Search Results for author:
Found 62 papers, 18 papers with code
Multi-agent Long-term 3D Human Pose Forecasting via Interaction-aware Trajectory Conditioning
Our model effectively handles the multi-modality of human motion and the complexity of long-term multi-agent interactions, improving performance in complex environments.
Stable Surface Regularization for Fast Few-Shot NeRF
This paper proposes an algorithm for synthesizing novel views under few-shot setup.
T4P: Test-Time Training of Trajectory Prediction via Masked Autoencoder and Actor-specific Token Memory
Our method surpasses the performance of existing state-of-the-art online learning methods in terms of both prediction accuracy and computational efficiency.
Improving Transferability for Cross-domain Trajectory Prediction via Neural Stochastic Differential Equation
To address this limitation, we propose a method based on continuous and stochastic representations of Neural Stochastic Differential Equations (NSDE) for alleviating discrepancies due to data acquisition strategy.
Label-Free Event-based Object Recognition via Joint Learning with Image Reconstruction from Events
To this end, we propose a joint formulation of object recognition and image reconstruction in a complementary manner.
Cognitive TransFuser: Semantics-guided Transformer-based Sensor Fusion for Improved Waypoint Prediction
Sensor fusion approaches for intelligent self-driving agents remain key to driving scene understanding given visual global contexts acquired from input sensors.
Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction
We also model the interaction using a probabilistic distribution, which allows for multiple possible future interactions.
Ranked #2 on
Trajectory Prediction
on nuScenes
Video-kMaX: A Simple Unified Approach for Online and Near-Online Video Panoptic Segmentation
The meta architecture of the proposed Video-kMaX consists of two components: within clip segmenter (for clip-level segmentation) and cross-clip associater (for association beyond clips).
TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation
Unlike previous unsupervised domain adaptation methods for category-level object pose estimation, our approach processes the test data in a sequential, online manner, and it does not require access to the source domain at runtime.
Single Domain Generalization for LiDAR Semantic Segmentation
In this paper, we propose a single domain generalization method for LiDAR semantic segmentation (DGLSS) that aims to ensure good performance not only in the source domain but also in the unseen domain by learning only on the source domain.
Learning Adaptive Dense Event Stereo From the Image Domain
To tackle this issue, we propose a novel unsupervised domain Adaptive Dense Event Stereo (ADES), which resolves gaps between the different domains and input modalities.
Non-Coaxial Event-Guided Motion Deblurring with Spatial Alignment
Motion deblurring from a blurred image is a challenging computer vision problem because frame-based cameras lose information during the blurring process.
Cross-Guided Optimization of Radiance Fields With Multi-View Image Super-Resolution for High-Resolution Novel View Synthesis
We perform multi-view image super-resolution (MVSR) on train-view images during the radiance fields optimization process.
Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor
To bring this idea into WSSS, we simultaneously train two models: a classifier generating CAMs that decompose an image into segments and a reconstructor that measures the inferability between the segments.
Ranked #13 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Learning Point Cloud Completion without Complete Point Clouds: A Pose-Aware Approach
Our main idea is to generate multiple incomplete point clouds of various poses and integrate them into a complete point cloud.
Event-Based Video Frame Interpolation With Cross-Modal Asymmetric Bidirectional Motion Fields
Video Frame Interpolation (VFI) aims to generate intermediate video frames between consecutive input frames.
One-Shot Neural Fields for 3D Object Understanding
At test-time, we build the representation from a single RGB input image observing the scene from only one viewpoint.
Learning Monocular Depth Estimation via Selective Distillation of Stereo Knowledge
Monocular depth estimation has been extensively explored based on deep learning, yet its accuracy and generalization ability still lag far behind the stereo-based methods.
MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation
In this paper, we propose and explore a new multi-modal extension of test-time adaptation for 3D semantic segmentation.
Lightweight HDR Camera ISP for Robust Perception in Dynamic Illumination Conditions via Fourier Adversarial Networks
The limited dynamic range of commercial compact camera sensors results in an inaccurate representation of scenes with varying illumination conditions, adversely affecting image quality and subsequently limiting the performance of underlying image processing algorithms.
DGSS : Domain Generalized Semantic Segmentation using Iterative Style Mining and Latent Representation Alignment
This framework allows us to achieve a domain generalized semantic segmentation algorithm with consistent performance without prior information of the target domain while relying on a single source.
Stereo Depth From Events Cameras: Concentrate and Focus on the Future
To alleviate the event missing or overriding issue, we propose to learn to concentrate on the dense events to produce a compact event representation with high details for depth estimation.
