Search Results for author:
Found 451 papers, 226 papers with code
Fixing Localization Errors to Improve Image Classification
This way, in an effort to fix localization errors, our loss provides an extra supervisory signal that helps the model to better discriminate between similar classes.
Modeling the Effects of Windshield Refraction for Camera Calibration
Instead of using a generalized camera approach, we propose a novel approach to jointly optimize a traditional camera model, and a mathematical representation of the windshield’s surface.
Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration
Deep point cloud registration methods face challenges to partial overlaps and rely on labeled data.
NeRF-GAN Distillation for Efficient 3D-Aware Generation with Convolutions
Pose-conditioned convolutional generative models struggle with high-quality 3D-consistent image generation from single-view datasets, due to their lack of sufficient 3D priors.
Lidar Line Selection with Spatially-Aware Shapley Value for Cost-Efficient Depth Completion
Lidar is a vital sensor for estimating the depth of a scene.
DiffIR: Efficient Diffusion Model for Image Restoration
Since the iterations are few, our DiffIR can adopt a joint optimization of CPEN$_{S2}$, DIRformer, and denoising network, which can further reduce the estimation error influence.
Spherical Space Feature Decomposition for Guided Depth Map Super-Resolution
Then, the extracted features are mapped to the spherical space to complete the separation of private features and the alignment of shared features.
Graph Transformer GANs for Graph-Constrained House Generation
We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations in an end-to-end fashion for the challenging graph-constrained house generation task.
DDFM: Denoising Diffusion Model for Multi-Modality Image Fusion
To leverage strong generative priors and address challenges such as unstable training and lack of interpretability for GAN-based generative methods, we propose a novel fusion algorithm based on the denoising diffusion probabilistic model (DDPM).
Contrastive Model Adaptation for Cross-Condition Robustness in Semantic Segmentation
We investigate normal-to-adverse condition model adaptation for semantic segmentation, whereby image-level correspondences are available in the target domain.
A Multiplicative Value Function for Safe and Efficient Reinforcement Learning
To this end, we propose a safe model-free RL algorithm with a novel multiplicative value function consisting of a safety critic and a reward critic.
TrafficBots: Towards World Models for Autonomous Driving Simulation and Motion Prediction
We present TrafficBots, a multi-agent policy built upon motion prediction and end-to-end driving, and based on TrafficBots we obtain a world model tailored for the planning module of autonomous vehicles.
Efficient and Explicit Modelling of Image Hierarchies for Image Restoration
The aim of this paper is to propose a mechanism to efficiently and explicitly model image hierarchies in the global, regional, and local range for image restoration.
VA-DepthNet: A Variational Approach to Single Image Depth Prediction
While state-of-the-art deep neural network methods for SIDP learn the scene depth from images in a supervised setting, they often overlook the invaluable invariances and priors in the rigid scene space, such as the regularity of the scene.
Summarize the Past to Predict the Future: Natural Language Descriptions of Context Boost Multimodal Object Interaction
This action context together with the next video frame is processed by the multimodal fusion module to forecast the next object interaction.
Event-Based Frame Interpolation with Ad-hoc Deblurring
The performance of video frame interpolation is inherently correlated with the ability to handle motion in the input scene.
Beyond SOT: It's Time to Track Multiple Generic Objects at Once
TaMOs achieves a 4x faster run-time in case of 10 concurrent objects compared to tracking each object independently and outperforms existing single object trackers on our new benchmark.
One-Shot Domain Adaptive and Generalizable Semantic Segmentation with Class-Aware Cross-Domain Transformers
Thus, we aim to relieve this need on a large number of real data, and explore the one-shot unsupervised sim-to-real domain adaptation (OSUDA) and generalization (OSDG) problem, where only one real-world data sample is available.
CamoFormer: Masked Separable Attention for Camouflaged Object Detection
How to identify and segment camouflaged objects from the background is challenging.
Source-free Depth for Object Pop-out
In this work, we adapt such depth inference models for object segmentation using the objects' ``pop-out'' prior in 3D.
