no code implementations • 14 Mar 2024 • Pawel Knap, Peter Hardy, Alberto Tamajo, Hwasup Lim, Hansung Kim
Therefore, this paper presents one of the first 3D multi-person human pose estimation systems that is able to work in real-time and is also able to handle basic forms of occlusion.
1 code implementation • 2 Feb 2024 • Hansung Kim, Siddharth H. Nair, Francesco Borrelli
We propose a hierarchical architecture designed for scalable real-time Model Predictive Control (MPC) in complex, multi-modal traffic scenarios.
no code implementations • 16 Nov 2023 • Yihong Wu, Yuwen Heng, Mahesan Niranjan, Hansung Kim
To this end, in this work, we quantify the relative contributions of the known cues of depth in a monocular depth estimation setting using an indoor scene data set.
no code implementations • 26 Sep 2023 • Peter Hardy, Hansung Kim
To address the issue of perspective ambiguity, we expand upon prior work by predicting the cameras' elevation angle relative to the subjects' pelvis.
no code implementations • 13 Sep 2023 • Peter Hardy, Hansung Kim
Furthermore, our method excels in accurately retrieving complete 3D poses even in the presence of occlusions, making it highly applicable in situations where complete 2D pose information is unavailable.
1 code implementation • 21 Jul 2023 • Yuwen Heng, Yihong Wu, Jiawen Chen, Srinandan Dasmahapatra, Hansung Kim
The network leverages the principles of colour perception in modern cameras to constrain the reconstructed hyperspectral images and employs the domain adaptation method to generalise the hyperspectral reconstruction capability from a spectral recovery dataset to material segmentation datasets.
1 code implementation • 6 May 2023 • Yuwen Heng, Srinandan Dasmahapatra, Hansung Kim
By analysing the cross-resolution features and the attention weights, this paper interprets how the DBAT learns from image patches.
no code implementations • 1 Sep 2022 • Peter Hardy, Srinandan Dasmahapatra, Hansung Kim
With a maximum architecture capacity of 6 residual blocks, we evaluate the performance of 5 models which each represent a 2D pose differently during the adversarial unsupervised 2D-3D HPE process.
no code implementations • 12 May 2022 • Peter Hardy, Srinandan Dasmahapatra, Hansung Kim
We show that for two independent generators training adversarially has improved stability than that of a solo generator which collapses.
Ranked #46 on 3D Human Pose Estimation on MPI-INF-3DHP (AUC metric)
no code implementations • 27 Oct 2021 • Geunseong Jung, Sungjae Han, Hansung Kim, Kwanguk Kim, Jaehyuk Cha
We propose this first browsing area, which is the top side of a web document for simulating situations where a user first encountered a web page.
no code implementations • 5 Jul 2021 • Peter Hardy, Srinandan Dasmahapatra, Hansung Kim
Second, the keypoint detection performance gained is dependent on that persons pixel count in the original image prior to any application of SR; keypoint detection performance was improved when SR was applied to people with a small initial segmentation area, but degrades as this becomes larger.
1 code implementation • 8 Aug 2019 • Aloisio Dourado, Teofilo Emidio de Campos, Hansung Kim, Adrian Hilton
Semantic scene completion is the task of predicting a complete 3D representation of volumetric occupancy with corresponding semantic labels for a scene from a single point of view.
Ranked #22 on 3D Semantic Scene Completion on NYUv2
no code implementations • 18 Jul 2019 • Armin Mustafa, Marco Volino, Hansung Kim, Jean-yves Guillemaut, Adrian Hilton
Existing techniques for dynamic scene reconstruction from multiple wide-baseline cameras primarily focus on reconstruction in controlled environments, with fixed calibrated cameras and strong prior constraints.
no code implementations • CVPR 2016 • Armin Mustafa, Hansung Kim, Jean-yves Guillemaut, Adrian Hilton
Sparse-to-dense temporal correspondence is integrated with joint multi-view segmentation and reconstruction to obtain a complete 4D representation of static and dynamic objects.
no code implementations • ICCV 2015 • Armin Mustafa, Hansung Kim, Jean-yves Guillemaut, Adrian Hilton
The primary contributions of this paper are twofold: an automatic method for initial coarse dynamic scene segmentation and reconstruction without prior knowledge of background appearance or structure; and a general robust approach for joint segmentation refinement and dense reconstruction of dynamic scenes from multiple wide-baseline static or moving cameras.