animation Video Interpolation in the Wild
In the animation industry, cartoon videos are usually produced at low frame rate since hand drawing of such frames is costly and time-consuming.
Domain Generalization: A Survey
Generalization to out-of-distribution (OOD) data is a capability natural to humans yet challenging for machines to reproduce.
Network Pruning via Resource Reallocation
Channel pruning is broadly recognized as an effective approach to obtain a small compact model through eliminating unimportant channels from a large cumbersome network.
Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation
This paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.
FASA: Feature Augmentation and Sampling Adaptation for Long-Tailed Instance Segmentation
We propose a simple yet effective method, Feature Augmentation and Sampling Adaptation (FASA), that addresses the data scarcity issue by augmenting the feature space especially for rare classes.
DeeperForensics Challenge 2020 on Real-World Face Forgery Detection: Methods and Results
This paper reports methods and results in the DeeperForensics Challenge 2020 on real-world face forgery detection.
Chasing the Tail in Monocular 3D Human Reconstruction with Prototype Memory
The reason is that most of the current models perform regression based on a single human prototype, which is similar to common poses while far from the rare poses.
Focal Frequency Loss for Image Reconstruction and Synthesis
In this study, we show that narrowing gaps in the frequency domain can ameliorate image reconstruction and synthesis quality further.
Exploring Data Augmentation for Multi-Modality 3D Object Detection
Due to the fact that multi-modality data augmentation must maintain consistency between point cloud and images, recent methods in this field typically use relatively insufficient data augmentation.
Computation-Efficient Knowledge Distillation via Uncertainty-Aware Mixup
Our goal is to achieve a performance comparable to conventional knowledge distillation with a lower computation cost during training.
Positional Encoding as Spatial Inductive Bias in GANs
In this work, taking SinGAN and StyleGAN2 as examples, we show that such capability, to a large extent, is brought by the implicit positional encoding when using zero padding in the generators.
CARAFE++: Unified Content-Aware ReAssembly of FEatures
Feature reassembly, i. e. feature downsampling and upsampling, is a key operation in a number of modern convolutional network architectures, e. g., residual networks and feature pyramids.
BasicVSR: The Search for Essential Components in Video Super-Resolution and Beyond
Video super-resolution (VSR) approaches tend to have more components than the image counterparts as they need to exploit the additional temporal dimension.
GLEAN: Generative Latent Bank for Large-Factor Image Super-Resolution
We show that pre-trained Generative Adversarial Networks (GANs), e. g., StyleGAN, can be used as a latent bank to improve the restoration quality of large-factor image super-resolution (SR).
Do 2D GANs Know 3D Shape? Unsupervised 3D shape reconstruction from 2D Image GANs
Through our investigation, we found that such a pre-trained GAN indeed contains rich 3D knowledge and thus can be used to recover 3D shape from a single 2D image in an unsupervised manner.
Flexible Piecewise Curves Estimation for Photo Enhancement
This paper presents a new method, called FlexiCurve, for photo enhancement.
Texture Memory-Augmented Deep Patch-Based Image Inpainting
By bringing together the best of both paradigms, we propose a new deep inpainting framework where texture generation is guided by a texture memory of patch samples extracted from unmasked regions.
Understanding Deformable Alignment in Video Super-Resolution
Aside from the contributions to deformable alignment, our formulation inspires a more flexible approach to introduce offset diversity to flow-based alignment, improving its performance.
Delving into Inter-Image Invariance for Unsupervised Visual Representations
In this work, we present a comprehensive empirical study to better understand the role of inter-image invariance learning from three main constituting components: pseudo-label maintenance, sampling strategy, and decision boundary design.
Seesaw Loss for Long-Tailed Instance Segmentation
Instances of head classes dominate a long-tailed dataset and they serve as negative samples of tail categories.
MessyTable: Instance Association in Multiple Camera Views
We present an interesting and challenging dataset that features a large number of scenes with messy tables captured from multiple camera views.
TSIT: A Simple and Versatile Framework for Image-to-Image Translation
We introduce a simple and versatile framework for image-to-image translation.
LiteFlowNet3: Resolving Correspondence Ambiguity for More Accurate Optical Flow Estimation
The keys to success lie in the use of cost volume and coarse-to-fine flow inference.
