259 citations · 803 across the 48 of their papers we have counts for
56 papers
Mobile-4DGS: Unified Static-Dynamic Real-time Mobile Gaussian Splatting
Xiaobiao Du, Beixi Hao, Zhen Fang +3
Recent advances in 3D Gaussian Splatting (3DGS) have achieved remarkable performance in novel view synthesis, yet deploying both static and dynamic Gaussian representations on reso…
LDP: Language-driven Dual-Pixel Image Defocus Deblurring Network
Hao Yang, Liyuan Pan, Yan Yang +2
Recovering sharp images from dual-pixel (DP) pairs with disparity-dependent blur is a challenging task.~Existing blur map-based deblurring methods have demonstrated promising resul…
Contact-aware Human Motion Forecasting
Wei Mao, Miaomiao Liu, Richard Hartley +1
In this paper, we tackle the task of scene-aware 3D human motion forecasting, which consists of predicting future human poses given a 3D scene and a past human motion. A key challe…
Manifold Learning Benefits GANs
Yao Ni, Piotr Koniusz, Richard Hartley +1
In this paper, we improve Generative Adversarial Networks by incorporating a manifold learning step into the discriminator. We consider locality-constrained linear and subspace-bas…
Semi-Supervised 3D Hand Shape and Pose Estimation with Label Propagation
Samira Kaviani, Amir Rahimi, Richard Hartley
To obtain 3D annotations, we are restricted to controlled environments or synthetic datasets, leading us to 3D datasets with less generalizability to real-world scenarios. To tackl…
Dense Uncertainty Estimation via an Ensemble-based Conditional Latent Variable Model
Jing Zhang, Yuchao Dai, Mehrtash Harandi +3
Uncertainty estimation has been extensively studied in recent literature, which can usually be classified as aleatoric uncertainty and epistemic uncertainty. In current aleatoric u…
Invertible Attention
Jiajun Zha, Yiran Zhong, Jing Zhang +2
Attention has been proved to be an efficient mechanism to capture long-range dependencies. However, so far it has not been deployed in invertible networks. This is due to the fact…
One Ring to Rule Them All: a simple solution to multi-view 3D-Reconstruction of shapes with unknown BRDF via a small Recurrent ResNet
Ziang Cheng, Hongdong Li, Richard Hartley +2
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 c…
Learning Optical Flow from a Few Matches
Shihao Jiang, Yao Lu, Hongdong Li +1
State-of-the-art neural network models for optical flow estimation require a dense correlation volume at high resolutions for representing per-pixel displacement. Although the dens…
Learning to Estimate Hidden Motions with Global Motion Aggregation
Shihao Jiang, Dylan Campbell, Yao Lu +2
Occlusions pose a significant challenge to optical flow algorithms that rely on local evidences. We consider an occluded point to be one that is imaged in the first frame but not i…
Few-shot Weakly-Supervised Object Detection via Directional Statistics
Amirreza Shaban, Amir Rahimi, Thalaiyasingam Ajanthan +2
Detecting novel objects from few examples has become an emerging topic in computer vision recently. However, these methods need fully annotated training images to learn new object…
RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
Zhiwei Xu, Thalaiyasingam Ajanthan, Vibhav Vineet +1
Although 3D Convolutional Neural Networks are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory and com…
Uncertainty-Aware Deep Calibrated Salient Object Detection
Jing Zhang, Yuchao Dai, Xin Yu +3
Existing deep neural network based salient object detection (SOD) methods mainly focus on pursuing high network accuracy. However, those methods overlook the gap between network ac…
Dual Pixel Exploration: Simultaneous Depth Estimation and Image Restoration
Liyuan Pan, Shah Chowdhury, Richard Hartley +3
The dual-pixel (DP) hardware works by splitting each pixel in half and creating an image pair in a single snapshot. Several works estimate depth/inverse depth by treating the DP pa…
Refining Semantic Segmentation with Superpixel by Transparent Initialization and Sparse Encoder
Zhiwei Xu, Thalaiyasingam Ajanthan, Richard Hartley
Although deep learning greatly improves the performance of semantic segmentation, its success mainly lies in object central areas without accurate edges. As superpixels are a popul…
RANP: Resource Aware Neuron Pruning at Initialization for 3D CNNs
Zhiwei Xu, Thalaiyasingam Ajanthan, Vibhav Vineet +1
Although 3D Convolutional Neural Networks (CNNs) are essential for most learning based applications involving dense 3D data, their applicability is limited due to excessive memory…
Calibration of Neural Networks using Splines
Kartik Gupta, Amir Rahimi, Thalaiyasingam Ajanthan +3
Calibrating neural networks is of utmost importance when employing them in safety-critical applications where the downstream decision making depends on the predicted probabilities.…
Single Image Optical Flow Estimation with an Event Camera
Liyuan Pan, Miaomiao Liu, Richard Hartley
Event cameras are bio-inspired sensors that asynchronously report intensity changes in microsecond resolution. DAVIS can capture high dynamics of a scene and simultaneously output…
Pairwise Similarity Knowledge Transfer for Weakly Supervised Object Localization
Amir Rahimi, Amirreza Shaban, Thalaiyasingam Ajanthan +2
Weakly Supervised Object Localization (WSOL) methods only require image level labels as opposed to expensive bounding box annotations required by fully supervised algorithms. We st…
Intra Order-preserving Functions for Calibration of Multi-Class Neural Networks
Amir Rahimi, Amirreza Shaban, Ching-An Cheng +2
Predicting calibrated confidence scores for multi-class deep networks is important for avoiding rare but costly mistakes. A common approach is to learn a post-hoc calibration funct…
Joint Unsupervised Learning of Optical Flow and Egomotion with Bi-Level Optimization
Shihao Jiang, Dylan Campbell, Miaomiao Liu +2
We address the problem of joint optical flow and camera motion estimation in rigid scenes by incorporating geometric constraints into an unsupervised deep learning framework. Unlik…
Action Anticipation with RBF Kernelized Feature Mapping RNN
Yuge Shi, Basura Fernando, Richard Hartley
We introduce a novel Recurrent Neural Network-based algorithm for future video feature generation and action anticipation called feature mapping RNN. Our novel RNN architecture bui…
Fast and Differentiable Message Passing on Pairwise Markov Random Fields
Zhiwei Xu, Thalaiyasingam Ajanthan, Richard Hartley
Despite the availability of many Markov Random Field (MRF) optimization algorithms, their widespread usage is currently limited due to imperfect MRF modelling arising from hand-cra…
Mirror Descent View for Neural Network Quantization
Thalaiyasingam Ajanthan, Kartik Gupta, Philip H. S. Torr +2
Quantizing large Neural Networks (NN) while maintaining the performance is highly desirable for resource-limited devices due to reduced memory and time complexity. It is usually fo…