Search
Results
-
CompositeTasking: Understanding Images by Spatial Composition of Tasks
(2021)2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)We define the concept of CompositeTasking as the fusion of multiple, spatially distributed tasks, for various aspects of image understanding. Learning to perform spatially distributed tasks is motivated by the frequent availability of only sparse labels across tasks, and the desire for a compact multi-tasking network. To facilitate CompositeTasking, we introduce a novel task conditioning model – a single encoder-decoder network that ...Conference Paper -
Coarse-to-Fine Feature Mining for Video Semantic Segmentation
(2022)2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)The contextual information plays a core role in semantic segmentation. As for video semantic segmentation, the contexts include static contexts and motional contexts, corresponding to static content and moving content in a video clip, respectively. The static contexts are well exploited in image semantic segmentation by learning multiscale and global/long-range features. The motional contexts are studied in previous video semantic ...Conference Paper -
Deeply Learned 2D Tool Pose Estimation for Robot-to-Camera Registration
(2017)Proceedings of the 7th Joint Workshop on New Technologies for Computer/Robot Assisted SurgeryConference Paper -
Unsupervised learning of consensus maximization for 3D vision problems
(2019)Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019)Conference Paper -
Model-free Consensus Maximization for Non-Rigid Shapes
(2018)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2018Many computer vision methods use consensus maximization to relate measurements containing outliers with the correct transformation model. In the context of rigid shapes, this is typically done using Random Sampling and Consensus (RANSAC) by estimating an analytical model that agrees with the largest number of measurements (inliers). However, small parameter models may not be always available. In this paper, we formulate the model-free ...Conference Paper -
Incremental Non-Rigid Structure-from-Motion with Unknown Focal Length
(2018)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2018 15th European Conference, Munich, Germany, September 8-14, 2018, Proceedings, Part XIIIThe perspective camera and the isometric surface prior have recently gathered increased attention for Non-Rigid Structure-from-Motion (NRSfM). Despite the recent progress, several challenges remain, particularly the computational complexity and the unknown camera focal length. In this paper we present a method for incremental Non-Rigid Structure-from-Motion (NRSfM) with the perspective camera model and the isometric surface prior with ...Conference Paper -
Self-supervised 3D hand pose estimation through training by fitting
(2019)Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019)Conference Paper -
What correspondences reveal about unknown camera and motion models?
(2019)Proceedings of the 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR 2019)Conference Paper -
Efficient Model-free Anthropometry from Depth Data
(2017)2017 International Conference on 3D Vision (3DV)Conference Paper -
Self-Supervised 3D Hand Pose Estimation Through Training by Fitting
(2019)We present a self-supervision method for 3D hand pose estimation from depth maps. We begin with a neural network initialized with synthesized data and fine-tune it on real but unlabelled depth maps by minimizing a set of datafitting terms. By approximating the hand surface with a set of spheres, we design a differentiable hand renderer to align estimates by comparing the rendered and input depth maps. In addition, we place a set of priors ...Conference Paper