Search
Results
-
Neural Radiance Fields Approach to Deep Multi-View Photometric Stereo
(2022)2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)We present a modern solution to the multi-view photometric stereo problem (MVPS). Our work suitably exploits the image formation model in a MVPS experimental setup to recover the dense 3D reconstruction of an object from images. We procure the surface orientation using a photometric stereo (PS) image formation model and blend it with a multi-view neural radiance field representation to recover the object’s surface geometry. Contrary to ...Conference Paper -
Cluster, Split, Fuse, and Update: Meta-Learning for Open Compound Domain Adaptive Semantic Segmentation
(2021)2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)Open compound domain adaptation (OCDA) is a domain adaptation setting, where target domain is modeled as a compound of multiple unknown homogeneous domains, which brings the advantage of improved generalization to unseen domains. In this work, we propose a principled meta-learning based approach to OCDA for semantic segmentation, MOCDA, by modeling the unlabeled target domain continuously. Our approach consists of four key steps. First, ...Conference Paper -
Decoder Fusion RNN: Context and Interaction Aware Decoders for Trajectory Prediction
(2021)2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)Conference Paper -
Decomposing Image Generation into Layout Prediction and Conditional Synthesis
(2020)2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)Learning the distribution of multi-object scenes with Generative Adversarial Networks (GAN) is challenging. Guiding the learning using semantic intermediate representations, which are less complex than images, can be a solution. In this article, we investigate splitting the optimisation of generative adversarial networks into two parts, by first generating a semantic segmentation mask from noise and then translating that segmentation mask ...Conference Paper -
End-to-End Learning of Driving Models with Surround-View Cameras and Route Planners
(2018)Lecture Notes in Computer Science ~ Computer Vision – ECCV 2018Conference 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)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 -
GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network
(2021)Advances in Neural Information Processing Systems 33The feature correlation layer serves as a key neural network module in numerous computer vision problems that involve dense correspondences between image pairs. It predicts a correspondence volume by evaluating dense scalar products between feature vectors extracted from pairs of locations in two images. However, this point-to-point feature comparison is insufficient when disambiguating multiple similar regions in an image, severely ...Conference Paper -
Some like it hot - visual guidance for preference prediction
(2016)Proceedings of the 29th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016)Conference Paper