Search Results for author:
Found 156 papers, 72 papers with code
Winding Number for Region-Boundary Consistent Salient Contour Extraction
The main focus is given to how to maintain the consistency (compatibility) between the region cues and the boundary cues.
Efficient Computation of Relative Pose for Multi-Camera Systems
We present a novel solution to compute the relative pose of a generalized camera.
Expanding the Family of Grassmannian Kernels: An Embedding Perspective
Modeling videos and image-sets as linear subspaces has proven beneficial for many visual recognition tasks.
Iteratively Reweighted Graph Cut for Multi-label MRFs with Non-convex Priors
While widely acknowledged as highly effective in computer vision, multi-label MRFs with non-convex priors are difficult to optimize.
Kernel Methods on Riemannian Manifolds with Gaussian RBF Kernels
We then use the proposed framework to identify positive definite kernels on two specific manifolds commonly encountered in computer vision: the Riemannian manifold of symmetric positive definite matrices and the Grassmann manifold, i. e., the Riemannian manifold of linear subspaces of a Euclidean space.
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
To encode the geometry of the manifold in the mapping, we introduce a family of provably positive definite kernels on the Riemannian manifold of SPD matrices.
Optimizing Over Radial Kernels on Compact Manifolds
We tackle the problem of optimizing over all possible positive definite radial kernels on Riemannian manifolds for classification.
A Framework for Shape Analysis via Hilbert Space Embedding
We propose a framework for 2D shape analysis using positive definite kernels defined on Kendall's shape manifold.
Dense, Accurate Optical Flow Estimation With Piecewise Parametric Model
This paper proposes a simple method for estimating dense and accurate optical flow field.
Tracking Randomly Moving Objects on Edge Box Proposals
Our method generates a small number of "high-quality" proposals by a novel instance-specific objectness measure and evaluates them against the object model that can be adopted from an existing tracking-by-detection approach as a core tracker.
Shape Interaction Matrix Revisited and Robustified: Efficient Subspace Clustering with Corrupted and Incomplete Data
The Shape Interaction Matrix (SIM) is one of the earliest approaches to performing subspace clustering (i. e., separating points drawn from a union of subspaces).
Ranked #2 on
Motion Segmentation
on Hopkins155
Robust Multi-body Feature Tracker: A Segmentation-free Approach
Feature tracking is a fundamental problem in computer vision, with applications in many computer vision tasks, such as visual SLAM and action recognition.
Neural Aggregation Network for Video Face Recognition
The network takes a face video or face image set of a person with a variable number of face images as its input, and produces a compact, fixed-dimension feature representation for recognition.
Ranked #7 on
Face Verification
on IJB-A
Learning Image Matching by Simply Watching Video
This work presents an unsupervised learning based approach to the ubiquitous computer vision problem of image matching.
Rolling Shutter Camera Relative Pose: Generalized Epipolar Geometry
The vast majority of modern consumer-grade cameras employ a rolling shutter mechanism.
Beyond Local Search: Tracking Objects Everywhere with Instance-Specific Proposals
Our method generates a small number of "high-quality" proposals by a novel instance-specific objectness measure and evaluates them against the object model that can be adopted from an existing tracking-by-detection approach as a core tracker.
Robust Optical Flow Estimation of Double-Layer Images under Transparency or Reflection
This paper deals with a challenging, frequently encountered, yet not properly investigated problem in two-frame optical flow estimation.
Go-ICP: A Globally Optimal Solution to 3D ICP Point-Set Registration
The evaluation demonstrates that the proposed method is able to produce reliable registration results regardless of the initialization.
Ranked #6 on
Point Cloud Registration
on FP-O-H
Robust and Efficient Relative Pose with a Multi-camera System for Autonomous Vehicle in Highly Dynamic Environments
When the solver is used in combination with RANSAC, we are able to quickly prune unpromising hypotheses, significantly improve the chance of finding inliers.
Multi-body Non-rigid Structure-from-Motion
Recent progress have extended SFM to the areas of {multi-body SFM} (where there are {multiple rigid} relative motions in the scene), as well as {non-rigid SFM} (where there is a single non-rigid, deformable object or scene).