CiaoSR: Continuous Implicit Attention-in-Attention Network for Arbitrary-Scale Image Super-Resolution
The effectiveness of the method is also demonstrated on the real-world SR setting.
I2MVFormer: Large Language Model Generated Multi-View Document Supervision for Zero-Shot Image Classification
Our proposed model, I2MVFormer, learns multi-view semantic embeddings for zero-shot image classification with these class views.
MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation
MIC significantly improves the state-of-the-art performance across the different recognition tasks for synthetic-to-real, day-to-nighttime, and clear-to-adverse-weather UDA.
Neural Radiance Fields for Manhattan Scenes with Unknown Manhattan Frame
Such representations are known to benefit from additional geometric and semantic supervision.
Knowledge Distillation based Degradation Estimation for Blind Super-Resolution
It consists of a knowledge distillation based implicit degradation estimator network (KD-IDE) and an efficient SR network.
CDDFuse: Correlation-Driven Dual-Branch Feature Decomposition for Multi-Modality Image Fusion
In the second stage, the LT-based global fusion and INN-based local fusion layers output the fused image.
DiffDreamer: Towards Consistent Unsupervised Single-view Scene Extrapolation with Conditional Diffusion Models
Scene extrapolation -- the idea of generating novel views by flying into a given image -- is a promising, yet challenging task.
Ranked #1 on
Perpetual View Generation
on LHQ
Piecewise Planar Hulls for Semi-Supervised Learning of 3D Shape and Pose from 2D Images
On the one hand, the proposed method learns to segment these planar hulls from the labeled data.
Advancing Learned Video Compression with In-loop Frame Prediction
In this paper, we propose an Advanced Learned Video Compression (ALVC) approach with the in-loop frame prediction module, which is able to effectively predict the target frame from the previously compressed frames, without consuming any bit-rate.
MicroISP: Processing 32MP Photos on Mobile Devices with Deep Learning
While neural networks-based photo processing solutions can provide a better image quality compared to the traditional ISP systems, their application to mobile devices is still very limited due to their very high computational complexity.
PyNet-V2 Mobile: Efficient On-Device Photo Processing With Neural Networks
The increased importance of mobile photography created a need for fast and performant RAW image processing pipelines capable of producing good visual results in spite of the mobile camera sensor limitations.
Towards Versatile Embodied Navigation
With the emergence of varied visual navigation tasks (e. g, image-/object-/audio-goal and vision-language navigation) that specify the target in different ways, the community has made appealing advances in training specialized agents capable of handling individual navigation tasks well.
TripletTrack: 3D Object Tracking using Triplet Embeddings and LSTM
We start from an off-the-shelf 3D object detector, and apply a tracking mechanism where objects are matched by an affinity score computed on local object feature embeddings and motion descriptors.
Masked Vision-Language Transformer in Fashion
We present a masked vision-language transformer (MVLT) for fashion-specific multi-modal representation.
Learning Attention Propagation for Compositional Zero-Shot Learning
CAPE learns to identify this structure and propagates knowledge between them to learn class embedding for all seen and unseen compositions.
Multi-View Photometric Stereo Revisited
The proposed approach in this paper exploits the benefit of uncertainty modeling in a deep neural network for a reliable fusion of photometric stereo (PS) and multi-view stereo (MVS) network predictions.
Composite Learning for Robust and Effective Dense Predictions
In this paper, we find that jointly training a dense prediction (target) task with a self-supervised (auxiliary) task can consistently improve the performance of the target task, while eliminating the need for labeling auxiliary tasks.
Ranked #64 on
Semantic Segmentation
on NYU Depth v2
SiNeRF: Sinusoidal Neural Radiance Fields for Joint Pose Estimation and Scene Reconstruction
NeRFmm is the Neural Radiance Fields (NeRF) that deal with Joint Optimization tasks, i. e., reconstructing real-world scenes and registering camera parameters simultaneously.