Ranked #1 on
Scene Flow Estimation
on KITTI 2012
RGB-D Salient Object Detection with Cross-Modality Modulation and Selection
Second, we propose an adaptive feature selection (AFS) module to select saliency-related features and suppress the inferior ones.
Ranked #8 on
RGB-D Salient Object Detection
on NJU2K
Cross-Scale Internal Graph Neural Network for Image Super-Resolution
Specifically, we dynamically construct a cross-scale graph by searching k-nearest neighboring patches in the downsampled LR image for each query patch in the LR image.
Online Deep Clustering for Unsupervised Representation Learning
In this way, labels and the network evolve shoulder-to-shoulder rather than alternatingly.
Knowledge Distillation Meets Self-Supervision
Knowledge distillation, which involves extracting the "dark knowledge" from a teacher network to guide the learning of a student network, has emerged as an important technique for model compression and transfer learning.
Ranked #14 on
Knowledge Distillation
on ImageNet
Inter-Region Affinity Distillation for Road Marking Segmentation
We study the problem of distilling knowledge from a large deep teacher network to a much smaller student network for the task of road marking segmentation.
Ranked #1 on
Semantic Segmentation
on ApolloScape
Feature Pyramid Grids
Feature pyramid networks have been widely adopted in the object detection literature to improve feature representations for better handling of variations in scale.
Self-Supervised Scene De-occlusion
This is achieved via Partial Completion Network (PCNet)-mask (M) and -content (C), that learn to recover fractions of object masks and contents, respectively, in a self-supervised manner.
Learning to Cluster Faces via Confidence and Connectivity Estimation
With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters.
TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting
We present a lightweight video motion retargeting approach TransMoMo that is capable of transferring motion of a person in a source video realistically to another video of a target person.
Exploiting Deep Generative Prior for Versatile Image Restoration and Manipulation
Learning a good image prior is a long-term goal for image restoration and manipulation.
1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.
Residual Knowledge Distillation
Knowledge distillation (KD) is one of the most potent ways for model compression.
Real or Not Real, that is the Question
While generative adversarial networks (GAN) have been widely adopted in various topics, in this paper we generalize the standard GAN to a new perspective by treating realness as a random variable that can be estimated from multiple angles.
Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement
The paper presents a novel method, Zero-Reference Deep Curve Estimation (Zero-DCE), which formulates light enhancement as a task of image-specific curve estimation with a deep network.
Ranked #1 on
Low-Light Image Enhancement
on NPE
(User Study Score metric)
Everybody's Talkin': Let Me Talk as You Want
The audio-translated expression parameters are then used to synthesize a photo-realistic human subject in each video frame, with the movement of the mouth regions precisely mapped to the source audio.
DeeperForensics-1.0: A Large-Scale Dataset for Real-World Face Forgery Detection
The quality of generated videos outperforms those in existing datasets, validated by user studies.
EcoNAS: Finding Proxies for Economical Neural Architecture Search
While many methods have been proposed to improve the efficiency of NAS, the search progress is still laborious because training and evaluating plausible architectures over large search space is time-consuming.
Side-Aware Boundary Localization for More Precise Object Detection
To tackle the difficulty of precise localization in the presence of displacements with large variance, we further propose a two-step localization scheme, which first predicts a range of movement through bucket prediction and then pinpoints the precise position within the predicted bucket.
Learning to Synthesize Fashion Textures
Another important observation is that fashion textures are multi-modal.
Robust Multi-Modality Multi-Object Tracking
Multi-sensor perception is crucial to ensure the reliability and accuracy in autonomous driving system, while multi-object tracking (MOT) improves that by tracing sequential movement of dynamic objects.
Ranked #9 on
Multiple Object Tracking
on KITTI Tracking test
Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild
Specifically, we focus on the challenging task of in-the-wild 3D human recovery from single images when paired 3D annotations are not fully available.
One-shot Face Reenactment
However, in real-world scenario end-users often only have one target face at hand, rendering existing methods inapplicable.
Learning Lightweight Lane Detection CNNs by Self Attention Distillation
Training deep models for lane detection is challenging due to the very subtle and sparse supervisory signals inherent in lane annotations.