Semi-Dense Visual Odometry for RGB-D Cameras Using Approximate Nearest Neighbour Fields
This paper presents a robust and efficient semi-dense visual odometry solution for RGB-D cameras.
Spatial-Temporal Union of Subspaces for Multi-body Non-rigid Structure-from-Motion
This spatio-temporal representation not only provides competitive 3D reconstruction but also outputs robust segmentation of multiple non-rigid objects.
Pixel-variant Local Homography for Fisheye Stereo Rectification Minimizing Resampling Distortion
First, we prove that there indeed exist enough degrees of freedom to apply pixel-wise local homography for stereo rectification.
"Maximizing rigidity" revisited: a convex programming approach for generic 3D shape reconstruction from multiple perspective views
Rigid structure-from-motion (RSfM) and non-rigid structure-from-motion (NRSfM) have long been treated in the literature as separate (different) problems.
Adaptive Low-Rank Kernel Subspace Clustering
In this paper, we present a kernel subspace clustering method that can handle non-linear models.
Monocular Dense 3D Reconstruction of a Complex Dynamic Scene from Two Perspective Frames
This paper proposes a new approach for monocular dense 3D reconstruction of a complex dynamic scene from two perspective frames.
Self-Supervised Learning for Stereo Matching with Self-Improving Ability
Exiting deep-learning based dense stereo matching methods often rely on ground-truth disparity maps as the training signals, which are however not always available in many situations.
Deep Subspace Clustering Networks
We present a novel deep neural network architecture for unsupervised subspace clustering.
Ranked #3 on
Image Clustering
on Extended Yale-B
Globally-Optimal Inlier Set Maximisation for Simultaneous Camera Pose and Feature Correspondence
Estimating the 6-DoF pose of a camera from a single image relative to a pre-computed 3D point-set is an important task for many computer vision applications.
Efficient Global 2D-3D Matching for Camera Localization in a Large-Scale 3D Map
In this paper, we introduce a global method which harnesses global contextual information exhibited both within the query image and among all the 3D points in the map.
Scalable Dense Non-rigid Structure-from-Motion: A Grassmannian Perspective
To address these issues, in this paper, we propose a new approach for dense NRSfM by modeling the problem on a Grassmann manifold.
Adversarial Spatio-Temporal Learning for Video Deblurring
To tackle the second challenge, we leverage the developed DBLRNet as a generator in the GAN (generative adversarial network) architecture, and employ a content loss in addition to an adversarial loss for efficient adversarial training.
Semantic Single-Image Dehazing
In experiments, we validate our ap- proach upon synthetic and real hazy images, where our method showed superior performance over state-of-the-art approaches, suggesting semantic information facilitates the haze removal task.
Structure from Recurrent Motion: From Rigidity to Recurrency
This paper proposes a new method for Non-Rigid Structure-from-Motion (NRSfM) from a long monocular video sequence observing a non-rigid object performing recurrent and possibly repetitive dynamic action.
Semi-Dense 3D Reconstruction with a Stereo Event Camera
Event cameras are bio-inspired sensors that offer several advantages, such as low latency, high-speed and high dynamic range, to tackle challenging scenarios in computer vision.
Action Anticipation By Predicting Future Dynamic Images
Human action-anticipation methods predict what is the future action by observing only a few portion of an action in progress.
Open-World Stereo Video Matching with Deep RNN
Deep Learning based stereo matching methods have shown great successes and achieved top scores across different benchmarks.
3D Geometry-Aware Semantic Labeling of Outdoor Street Scenes
This paper is concerned with the problem of how to better exploit 3D geometric information for dense semantic image labeling.
Stereo Computation for a Single Mixture Image
This paper proposes an original problem of \emph{stereo computation from a single mixture image}-- a challenging problem that had not been researched before.
Stochastic Attraction-Repulsion Embedding for Large Scale Image Localization
This paper tackles the problem of large-scale image-based localization (IBL) where the spatial location of a query image is determined by finding out the most similar reference images in a large database.