Robustifying the Multi-Scale Representation of Neural Radiance Fields
Although recently proposed Mip-NeRF could handle multi-scale imaging problems with NeRF, it cannot handle camera pose estimation error.
Basic Binary Convolution Unit for Binarized Image Restoration Network
In this study, we reconsider components in binary convolution, such as residual connection, BatchNorm, activation function, and structure, for IR tasks.
TT-NF: Tensor Train Neural Fields
Learning neural fields has been an active topic in deep learning research, focusing, among other issues, on finding more compact and easy-to-fit representations.
Exploiting Instance-based Mixed Sampling via Auxiliary Source Domain Supervision for Domain-adaptive Action Detection
We propose a novel domain adaptive action detection approach and a new adaptation protocol that leverages the recent advancements in image-level unsupervised domain adaptation (UDA) techniques and handle vagaries of instance-level video data.
I2DFormer: Learning Image to Document Attention for Zero-Shot Image Classification
In order to distill discriminative visual words from noisy documents, we introduce a new cross-modal attention module that learns fine-grained interactions between image patches and document words.
Spatio-Temporal Action Detection Under Large Motion
Current methods for spatiotemporal action tube detection often extend a bounding box proposal at a given keyframe into a 3D temporal cuboid and pool features from nearby frames.
Learning Task-Oriented Flows to Mutually Guide Feature Alignment in Synthesized and Real Video Denoising
To this end, we propose a new multi-scale refined optical flow-guided video denoising method, which is more robust to different noise levels.
Ranked #1 on
Video Denoising
on VideoLQ
ManiFlow: Implicitly Representing Manifolds with Normalizing Flows
In contrast to prior work, we approach this problem by generating samples from the original data distribution given full knowledge about the perturbed distribution and the noise model.
AVisT: A Benchmark for Visual Object Tracking in Adverse Visibility
While being greatly benefiting to the tracking research, existing benchmarks do not pose the same difficulty as before with recent trackers achieving higher performance mainly due to (i) the introduction of more sophisticated transformers-based methods and (ii) the lack of diverse scenarios with adverse visibility such as, severe weather conditions, camouflage and imaging effects.
Reference-based Image Super-Resolution with Deformable Attention Transformer
Reference-based image super-resolution (RefSR) aims to exploit auxiliary reference (Ref) images to super-resolve low-resolution (LR) images.
Towards Interpretable Video Super-Resolution via Alternating Optimization
These issues can be alleviated by a cascade of three separate sub-tasks, including video deblurring, frame interpolation, and super-resolution, which, however, would fail to capture the spatial and temporal correlations among video sequences.
Mining Relations among Cross-Frame Affinities for Video Semantic Segmentation
The essence of video semantic segmentation (VSS) is how to leverage temporal information for prediction.
Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditions
Due to the scarcity of dense pixel-level semantic annotations for images recorded in adverse visual conditions, there has been a keen interest in unsupervised domain adaptation (UDA) for the semantic segmentation of such images.
Ranked #1 on
Semantic Segmentation
on Nighttime Driving
Organic Priors in Non-Rigid Structure from Motion
Besides that, the paper provides insights into the NRSfM factorization -- both in terms of shape and motion -- and is the first approach to show the benefit of single rotation averaging for NRSfM.
OSFormer: One-Stage Camouflaged Instance Segmentation with Transformers
We present OSFormer, the first one-stage transformer framework for camouflaged instance segmentation (CIS).
L2E: Lasers to Events for 6-DoF Extrinsic Calibration of Lidars and Event Cameras
As neuromorphic technology is maturing, its application to robotics and autonomous vehicle systems has become an area of active research.
HRFuser: A Multi-resolution Sensor Fusion Architecture for 2D Object Detection
Besides standard cameras, autonomous vehicles typically include multiple additional sensors, such as lidars and radars, which help acquire richer information for perceiving the content of the driving scene.
Ranked #1 on
2D object detection
on Clear Weather
3D-Aware Video Generation
Generative models have emerged as an essential building block for many image synthesis and editing tasks.
SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation
Adapting to a continuously evolving environment is a safety-critical challenge inevitably faced by all autonomous driving systems.
Structured Sparsity Learning for Efficient Video Super-Resolution
In SSL, we design pruning schemes for several key components in VSR models, including residual blocks, recurrent networks, and upsampling networks.
Discovering Object Masks with Transformers for Unsupervised Semantic Segmentation
This paper presents MaskDistill: a novel framework for unsupervised semantic segmentation based on three key ideas.
Ranked #2 on
Unsupervised Semantic Segmentation
on PASCAL VOC 2012 val
(using extra training data)
Recurrent Video Restoration Transformer with Guided Deformable Attention
Specifically, RVRT divides the video into multiple clips and uses the previously inferred clip feature to estimate the subsequent clip feature.
Ranked #1 on
Deblurring
on DVD
Gradient Obfuscation Checklist Test Gives a False Sense of Security
It has since become a trend to use these five characteristics as a sufficient test, to determine whether or not gradient obfuscation is the main source of robustness.
GCoNet+: A Stronger Group Collaborative Co-Salient Object Detector
In this paper, we present a novel end-to-end group collaborative learning network, termed GCoNet+, which can effectively and efficiently (250 fps) identify co-salient objects in natural scenes.
Ranked #1 on
Co-Salient Object Detection
on CoSal2015
Deep Gradient Learning for Efficient Camouflaged Object Detection
This paper introduces DGNet, a novel deep framework that exploits object gradient supervision for camouflaged object detection (COD).
Unsupervised Flow-Aligned Sequence-to-Sequence Learning for Video Restoration
On the other hand, we equip the sequence-to-sequence model with an unsupervised optical flow estimator to maximize its potential.
Ranked #2 on
Video Enhancement
on MFQE v2
Degradation-Aware Unfolding Half-Shuffle Transformer for Spectral Compressive Imaging
In coded aperture snapshot spectral compressive imaging (CASSI) systems, hyperspectral image (HSI) reconstruction methods are employed to recover the spatial-spectral signal from a compressed measurement.
A Continual Deepfake Detection Benchmark: Dataset, Methods, and Essentials
Within the proposed benchmark, we explore some commonly known essentials of standard continual learning.
Revisiting Random Channel Pruning for Neural Network Compression
The proposed approach provides a new way to compare different methods, namely how well they behave compared with random pruning.
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.
HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation
Therefore, we propose HRDA, a multi-resolution training approach for UDA, that combines the strengths of small high-resolution crops to preserve fine segmentation details and large low-resolution crops to capture long-range context dependencies with a learned scale attention, while maintaining a manageable GPU memory footprint.
MST++: Multi-stage Spectral-wise Transformer for Efficient Spectral Reconstruction
Existing leading methods for spectral reconstruction (SR) focus on designing deeper or wider convolutional neural networks (CNNs) to learn the end-to-end mapping from the RGB image to its hyperspectral image (HSI).
Neural Vector Fields for Implicit Surface Representation and Inference
Implicit fields have been very effective to represent and learn 3D shapes accurately.
Coarse-to-Fine Feature Mining for Video Semantic Segmentation
To address this problem, we propose a Coarse-to-Fine Feature Mining (CFFM) technique to learn a unified presentation of static contexts and motional contexts.
Learning Online Multi-Sensor Depth Fusion
Multi-sensor depth fusion is able to substantially improve the robustness and accuracy of 3D reconstruction methods, but existing techniques are not robust enough to handle sensors which operate with diverse value ranges as well as noise and outlier statistics.
Deep Interactive Motion Prediction and Planning: Playing Games with Motion Prediction Models
Fundamental to the success of our method is the design of a novel multi-agent policy network that can steer a vehicle given the state of the surrounding agents and the map information.
Arbitrary-Scale Image Synthesis
Positional encodings have enabled recent works to train a single adversarial network that can generate images of different scales.
P3Depth: Monocular Depth Estimation with a Piecewise Planarity Prior
We focus on the supervised setup, in which ground-truth depth is available only at training time.