SphereSR: 360deg Image Super-Resolution With Arbitrary Projection via Continuous Spherical Image Representation
In this paper, we propose SphereSR, a novel framework to generate a continuous spherical image representation from an LR 360deg image, with the goal of predicting the RGB values at given spherical coordinates for superresolution with an arbitrary 360deg image projection.
GIQE: Generic Image Quality Enhancement via Nth Order Iterative Degradation
Visual degradations caused by motion blur, raindrop, rain, snow, illumination, and fog deteriorate image quality and, subsequently, the performance of perception algorithms deployed in outdoor conditions.
Event-guided Deblurring of Unknown Exposure Time Videos
To this end, we first derive a new formulation for event-guided motion deblurring by considering the exposure and readout time in the video frame acquisition process.
SphereSR: 360° Image Super-Resolution with Arbitrary Projection via Continuous Spherical Image Representation
We then propose a spherical local implicit image function (SLIIF) to predict RGB values at the spherical coordinates.
BIPS: Bi-modal Indoor Panorama Synthesis via Residual Depth-aided Adversarial Learning
Providing omnidirectional depth along with RGB information is important for numerous applications, eg, VR/AR.
Pixel-wise Deep Image Stitching
In this paper, instead of relying on the homography-based warp, we propose a novel deep image stitching framework exploiting the pixel-wise warp field to handle the large-parallax problem.
Exploring Pixel-level Self-supervision for Weakly Supervised Semantic Segmentation
In our framework, with the help of the proposed Regional Contrastive Module (RCM) and Multi-scale Attentive Module (MAM), MainNet is trained by self-supervision from the SupportNet.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Facial Depth and Normal Estimation using Single Dual-Pixel Camera
Many mobile manufacturers recently have adopted Dual-Pixel (DP) sensors in their flagship models for faster auto-focus and aesthetic image captures.
EvDistill: Asynchronous Events to End-task Learning via Bidirectional Reconstruction-guided Cross-modal Knowledge Distillation
To enable KD across the unpaired modalities, we first propose a bidirectional modality reconstruction (BMR) module to bridge both modalities and simultaneously exploit them to distill knowledge via the crafted pairs, causing no extra computation in the inference.
Ranked #7 on
Event-based Object Segmentation
on MVSEC-SEG
UDA-COPE: Unsupervised Domain Adaptation for Category-level Object Pose Estimation
Inspired by recent multi-modal UDA techniques, the proposed method exploits a teacher-student self-supervised learning scheme to train a pose estimation network without using target domain pose labels.
Ranked #5 on
6D Pose Estimation using RGBD
on REAL275
Deep Learning for HDR Imaging: State-of-the-Art and Future Trends
High dynamic range (HDR) imaging is a technique that allows an extensive dynamic range of exposures, which is important in image processing, computer graphics, and computer vision.
SiamEvent: Event-based Object Tracking via Edge-aware Similarity Learning with Siamese Networks
Importantly, to find the part having the most similar edge structure of target, we propose to correlate the embedded events at two timestamps to compute the target edge similarity.
Dual Transfer Learning for Event-based End-task Prediction via Pluggable Event to Image Translation
Event cameras are novel sensors that perceive the per-pixel intensity changes and output asynchronous event streams with high dynamic range and less motion blur.
Ranked #4 on
Event-based Object Segmentation
on MVSEC-SEG
Evaluating COPY-BLEND Augmentation for Low Level Vision Tasks
However, as these techniques destroy spatial relationship with neighboring regions, performance can be deteriorated when using them to train algorithms designed for low level vision tasks (low light image enhancement, image dehazing, deblurring, etc.)
Towards Domain Invariant Single Image Dehazing
However owing to fixed receptive field of convolutional kernels and non uniform haze distribution, assuring consistency between regions is difficult.
Unlocking the Potential of Ordinary Classifier: Class-Specific Adversarial Erasing Framework for Weakly Supervised Semantic Segmentation
In this paper, we review the potential of the pre-trained classifier which is trained on the raw images.
Ranked #30 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Event-Intensity Stereo: Estimating Depth by the Best of Both Worlds
Event cameras can report scene movements as an asynchronous stream of data called the events.
Learning Icosahedral Spherical Probability Map Based on Bingham Mixture Model for Vanishing Point Estimation
Based on this map, we can detect all the VPs.