ApolloCar3D: A Large 3D Car Instance Understanding Benchmark for Autonomous Driving
Specifically, we first segment each car with a pre-trained Mask R-CNN, and then regress towards its 3D pose and shape based on a deformable 3D car model with or without using semantic keypoints.
The Alignment of the Spheres: Globally-Optimal Spherical Mixture Alignment for Camera Pose Estimation
Determining the position and orientation of a calibrated camera from a single image with respect to a 3D model is an essential task for many applications.
Dense Depth Estimation of a Complex Dynamic Scene without Explicit 3D Motion Estimation
Given per-pixel optical flow correspondences between two consecutive frames and, the sparse depth prior for the reference frame, we show that, we can effectively recover the dense depth map for the successive frames without solving for 3D motion parameters.
Breaking the Spatio-Angular Trade-off for Light Field Super-Resolution via LSTM Modelling on Epipolar Plane Images
We prove that the light field is a 2D series, thus, a specifically designed CNN-LSTM network is proposed to capture the continuity property of the EPI.
Ground Plane based Absolute Scale Estimation for Monocular Visual Odometry
Recovering the absolute metric scale from a monocular camera is a challenging but highly desirable problem for monocular camera-based systems.
Lending Orientation to Neural Networks for Cross-view Geo-localization
The goal is to predict the spatial location of a ground-level query image by matching it to a large geotagged aerial image database (e. g., satellite imagery).
Deep Stacked Hierarchical Multi-patch Network for Image Deblurring
depth, we propose a stacked version of our multi-patch model.
Ranked #9 on
Deblurring
on RealBlur-R (trained on GoPro)
(SSIM (sRGB) metric)
Noise-Aware Unsupervised Deep Lidar-Stereo Fusion
In this paper, we present LidarStereoNet, the first unsupervised Lidar-stereo fusion network, which can be trained in an end-to-end manner without the need of ground truth depth maps.
Unsupervised Deep Epipolar Flow for Stationary or Dynamic Scenes
In this paper, we propose Deep Epipolar Flow, an unsupervised optical flow method which incorporates global geometric constraints into network learning.
Neural Collaborative Subspace Clustering
We introduce the Neural Collaborative Subspace Clustering, a neural model that discovers clusters of data points drawn from a union of low-dimensional subspaces.
Optimal Feature Transport for Cross-View Image Geo-Localization
This paper proposes a novel Cross-View Feature Transport (CVFT) technique to explicitly establish cross-view domain transfer that facilitates feature alignment between ground and aerial images.
Learning Trajectory Dependencies for Human Motion Prediction
In this paper, we propose a simple feed-forward deep network for motion prediction, which takes into account both temporal smoothness and spatial dependencies among human body joints.
Proposal-free Temporal Moment Localization of a Natural-Language Query in Video using Guided Attention
Given an untrimmed video and a sentence as the query, the goal is to determine the starting, and the ending, of the relevant visual moment in the video, that corresponds to the query sentence.
Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison
Based on this new large-scale dataset, we are able to experiment with several deep learning methods for word-level sign recognition and evaluate their performances in large scale scenarios.
Ranked #3 on
Sign Language Recognition
on WLASL100
Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene
We assume that a dynamic scene can be approximated by numerous piecewise planar surfaces, where each planar surface enjoys its own rigid motion, and the global change in the scene between two frames is as-rigid-as-possible (ARAP).
Spatial-Aware Feature Aggregation for Image based Cross-View Geo-Localization
The first step is to apply a regular polar transform to warp an aerial image such that its domain is closer to that of a ground-view panorama.
Ranked #4 on
Image-Based Localization
on VIGOR Cross Area
Rethinking Class Relations: Absolute-relative Supervised and Unsupervised Few-shot Learning
The majority of existing few-shot learning methods describe image relations with binary labels.
Few-shot Action Recognition with Permutation-invariant Attention
Such encoded blocks are aggregated by permutation-invariant pooling to make our approach robust to varying action lengths and long-range temporal dependencies whose patterns are unlikely to repeat even in clips of the same class.
