Search Results for author:
Found 21 papers, 6 papers with code
State-of-the-Art Fails in the Art of Damage Detection
Accurately detecting and classifying damage in analogue media such as paintings, photographs, textiles, mosaics, and frescoes is essential for cultural heritage preservation.
Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models
Then, we train a multi-view diffusion model over the latent space to learn an efficient generative model.
Detail-Enhanced Intra- and Inter-modal Interaction for Audio-Visual Emotion Recognition
Capturing complex temporal relationships between video and audio modalities is vital for Audio-Visual Emotion Recognition (AVER).
Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning
In this paper, we show that human-labelling errors not only differ significantly from synthetic label errors, but also pose unique challenges in SCL, different to those in traditional supervised learning methods.
Denoising Diffusion via Image-Based Rendering
In this work, we introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes.
Foveation in the Era of Deep Learning
In this paper, we tackle the challenge of actively attending to visual scenes using a foveated sensor.
Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning
However, while the detrimental effects of noisy labels in supervised learning are well-researched, their influence on SCL remains largely unexplored.
Multi-Scale Cross Contrastive Learning for Semi-Supervised Medical Image Segmentation
Semi-supervised learning has demonstrated great potential in medical image segmentation by utilizing knowledge from unlabeled data.
Simulating analogue film damage to analyse and improve artefact restoration on high-resolution scans
We address the lack of ground-truth data for evaluation by collecting a dataset of 4K damaged analogue film scans paired with manually-restored versions produced by a human expert, allowing quantitative evaluation of restoration performance.
RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
In this paper, we present RenderDiffusion, the first diffusion model for 3D generation and inference, trained using only monocular 2D supervision.
Deep learning extraction of band structure parameters from density of states: a case study on trilayer graphene
Next, we use the fast and accurate predictions from the trained network to automatically determine tight-binding parameters directly from experimental data, with extracted parameters being in a good agreement with values in the literature.
Unsupervised Video Prediction from a Single Frame by Estimating 3D Dynamic Scene Structure
Our goal in this work is to generate realistic videos given just one initial frame as input.
Computational Design of Cold Bent Glass Façades
However, it is very challenging to navigate the design space of cold bent glass panels due to the fragility of the material, which impedes the form-finding for practically feasible and aesthetically pleasing cold bent glass fa\c{c}ades.
Unsupervised object-centric video generation and decomposition in 3D
A natural approach to generative modeling of videos is to represent them as a composition of moving objects.
Leveraging 2D Data to Learn Textured 3D Mesh Generation
Thus, it learns to generate meshes that when rendered, produce images similar to those in its training set.
Object-Centric Image Generation with Factored Depths, Locations, and Appearances
We present a generative model of images that explicitly reasons over the set of objects they show.
Learning single-image 3D reconstruction by generative modelling of shape, pose and shading
Importantly, it can be trained purely from 2D images, without pose annotations, and with only a single view per instance.
Learning to Generate and Reconstruct 3D Meshes with only 2D Supervision
Importantly, it can be trained purely from 2D images, without ground-truth pose annotations, and with a single view per instance.
Automatic Generation of Constrained Furniture Layouts
Efficient authoring of vast virtual environments hinges on algorithms that are able to automatically generate content while also being controllable.
End-to-end training of object class detectors for mean average precision
We present a method for training CNN-based object class detectors directly using mean average precision (mAP) as the training loss, in a truly end-to-end fashion that includes non-maximum suppression (NMS) at training time.
Automatically selecting inference algorithms for discrete energy minimisation
Minimisation of discrete energies defined over factors is an important problem in computer vision, and a vast number of MAP inference algorithms have been proposed.