Knowledge Distillation and Student-Teacher Learning for Visual Intelligence: A Review and New Outlooks
To achieve faster speeds and to handle the problems caused by the lack of data, knowledge distillation (KD) has been proposed to transfer information learned from one model to another.
EventSR: From Asynchronous Events to Image Reconstruction, Restoration, and Super-Resolution via End-to-End Adversarial Learning
While each phase is mainly for one of the three tasks, the networks in earlier phases are fine-tuned by respective loss functions in an end-to-end manner.
Deceiving Image-to-Image Translation Networks for Autonomous Driving with Adversarial Perturbations
However, most previous works have focused on image classification tasks, and it has never been studied regarding adversarial perturbations on Image-to-image (Im2Im) translation tasks, showing great success in handling paired and/or unpaired mapping problems in the field of autonomous driving and robotics.
Learning to Super Resolve Intensity Images from Events
An event camera detects per-pixel intensity difference and produces asynchronous event stream with low latency, high dynamic range, and low power consumption.
Gyroscope-aided Relative Pose Estimation for Rolling Shutter Cameras
The rolling shutter camera has received great attention due to its low cost imaging capability, however, the estimation of relative pose between rolling shutter cameras still remains a difficult problem owing to its line-by-line image capturing characteristics.
SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360 degree Images
This method minimizes thevariance of the spatial resolving power on the sphere sur-face, and includes new convolution and pooling methodsfor the proposed representation.
Event-based High Dynamic Range Image and Very High Frame Rate Video Generation using Conditional Generative Adversarial Networks
Event cameras have a lot of advantages over traditional cameras, such as low latency, high temporal resolution, and high dynamic range.
Consistent Multiple Graph Matching with Multi-layer Random Walks Synchronization
We describe each pair of graphs by combining multiple attributes, then jointly match them in a unified framework.
Inertial-aided Rolling Shutter Relative Pose Estimation
Relative pose estimation is a fundamental problem in computer vision and it has been studied for conventional global shutter cameras for decades.
Distance-based Camera Network Topology Inference for Person Re-identification
The proposed distance-based topology can be applied adaptively to each person according to its speed and handle diverse transition time of people between non-overlapping cameras.
Joint Person Re-identification and Camera Network Topology Inference in Multiple Cameras
Person re-identification is the task of recognizing or identifying a person across multiple views in multi-camera networks.
Automatic Content-Aware Projection for 360deg Videos
Finally, the temporal consistency for image projection is enforced for producing temporally stable normal-view videos.
PaMM: Pose-aware Multi-shot Matching for Improving Person Re-identification
Person re-identification is the problem of recognizing people across different images or videos with non-overlapping views.
Joint Layout Estimation and Global Multi-View Registration for Indoor Reconstruction
In this paper, we propose a novel method to jointly solve scene layout estimation and global registration problems for accurate indoor 3D reconstruction.
Unified Framework for Automated Person Re-identification and Camera Network Topology Inference in Camera Networks
Person re-identification in large-scale multi-camera networks is a challenging task because of the spatio-temporal uncertainty and high complexity due to large numbers of cameras and people.
Monocular Visual Odometry with a Rolling Shutter Camera
However, the MVO still has trouble in handling the RS distortion when the camera motion changes abruptly (e. g. vibration of mobile cameras causes extremely fast motion instantaneously).
Exploiting Multi-layer Graph Factorization for Multi-attributed Graph Matching
In this work, we propose a novel multi-attributed graph matching algorithm based on the multi-layer graph factorization.
Online Multi-Object Tracking via Structural Constraint Event Aggregation
In addition, to further improve the robustness of data association against mis-detections and clutters, a novel event aggregation approach is developed to integrate structural constraints in assignment costs for online MOT.
Ranked #21 on
Multiple Object Tracking
on KITTI Tracking test
Improving Person Re-Identification via Pose-Aware Multi-Shot Matching
Person re-identification is the problem of recognizing people across images or videos from non-overlapping views.
Real-Time Joint Estimation of Camera Orientation and Vanishing Points
The proposed method does not require the Manhattan world assumption, and can perform a highly accurate estimation of camera orientation in real time.
Leveraging Stereo Matching With Learning-Based Confidence Measures
We propose a new approach to associate supervised learning-based confidence prediction with the stereo matching problem.
Robust Online Multi-Object Tracking based on Tracklet Confidence and Online Discriminative Appearance Learning
We first propose the tracklet confidence using the detectability and continuity of a tracklet, and formulate a multi-object tracking problem based on the tracklet confidence.