Ranked #6 on
Few Shot Action Recognition
on Kinetics-100
6DoF Object Pose Estimation via Differentiable Proxy Voting Loss
In this paper, we aim to reduce such errors by incorporating the distances between pixels and keypoints into our objective.
Transferring Cross-domain Knowledge for Video Sign Language Recognition
To this end, we extract news signs using a base WSLR model, and then design a classifier jointly trained on news and isolated signs to coarsely align these two domain features.
Learning 2D-3D Correspondences To Solve The Blind Perspective-n-Point Problem
Conventional absolute camera pose via a Perspective-n-Point (PnP) solver often assumes that the correspondences between 2D image pixels and 3D points are given.
Deblurring by Realistic Blurring
To address this problem, we propose a new method which combines two GAN models, i. e., a learning-to-Blur GAN (BGAN) and learning-to-DeBlur GAN (DBGAN), in order to learn a better model for image deblurring by primarily learning how to blur images.
Ranked #17 on
Deblurring
on HIDE (trained on GOPRO)
Where am I looking at? Joint Location and Orientation Estimation by Cross-View Matching
Cross-view geo-localization is the problem of estimating the position and orientation (latitude, longitude and azimuth angle) of a camera at ground level given a large-scale database of geo-tagged aerial (e. g., satellite) images.
End-to-end Learning for Inter-Vehicle Distance and Relative Velocity Estimation in ADAS with a Monocular Camera
In this paper, we propose a monocular camera-based inter-vehicle distance and relative velocity estimation method based on end-to-end training of a deep neural network.
Dense Non-Rigid Structure from Motion: A Manifold Viewpoint
Assuming that a deforming shape is composed of a union of local linear subspace and, span a global low-rank space over multiple frames enables us to efficiently model complex non-rigid deformations.
The IKEA ASM Dataset: Understanding People Assembling Furniture through Actions, Objects and Pose
The availability of a large labeled dataset is a key requirement for applying deep learning methods to solve various computer vision tasks.
TSPNet: Hierarchical Feature Learning via Temporal Semantic Pyramid for Sign Language Translation
Sign language translation (SLT) aims to interpret sign video sequences into text-based natural language sentences.
DORi: Discovering Object Relationship for Moment Localization of a Natural-Language Query in Video
This paper studies the task of temporal moment localization in a long untrimmed video using natural language query.
Hierarchical Neural Architecture Search for Deep Stereo Matching
To reduce the human efforts in neural network design, Neural Architecture Search (NAS) has been applied with remarkable success to various high-level vision tasks such as classification and semantic segmentation.
Ranked #2 on
Stereo Disparity Estimation
on Scene Flow
Displacement-Invariant Matching Cost Learning for Accurate Optical Flow Estimation
Learning matching costs has been shown to be critical to the success of the state-of-the-art deep stereo matching methods, in which 3D convolutions are applied on a 4D feature volume to learn a 3D cost volume.
Displacement-Invariant Cost Computation for Efficient Stereo Matching
A common way to speed up the computation is to downsample the feature volume, but this loses high-frequency details.
Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration
The heavy defocus blur in DP pairs affects the performance of matching-based depth estimation approaches.
PlueckerNet: Learn to Register 3D Line Reconstructions
Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve correspondences and relative pose between line reconstructions.
Efficient Depth Completion Using Learned Bases
The given sparse depth points are served as a data term to constrain the weighting process.
Depth Completion using Piecewise Planar Model
More specifically, we represent the desired depth map as a collection of 3D planar and the reconstruction problem is formulated as the optimization of planar parameters.
Canny-VO: Visual Odometry with RGB-D Cameras based on Geometric 3D-2D Edge Alignment
The present paper reviews the classical problem of free-form curve registration and applies it to an efficient RGBD visual odometry system called Canny-VO, as it efficiently tracks all Canny edge features extracted from the images.
