A list of all the posts and pages found on the site. For you robots out there is an XML version available for digesting as well.
EuroGraphics 2022
We address the problem of single image relighting. Our work shows monocular depth estimators can provide sufficient geometry when combined with our novel 3D shadow map prediction module.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci 2018
An experimental assessment addressing the ability to train a deep CNN-based object detector (RetinaNet / Faster R-CNN on a low quantity of training data. Specifically in the context of repetitive features (railway track).
Progress in Physical Geography: Earth and Environment 2018
Linear topologies can be challenging terrains for SfM pipelines. A key source of error is caused by intrinsic camera distortions. We demonstrate through effective camera pre-calibration, distortions can be significantly reduced.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci 2019
A key issue when training deep neural networks for outdoor point clouds is the inevitable large data imbalance. For example, a typical street scene will contain orders of magnitudes more ground points than street furniture. We develop a novel solution to apply a weighted augmentation to reduce the class-imbalance.
Remote Sensing 2019
A comprehensive review paper on deep learning for 3D sensed data classification.
arXiv preprint 2019
We release a synthetic Mobile Laser Scanning (MLS) point cloud named SynthCity. Every point has a per-class and per-instance classification, along with colour, return intensity, end-of-line indicator and time.
ISPRS Journal of Photogrammetry and Remote Sensing 2019
Manually labelling buildings for segmentation is a time consuming task. We show that readily available GIS mapping data can be used as training data. We develop a novel pipeline which uses Active Contours to improve coarse polygons into fine per-pixel label maps.
European Conference on Computer Vision (ECCV) 2020
We present a novel weakly-supervised approach for 3D object detection. Our method can be trained on upto 95% less labeled data and still benefits from unlabeled data.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci 2021
A pipeline which demonstrates that Terrestrial Laser Scanning (TLS) 3D data can be automatically labelled using off-the-shelf 2D semantic segmentation networks. With only a simple projection of a panoramic image, strong results can be generated with no additional training.
International Conference on 3D Vision (3DV) 2021
A novel method for self-supervised monocular 3D object detection. This is achieved through differentiable rendering and a GAN-like critic loss.
EuroGraphics 2022
We address the problem of single image relighting. Our work shows monocular depth estimators can provide sufficient geometry when combined with our novel 3D shadow map prediction module.
NeurIPS 2024
A framework for training any-to-any multimodal foundation models. Scalable. Open-sourced. Across tens of modalities and tasks.
arXiv 2024
We scale 3D object detection to every object in indoor scenes. Our work demonstrates that as we scale to smaller objects, 3D inductive priors become less valuable and a fully-transformer architecture out-performs SOTA 3D networks.
Published:
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci 2018
An experimental assessment addressing the ability to train a deep CNN-based object detector (RetinaNet / Faster R-CNN on a low quantity of training data. Specifically in the context of repetitive features (railway track).
Progress in Physical Geography: Earth and Environment 2018
Linear topologies can be challenging terrains for SfM pipelines. A key source of error is caused by intrinsic camera distortions. We demonstrate through effective camera pre-calibration, distortions can be significantly reduced.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci 2019
A key issue when training deep neural networks for outdoor point clouds is the inevitable large data imbalance. For example, a typical street scene will contain orders of magnitudes more ground points than street furniture. We develop a novel solution to apply a weighted augmentation to reduce the class-imbalance.
Remote Sensing 2019
A comprehensive review paper on deep learning for 3D sensed data classification.
arXiv preprint 2019
We release a synthetic Mobile Laser Scanning (MLS) point cloud named SynthCity. Every point has a per-class and per-instance classification, along with colour, return intensity, end-of-line indicator and time.
ISPRS Journal of Photogrammetry and Remote Sensing 2019
Manually labelling buildings for segmentation is a time consuming task. We show that readily available GIS mapping data can be used as training data. We develop a novel pipeline which uses Active Contours to improve coarse polygons into fine per-pixel label maps.
European Conference on Computer Vision (ECCV) 2020
We present a novel weakly-supervised approach for 3D object detection. Our method can be trained on upto 95% less labeled data and still benefits from unlabeled data.
Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci 2021
A pipeline which demonstrates that Terrestrial Laser Scanning (TLS) 3D data can be automatically labelled using off-the-shelf 2D semantic segmentation networks. With only a simple projection of a panoramic image, strong results can be generated with no additional training.
International Conference on 3D Vision (3DV) 2021
A novel method for self-supervised monocular 3D object detection. This is achieved through differentiable rendering and a GAN-like critic loss.
EuroGraphics 2022
We address the problem of single image relighting. Our work shows monocular depth estimators can provide sufficient geometry when combined with our novel 3D shadow map prediction module.
NeurIPS 2024
A framework for training any-to-any multimodal foundation models. Scalable. Open-sourced. Across tens of modalities and tasks.
arXiv 2024
We scale 3D object detection to every object in indoor scenes. Our work demonstrates that as we scale to smaller objects, 3D inductive priors become less valuable and a fully-transformer architecture out-performs SOTA 3D networks.