Ranked #4 on
Lane Detection
on BDD100K val
MMDetection: Open MMLab Detection Toolbox and Benchmark
In this paper, we introduce the various features of this toolbox.
Disentangling Content and Style via Unsupervised Geometry Distillation
It is challenging to disentangle an object into two orthogonal spaces of content and style since each can influence the visual observation differently and unpredictably.
Deep Flow-Guided Video Inpainting
Then the synthesized flow field is used to guide the propagation of pixels to fill up the missing regions in the video.
Ranked #7 on
Video Inpainting
on DAVIS
One-shot visual object segmentation
Optical Flow Estimation
+2
EDVR: Video Restoration with Enhanced Deformable Convolutional Networks
In this work, we propose a novel Video Restoration framework with Enhanced Deformable networks, termed EDVR, to address these challenges.
Ranked #2 on
Deblurring
on REDS
CARAFE: Content-Aware ReAssembly of FEatures
CARAFE introduces little computational overhead and can be readily integrated into modern network architectures.
Path-Restore: Learning Network Path Selection for Image Restoration
To leverage this, we propose Path-Restore, a multi-path CNN with a pathfinder that can dynamically select an appropriate route for each image region.
TransGaGa: Geometry-Aware Unsupervised Image-to-Image Translation
Extensive experiments demonstrate the superior performance of our method to other state-of-the-art approaches, especially in the challenging near-rigid and non-rigid objects translation tasks.
Prime Sample Attention in Object Detection
Our experiments demonstrate that it is often more effective to focus on prime samples than hard samples when training a detector.
Learning to Cluster Faces on an Affinity Graph
Face recognition sees remarkable progress in recent years, and its performance has reached a very high level.
Self-Supervised Learning via Conditional Motion Propagation
Instead of explicitly modeling the motion probabilities, we design the pretext task as a conditional motion propagation problem.
Dense Intrinsic Appearance Flow for Human Pose Transfer
Unlike existing methods, we propose to estimate dense and intrinsic 3D appearance flow to better guide the transfer of pixels between poses.
A Lightweight Optical Flow CNN -- Revisiting Data Fidelity and Regularization
Over four decades, the majority addresses the problem of optical flow estimation using variational methods.
Ranked #3 on
Optical Flow Estimation
on KITTI 2012
Unsupervised Bi-directional Flow-based Video Generation from one Snapshot
Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions.
WIDER Face and Pedestrian Challenge 2018: Methods and Results
This paper presents a review of the 2018 WIDER Challenge on Face and Pedestrian.
Hybrid Task Cascade for Instance Segmentation
In exploring a more effective approach, we find that the key to a successful instance segmentation cascade is to fully leverage the reciprocal relationship between detection and segmentation.
Ranked #25 on
Object Detection
on COCO test-dev
Region Proposal by Guided Anchoring
State-of-the-art detectors mostly rely on a dense anchoring scheme, where anchors are sampled uniformly over the spatial domain with a predefined set of scales and aspect ratios.
Ranked #1 on
Region Proposal
on COCO test-dev
An Embarrassingly Simple Approach for Knowledge Distillation
Knowledge Distillation (KD) aims at improving the performance of a low-capacity student model by inheriting knowledge from a high-capacity teacher model.
Instance-level Facial Attributes Transfer with Geometry-Aware Flow
Geometry-aware flow is able to warp the source face attribute into the target face context and generate a warp-and-blend result.
Deep Network Interpolation for Continuous Imagery Effect Transition
Deep convolutional neural network has demonstrated its capability of learning a deterministic mapping for the desired imagery effect.
Learning to Steer by Mimicking Features from Heterogeneous Auxiliary Networks
In this paper, we considerably improve the accuracy and robustness of predictions through heterogeneous auxiliary networks feature mimicking, a new and effective training method that provides us with much richer contextual signals apart from steering direction.
Ranked #1 on
Steering Control
on BDD100K val
Unsupervised Disentangling Structure and Appearance
It is challenging to disentangle an object into two orthogonal spaces of structure and appearance since each can influence the visual observation in a different and unpredictable way.