Geometry-Guided Street-View Panorama Synthesis from Satellite Imagery
Specifically, we observe that when a 3D point in the real world is visible in both views, there is a deterministic mapping between the projected points in the two-view images given the height information of this 3D point.
ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring
Video deblurring models exploit consecutive frames to remove blurs from camera shakes and object motions.
Deep Dense Multi-scale Network for Snow Removal Using Semantic and Geometric Priors
Images captured in snowy days suffer from noticeable degradation of scene visibility, which degenerates the performance of current vision-based intelligent systems.
Self-Supervised Visibility Learning for Novel View Synthesis
We then warp and aggregate source view pixels to synthesize a novel view based on the estimated source-view visibility and target-view depth.
Deep Two-View Structure-from-Motion Revisited
Two-view structure-from-motion (SfM) is the cornerstone of 3D reconstruction and visual SLAM.
Ranked #24 on
Monocular Depth Estimation
on KITTI Eigen split
Learning Optical Flow from a Few Matches
In this paper, we show that the dense correlation volume representation is redundant and accurate flow estimation can be achieved with only a fraction of elements in it.
Ranked #11 on
Optical Flow Estimation
on KITTI 2015 (train)
Learning to Estimate Hidden Motions with Global Motion Aggregation
We demonstrate that the optical flow estimates in the occluded regions can be significantly improved without damaging the performance in non-occluded regions.
Ranked #5 on
Optical Flow Estimation
on Sintel-final
One Ring to Rule Them All: a simple solution to multi-view 3D-Reconstruction of shapes with unknown BRDF via a small Recurrent ResNet
This paper proposes a simple method which solves an open problem of multi-view 3D-Reconstruction for objects with unknown and generic surface materials, imaged by a freely moving camera and a freely moving point light source.
Lighting, Reflectance and Geometry Estimation from 360$^{\circ}$ Panoramic Stereo
We propose a method for estimating high-definition spatially-varying lighting, reflectance, and geometry of a scene from 360$^{\circ}$ stereo images.
Beyond Monocular Deraining: Parallel Stereo Deraining Network Via Semantic Prior
We first use a coarse deraining network to reduce the rain streaks on the input images, and then adopt a pre-trained semantic segmentation network to extract semantic features from the coarse derained image.
Multi-view 3D Reconstruction of a Texture-less Smooth Surface of Unknown Generic Reflectance
Recovering the 3D geometry of a purely texture-less object with generally unknown surface reflectance (e. g. non-Lambertian) is regarded as a challenging task in multi-view reconstruction.
Shell Theory: A Statistical Model of Reality
The foundational assumption of machine learning is that the data under consideration is separable into classes; while intuitively reasonable, separability constraints have proven remarkably difficult to formulate mathematically.
Ranked #1 on
Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly
on STL-10
(using extra training data)
Multi-level Motion Attention for Human Motion Prediction
Whether based on recurrent or feed-forward neural networks, existing learning based methods fail to model the observation that human motion tends to repeat itself, even for complex sports actions and cooking activities.
PluckerNet: Learn To Register 3D Line Reconstructions
Aligning two partially-overlapped 3D line reconstructions in Euclidean space is challenging, as we need to simultaneously solve line correspondences and relative pose between reconstructions.
Lighting, Reflectance and Geometry Estimation From 360deg Panoramic Stereo
We propose a method for estimating high-definition spatially-varying lighting, reflectance, and geometry of a scene from 360deg stereo images.
Underwater Image Restoration via Contrastive Learning and a Real-world Dataset
There are 2000 reference restored images and 6003 original underwater images in the unpaired training set.
Ranking Models in Unlabeled New Environments
For this problem, we propose to adopt a proxy dataset that 1) is fully labeled and 2) well reflects the true model rankings in a given target environment, and use the performance rankings on the proxy sets as surrogates.
Blind Image Decomposition
We propose and study a novel task named Blind Image Decomposition (BID), which requires separating a superimposed image into constituent underlying images in a blind setting, that is, both the source components involved in mixing as well as the mixing mechanism are unknown.