Ranked #4 on
Depth Estimation
on NYU-Depth V2
FoV-Net: Field-of-View Extrapolation Using Self-Attention and Uncertainty
The ability to make educated predictions about their surroundings, and associate them with certain confidence, is important for intelligent systems, like autonomous vehicles and robots.
Direct Dense Pose Estimation
In addition, DDP is computationally more efficient than previous dense pose estimation methods, and it reduces jitters when applied to a video sequence, which is a problem plaguing the previous methods.
Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation
Since the rise of vision-language navigation (VLN), great progress has been made in instruction following -- building a follower to navigate environments under the guidance of instructions.
LiDAR Snowfall Simulation for Robust 3D Object Detection
Due to the difficulty of collecting and annotating training data in this setting, we propose a physically based method to simulate the effect of snowfall on real clear-weather LiDAR point clouds.
Ranked #1 on
3D Object Detection
on Heavy Snowfall
Rethinking Semantic Segmentation: A Prototype View
Prevalent semantic segmentation solutions, despite their different network designs (FCN based or attention based) and mask decoding strategies (parametric softmax based or pixel-query based), can be placed in one category, by considering the softmax weights or query vectors as learnable class prototypes.
Video Polyp Segmentation: A Deep Learning Perspective
We present the first comprehensive video polyp segmentation (VPS) study in the deep learning era.
Ranked #1 on
Video Polyp Segmentation
on SUN-SEG-Easy (Unseen)
Continual Test-Time Domain Adaptation
However, real-world machine perception systems are running in non-stationary and continually changing environments where the target domain distribution can change over time.
Spatially Multi-conditional Image Generation
However, multi-conditional image generation is a very challenging problem due to the heterogeneity and the sparsity of the (in practice) available conditioning labels.
Practical Blind Denoising via Swin-Conv-UNet and Data Synthesis
While recent years have witnessed a dramatic upsurge of exploiting deep neural networks toward solving image denoising, existing methods mostly rely on simple noise assumptions, such as additive white Gaussian noise (AWGN), JPEG compression noise and camera sensor noise, and a general-purpose blind denoising method for real images remains unsolved.
Robust Visual Tracking by Segmentation
We infer a bounding box from the segmentation mask, validate our tracker on challenging tracking datasets and achieve the new state of the art on LaSOT with a success AUC score of 69. 7%.
Transforming Model Prediction for Tracking
Optimization based tracking methods have been widely successful by integrating a target model prediction module, providing effective global reasoning by minimizing an objective function.
Ranked #1 on
Visual Object Tracking
on LaSOT
(IS metric)
Transform your Smartphone into a DSLR Camera: Learning the ISP in the Wild
We propose a trainable Image Signal Processing (ISP) framework that produces DSLR quality images given RAW images captured by a smartphone.
Zero Pixel Directional Boundary by Vector Transform
One of the key problems in boundary detection is the label representation, which typically leads to class imbalance and, as a consequence, to thick boundaries that require non-differential post-processing steps to be thinned.
Scribble-Supervised LiDAR Semantic Segmentation
Densely annotating LiDAR point clouds remains too expensive and time-consuming to keep up with the ever growing volume of data.
Ranked #1 on
3D Semantic Segmentation
on ScribbleKITTI
Revisiting Deep Semi-supervised Learning: An Empirical Distribution Alignment Framework and Its Generalization Bound
Benefited from this new perspective, we first propose a new deep semi-supervised learning framework called Semi-supervised Learning by Empirical Distribution Alignment (SLEDA), in which existing technologies from the domain adaptation community can be readily used to address the semi-supervised learning problem through reducing the empirical distribution distance between labeled and unlabeled data.
Coarse-to-Fine Sparse Transformer for Hyperspectral Image Reconstruction
Many algorithms have been developed to solve the inverse problem of coded aperture snapshot spectral imaging (CASSI), i. e., recovering the 3D hyperspectral images (HSIs) from a 2D compressive measurement.
Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences
We propose Probabilistic Warp Consistency, a weakly-supervised learning objective for semantic matching.
ZippyPoint: Fast Interest Point Detection, Description, and Matching through Mixed Precision Discretization
Efficient detection and description of geometric regions in images is a prerequisite in visual systems for localization and mapping.
Barlow constrained optimization for Visual Question Answering
In this paper, we propose a novel regularization for VQA models, Constrained Optimization using Barlow's theory (COB), that improves the information content of the joint space by minimizing the redundancy.
HDNet: High-resolution Dual-domain Learning for Spectral Compressive Imaging
On the one hand, the proposed HR spatial-spectral attention module with its efficient feature fusion provides continuous and fine pixel-level features.
Pix2NeRF: Unsupervised Conditional $π$-GAN for Single Image to Neural Radiance Fields Translation
We propose a pipeline to generate Neural Radiance Fields~(NeRF) of an object or a scene of a specific class, conditioned on a single input image.
Uncertainty-Aware Deep Multi-View Photometric Stereo
At each pixel, our approach either selects or discards deep-PS and deep-MVS network prediction depending on the prediction uncertainty measure.
Adiabatic Quantum Computing for Multi Object Tracking
Multi-Object Tracking (MOT) is most often approached in the tracking-by-detection paradigm, where object detections are associated through time.
Fast Online Video Super-Resolution with Deformable Attention Pyramid
Our DAP aligns and integrates information from the recurrent state into the current frame prediction.
VRT: A Video Restoration Transformer
Besides, parallel warping is used to further fuse information from neighboring frames by parallel feature warping.
Ranked #1 on
Deblurring
on BASED
Revisiting RCAN: Improved Training for Image Super-Resolution
Image super-resolution (SR) is a fast-moving field with novel architectures attracting the spotlight.
RePaint: Inpainting using Denoising Diffusion Probabilistic Models
In this work, we propose RePaint: A Denoising Diffusion Probabilistic Model (DDPM) based inpainting approach that is applicable to even extreme masks.
Collapse by Conditioning: Training Class-conditional GANs with Limited Data
On the contrary, we observe that class-conditioning causes mode collapse in limited data settings, where unconditional learning leads to satisfactory generative ability.
End-To-End Optimization of LiDAR Beam Configuration for 3D Object Detection and Localization
In this work, we take a new route to learn to optimize the LiDAR beam configuration for a given application.
Flow-Guided Sparse Transformer for Video Deblurring
Exploiting similar and sharper scene patches in spatio-temporal neighborhoods is critical for video deblurring.
Ranked #1 on
Deblurring
on DVD
Sound and Visual Representation Learning with Multiple Pretraining Tasks
Specifically, for this study, we investigate binaural sounds and image data in isolation.
Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields Translation
We propose a pipeline to generate Neural Radiance Fields (NeRF) of an object or a scene of a specific class, conditioned on a single input image.
Facial-Sketch Synthesis: A New Challenge
Besides, we elaborate comprehensive experiments on the existing 19 cutting-edge models.
Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layers
We use linear layers with token-consistent stochastic parameters inside the multilayer perceptron blocks, without altering the architecture of the transformer.
End-to-End Learning of Multi-category 3D Pose and Shape Estimation
We use a Transformer-based architecture to detect the keypoints, as well as to summarize the visual context of the image.
Topology Preserving Local Road Network Estimation from Single Onboard Camera Image
We represent the road topology using a set of directed lane curves and their interactions, which are captured using their intersection points.
Efficient Visual Tracking with Exemplar Transformers
E. T. Track, our visual tracker that incorporates Exemplar Transformer modules, runs at 47 FPS on a CPU.
Implicit Neural Representations for Image Compression
Recently Implicit Neural Representations (INRs) gained attention as a novel and effective representation for various data types.
Event-Based Fusion for Motion Deblurring with Cross-modal Attention
Traditional frame-based cameras inevitably suffer from motion blur due to long exposure times.