Neural Plenoptic Sampling: Capture Light-field from Imaginary Eyes
It encodes a complete light-field (\ie, lumigraph) therefore allows one to freely roam in the space and view the scene from any location in any direction.
Neural Photometric Stereo for Shape and Material Estimation
This paper addresses a challenging Photometric-Stereo problem where the object to be reconstructed has unknown, non-Lambertian, and possibly spatially-varying surface materials.
Learning To Segment Dominant Object Motion From Watching Videos
Existing deep learning based unsupervised video object segmentation methods still rely on ground-truth segmentation masks to train.
HDR-NeRF: High Dynamic Range Neural Radiance Fields
The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper.
Improving GAN Equilibrium by Raising Spatial Awareness
We further propose to align the spatial awareness of G with the attention map induced from D. Through this way we effectively lessen the information gap between D and G. Extensive results show that our method pushes the two-player game in GANs closer to the equilibrium, leading to a better synthesis performance.
Label-Free Model Evaluation with Semi-Structured Dataset Representations
In the absence of image labels, based on dataset representations, we estimate model performance for AutoEval with regression.
MC-Blur: A Comprehensive Benchmark for Image Deblurring
Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios.
Align and Prompt: Video-and-Language Pre-training with Entity Prompts
To achieve this, we first introduce an entity prompter module, which is trained with VTC to produce the similarity between a video crop and text prompts instantiated with entity names.
Ranked #19 on
Zero-Shot Video Retrieval
on DiDeMo
Transcribing Natural Languages for The Deaf via Neural Editing Programs
This work studies the task of glossification, of which the aim is to em transcribe natural spoken language sentences for the Deaf (hard-of-hearing) community to ordered sign language glosses.
Multi-level Second-order Few-shot Learning
The goal of multi-level feature design is to extract feature representations at different layer-wise levels of CNN, realizing several levels of visual abstraction to achieve robust few-shot learning.
Deep Image Deblurring: A Survey
Image deblurring is a classic problem in low-level computer vision with the aim to recover a sharp image from a blurred input image.
You Only Cut Once: Boosting Data Augmentation with a Single Cut
We present You Only Cut Once (YOCO) for performing data augmentations.
Neural Reflectance for Shape Recovery with Shadow Handling
This network is able to leverage the observed photometric variance and shadows on the surface, and recover both surface shape and general non-Lambertian reflectance.
Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching
We address the problem of ground-to-satellite image geo-localization, that is, estimating the camera latitude, longitude and orientation (azimuth angle) by matching a query image captured at the ground level against a large-scale database with geotagged satellite images.
Stereo Unstructured Magnification: Multiple Homography Image for View Synthesis
A two-stage network is developed for novel view synthesis.
Beyond Cross-view Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image
This paper addresses the problem of vehicle-mounted camera localization by matching a ground-level image with an overhead-view satellite map.
Deep Non-rigid Structure-from-Motion: A Sequence-to-Sequence Translation Perspective
In this paper, we propose to model deep NRSfM from a sequence-to-sequence translation perspective, where the input 2D frame sequence is taken as a whole to reconstruct the deforming 3D non-rigid shape sequence.
Unsupervised Video Interpolation by Learning Multilayered 2.5D Motion Fields
This implicit neural representation learns the video as a space-time continuum, allowing frame interpolation at any temporal resolution.
CropMix: Sampling a Rich Input Distribution via Multi-Scale Cropping
We present a simple method, CropMix, for the purpose of producing a rich input distribution from the original dataset distribution.
Self-calibrating Photometric Stereo by Neural Inverse Rendering
This paper tackles the task of uncalibrated photometric stereo for 3D object reconstruction, where both the object shape, object reflectance, and lighting directions are unknown.
Satellite Image Based Cross-view Localization for Autonomous Vehicle
This paper introduces a novel approach to cross-view localization that departs from the conventional image retrieval method.
CVLNet: Cross-View Semantic Correspondence Learning for Video-based Camera Localization
The critical challenge of this task is to learn a powerful global feature descriptor for the sequential ground-view images while considering its domain alignment with reference satellite images.
NAF: Neural Attenuation Fields for Sparse-View CBCT Reconstruction
This paper proposes a novel and fast self-supervised solution for sparse-view CBCT reconstruction (Cone Beam Computed Tomography) that requires no external training data.
Ranked #2 on
Novel View Synthesis
on X3D
Distance Based Image Classification: A solution to generative classification's conundrum?
We use the model to develop a classification scheme which suppresses the impact of noise while preserving semantic cues.
Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video
The RSSR is a very challenging task, and to our knowledge, no practical solution exists to date.
A Survey of Deep Face Restoration: Denoise, Super-Resolution, Deblur, Artifact Removal
Second, we discuss the challenges of face restoration.
What Images are More Memorable to Machines?
This paper studies the problem of measuring and predicting how memorable an image is to pattern recognition machines, as a path to explore machine intelligence.
Interacting Hand-Object Pose Estimation via Dense Mutual Attention
In contrast, we propose a novel dense mutual attention mechanism that is able to model fine-grained dependencies between the hand and the object.
Ranked #2 on
hand-object pose
on HO-3D
(using extra training data)
Wide-Angle Rectification via Content-Aware Conformal Mapping
Despite the proliferation of ultra wide-angle lenses on smartphone cameras, such lenses often come with severe image distortion (e. g. curved linear structure, unnaturally skewed faces).
A Rotation-Translation-Decoupled Solution for Robust and Efficient Visual-Inertial Initialization
We propose a novel visual-inertial odometry (VIO) initialization method, which decouples rotation and translation estimation, and achieves higher efficiency and better robustness.
Spatial Steerability of GANs via Self-Supervision from Discriminator
In this work, we propose a self-supervised approach to improve the spatial steerability of GANs without searching for steerable directions in the latent space or requiring extra annotations.
CircNet: Meshing 3D Point Clouds with Circumcenter Detection
In this paper, we leverage the duality between a triangle and its circumcenter, and introduce a deep neural network that detects the circumcenters to achieve point cloud triangulation.
MEGANE: Morphable Eyeglass and Avatar Network
However, modeling the geometric and appearance interactions of glasses and the face of virtual representations of humans is challenging.
Event-guided Multi-patch Network with Self-supervision for Non-uniform Motion Deblurring
Contemporary deep learning multi-scale deblurring models suffer from many issues: 1) They perform poorly on non-uniformly blurred images/videos; 2) Simply increasing the model depth with finer-scale levels cannot improve deblurring; 3) Individual RGB frames contain a limited motion information for deblurring; 4) Previous models have a limited robustness to spatial transformations and noise.
Seeing Through the Glass: Neural 3D Reconstruction of Object Inside a Transparent Container
In this paper, we define a new problem of recovering the 3D geometry of an object confined in a transparent enclosure.
WildLight: In-the-wild Inverse Rendering with a Flashlight
Our system recovers scene geometry and reflectance using only multi-view images captured by a smartphone.
Inverting the Imaging Process by Learning an Implicit Camera Model
In principle, our new implicit neural camera model has the potential to benefit a wide array of other inverse imaging tasks.
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions
Second, we introduce a residual dense transformer block (RDTB) as the final GridFormer layer.
Boosting 3-DoF Ground-to-Satellite Camera Localization Accuracy via Geometry-Guided Cross-View Transformer
In this paper, we propose a method to increase the accuracy of a ground camera's location and orientation by estimating the relative rotation and translation between the ground-level image and its matched/retrieved satellite image.
EndoSurf: Neural Surface Reconstruction of Deformable Tissues with Stereo Endoscope Videos
We constrain the learned shape by tailoring multiple regularization strategies and disentangling geometry and appearance.
LLDiffusion: Learning Degradation Representations in Diffusion Models for Low-Light Image Enhancement
In this paper, we address this limitation by proposing a degradation-aware learning scheme for LLIE using diffusion models, which effectively integrates degradation and image priors into the diffusion process, resulting in improved image enhancement.