Ranked #1 on
Deblurring
on GoPro
(using extra training data)
3D Compositional Zero-shot Learning with DeCompositional Consensus
Parts represent a basic unit of geometric and semantic similarity across different objects.
DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation
It improves the state of the art by 10. 8 mIoU for GTA-to-Cityscapes and 5. 4 mIoU for Synthia-to-Cityscapes and enables learning even difficult classes such as train, bus, and truck well.
Ranked #5 on
Domain Adaptation
on Cityscapes to ACDC
Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model
We propose a novel framework, i. e., Predict, Prevent, and Evaluate (PPE), for disentangled text-driven image manipulation that requires little manual annotation while being applicable to a wide variety of manipulations.
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation
Estimating 3D human poses from monocular videos is a challenging task due to depth ambiguity and self-occlusion.
Ranked #8 on
3D Human Pose Estimation
on MPI-INF-3DHP
Global and Local Alignment Networks for Unpaired Image-to-Image Translation
The global alignment network aims to transfer the input image from the source domain to the target domain.
Mask-guided Spectral-wise Transformer for Efficient Hyperspectral Image Reconstruction
The HSI representations are highly similar and correlated across the spectral dimension.
Normalizing Flow as a Flexible Fidelity Objective for Photo-Realistic Super-resolution
Super-resolution is an ill-posed problem, where a ground-truth high-resolution image represents only one possibility in the space of plausible solutions.
Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo
Our method performs neural rendering of multi-view images while utilizing surface normals estimated by a deep photometric stereo network.
Neural Architecture Search for Efficient Uncalibrated Deep Photometric Stereo
We then perform a continuous relaxation of this search space and present a gradient-based optimization strategy to find an efficient light calibration and normal estimation network.
Structured Bird's-Eye-View Traffic Scene Understanding from Onboard Images
In this work, we study the problem of extracting a directed graph representing the local road network in BEV coordinates, from a single onboard camera image.
MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation
We surpass camera independent methods on the challenging KITTI3D benchmark and show the key benefits compared to camera dependent methods.
PDC-Net+: Enhanced Probabilistic Dense Correspondence Network
In order to apply dense methods to real-world applications, such as pose estimation, image manipulation, or 3D reconstruction, it is therefore crucial to estimate the confidence of the predicted matches.
Context-aware Padding for Semantic Segmentation
Zero padding is widely used in convolutional neural networks to prevent the size of feature maps diminishing too fast.
TACS: Taxonomy Adaptive Cross-Domain Semantic Segmentation
In many real-world settings, the target domain task requires a different taxonomy than the one imposed by the source domain.
Perceptual Learned Video Compression with Recurrent Conditional GAN
This paper proposes a Perceptual Learned Video Compression (PLVC) approach with recurrent conditional GAN.
Binaural SoundNet: Predicting Semantics, Depth and Motion with Binaural Sounds
Humans can robustly recognize and localize objects by using visual and/or auditory cues.
Improving Semi-Supervised and Domain-Adaptive Semantic Segmentation with Self-Supervised Depth Estimation
Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process.
Generalized Real-World Super-Resolution through Adversarial Robustness
Instead of learning a dataset-specific degradation, we employ adversarial attacks to create difficult examples that target the model's weaknesses.
SwinIR: Image Restoration Using Swin Transformer
In particular, the deep feature extraction module is composed of several residual Swin Transformer blocks (RSTB), each of which has several Swin Transformer layers together with a residual connection.
Ranked #2 on
Color Image Denoising
on urban100 sigma15
Deep Reparametrization of Multi-Frame Super-Resolution and Denoising
The deep reparametrization allows us to directly model the image formation process in the latent space, and to integrate learned image priors into the prediction.
Ranked #4 on
Burst Image Super-Resolution
on BurstSR
End-to-End Urban Driving by Imitating a Reinforcement Learning Coach
Our end-to-end agent achieves a 78% success rate while generalizing to a new town and new weather on the NoCrash-dense benchmark and state-of-the-art performance on the challenging public routes of the CARLA LeaderBoard.