View Consistent Purification for Accurate Cross-View Localization
This paper proposes a fine-grained self-localization method for outdoor robotics that utilizes a flexible number of onboard cameras and readily accessible satellite images.
Unsupervised 3D Pose Estimation with Non-Rigid Structure-from-Motion Modeling
Most of the previous 3D human pose estimation work relied on the powerful memory capability of the network to obtain suitable 2D-3D mappings from the training data.
Faster Stochastic Variance Reduction Methods for Compositional MiniMax Optimization
All the proposed complexities indicate that our proposed methods can match lower bounds to existing minimax optimizations, without requiring a large batch size in each iteration.
MB-TaylorFormer: Multi-branch Efficient Transformer Expanded by Taylor Formula for Image Dehazing
To address this issue, we propose a new Transformer variant, which applies the Taylor expansion to approximate the softmax-attention and achieves linear computational complexity.
Stereo Matching in Time: 100+ FPS Video Stereo Matching for Extended Reality
One of the major difficulties is the lack of high-quality indoor video stereo training datasets captured by head-mounted VR/AR glasses.
Deep Video Restoration for Under-Display Camera
With the pipeline, we build the first large-scale UDC video restoration dataset called PexelsUDC, which includes two subsets named PexelsUDC-T and PexelsUDC-P corresponding to different displays for UDC.
RGB-based Category-level Object Pose Estimation via Decoupled Metric Scale Recovery
While showing promising results, recent RGB-D camera-based category-level object pose estimation methods have restricted applications due to the heavy reliance on depth sensors.
Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic
In this paper, we detail the settings of Alice benchmarks, provide an analysis of existing commonly-used domain adaptation methods, and discuss some interesting future directions.
DeepSimHO: Stable Pose Estimation for Hand-Object Interaction via Physics Simulation
Specifically, for an initial hand-object pose estimated by a base network, we forward it to a physics simulator to evaluate its stability.
ConsistNet: Enforcing 3D Consistency for Multi-view Images Diffusion
Given a single image of a 3D object, this paper proposes a novel method (named ConsistNet) that is able to generate multiple images of the same object, as if seen they are captured from different viewpoints, while the 3D (multi-view) consistencies among those multiple generated images are effectively exploited.
3D Human Pose Analysis via Diffusion Synthesis
In this paper, we propose PADS (Pose Analysis by Diffusion Synthesis), a novel framework designed to address various challenges in 3D human pose analysis through a unified pipeline.
BlockFusion: Expandable 3D Scene Generation using Latent Tri-plane Extrapolation
A variational auto-encoder is employed to compress the tri-planes into the latent tri-plane space, on which the denoising diffusion process is performed.
PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal
For the prompt generation, we first propose a prompt pre-training strategy to train a frequency prompt encoder that encodes the ground-truth image into LF and HF prompts.
Strong and Controllable Blind Image Decomposition
To address this need, we add controllability to the blind image decomposition process, allowing users to enter which types of degradation to remove or retain.
Frankenstein: Generating Semantic-Compositional 3D Scenes in One Tri-Plane
We present Frankenstein, a diffusion-based framework that can generate semantic-compositional 3D scenes in a single pass.
NeuSDFusion: A Spatial-Aware Generative Model for 3D Shape Completion, Reconstruction, and Generation
3D shape generation aims to produce innovative 3D content adhering to specific conditions and constraints.
Homography Guided Temporal Fusion for Road Line and Marking Segmentation
Reliable segmentation of road lines and markings is critical to autonomous driving.
Beyond Monocular Deraining: Stereo Image Deraining via Semantic Understanding
Moreover, even for single image based monocular deraining, many current methods fail to complete the task satisfactorily because they mostly rely on per pixel loss functions and ignoring semantic information.
Automatic Gloss Dictionary for Sign Language Learners
A multi-language dictionary is a fundamental tool for language learning, allowing the learner to look up unfamiliar words.
Deep Novel View Synthesis from Colored 3D Point Clouds
We propose a new deep neural network which takes a colored 3D point cloud of a scene, and directly synthesizes a photo-realistic image from an arbitrary viewpoint.