Decoder Fusion RNN: Context and Interaction Aware Decoders for Trajectory Prediction
Forecasting the future behavior of all traffic agents in the vicinity is a key task to achieve safe and reliable autonomous driving systems.
Fog Simulation on Real LiDAR Point Clouds for 3D Object Detection in Adverse Weather
2) Through extensive experiments with several state-of-the-art detection approaches, we show that our fog simulation can be leveraged to significantly improve the performance for 3D object detection in the presence of fog.
Ranked #1 on
3D Object Detection
on Dense Fog
Mutual Affine Network for Spatially Variant Kernel Estimation in Blind Image Super-Resolution
Extensive experiments on synthetic and real images show that the proposed MANet not only performs favorably for both spatially variant and invariant kernel estimation, but also leads to state-of-the-art blind SR performance when combined with non-blind SR methods.
A Real-Time Online Learning Framework for Joint 3D Reconstruction and Semantic Segmentation of Indoor Scenes
This paper presents a real-time online vision framework to jointly recover an indoor scene's 3D structure and semantic label.
Hierarchical Conditional Flow: A Unified Framework for Image Super-Resolution and Image Rescaling
More specifically, HCFlow learns a bijective mapping between HR and LR image pairs by modelling the distribution of the LR image and the rest high-frequency component simultaneously.
Boosting Few-shot Semantic Segmentation with Transformers
Due to the fact that fully supervised semantic segmentation methods require sufficient fully-labeled data to work well and can not generalize to unseen classes, few-shot segmentation has attracted lots of research attention.
A Survey on Deep Learning Technique for Video Segmentation
Video segmentation -- partitioning video frames into multiple segments or objects -- plays a critical role in a broad range of practical applications, from enhancing visual effects in movie, to understanding scenes in autonomous driving, to creating virtual background in video conferencing.
On the Practicality of Deterministic Epistemic Uncertainty
We find that, while DUMs scale to realistic vision tasks and perform well on OOD detection, the practicality of current methods is undermined by poor calibration under distributional shifts.
GANmut: Learning Interpretable Conditional Space for Gamut of Emotions
On the other hand, learning from inexpensive and intuitive basic categorical emotion labels leads to limited emotion variability.
Video Super-Resolution Transformer
Specifically, to tackle the first issue, we present a spatial-temporal convolutional self-attention layer with a theoretical understanding to exploit the locality information.
Revisiting Contrastive Methods for Unsupervised Learning of Visual Representations
Contrastive self-supervised learning has outperformed supervised pretraining on many downstream tasks like segmentation and object detection.
Generative Flows with Invertible Attentions
The key idea is to exploit a masked scheme of these two attentions to learn long-range data dependencies in the context of generative flows.
Go with the Flows: Mixtures of Normalizing Flows for Point Cloud Generation and Reconstruction
Recently normalizing flows (NFs) have demonstrated state-of-the-art performance on modeling 3D point clouds while allowing sampling with arbitrary resolution at inference time.
Vision Transformers with Hierarchical Attention
This paper tackles the low-efficiency flaw of the vision transformer caused by the high computational/space complexity in Multi-Head Self-Attention (MHSA).
Fourier Space Losses for Efficient Perceptual Image Super-Resolution
As large models are often not practical in real-world applications, we investigate and propose novel loss functions, to enable SR with high perceptual quality from much more efficient models.
Boosting Crowd Counting with Transformers
This indicates that global scene context is essential, despite the seemingly bottom-up nature of the problem.
Unsupervised Compound Domain Adaptation for Face Anti-Spoofing
The proposed method successfully adapts to the compound target domain consisting multiple new spoof types.
Learning to Relate Depth and Semantics for Unsupervised Domain Adaptation
Specifically, we show that: (1) our approach improves performance on all tasks when they are complementary and mutually dependent; (2) the CTRL helps to improve both semantic segmentation and depth estimation tasks performance in the challenging UDA setting; (3) the proposed ISL training scheme further improves the semantic segmentation performance.
