Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models

We present a latent diffusion model over 3D scenes, that can be trained using only 2D image data. To achieve this, we first design an autoencoder that maps multi-view images to 3D Gaussian splats, and simultaneously builds a compressed latent representation of these splats. Then, we train a multi-view diffusion model over the latent space to learn an efficient generative model. This pipeline does not require object masks nor depths, and is suitable for complex scenes with arbitrary camera positions. We conduct careful experiments on two large-scale datasets of complex real-world scenes -- MVImgNet and RealEstate10K. We show that our approach enables generating 3D scenes in as little as 0.2 seconds, either from scratch, from a single input view, or from sparse input views. It produces diverse and high-quality results while running an order of magnitude faster than non-latent diffusion models and earlier NeRF-based generative models

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). However, existing methods lack attention to local details, such as facial state changes between video frames, which can reduce the discriminability of features and thus lower recognition accuracy. In this paper, we propose a Detail-Enhanced Intra- and Inter-modal Interaction network(DE-III) for AVER, incorporating several novel aspects. We introduce optical flow information to enrich video representations with texture details that better capture facial state changes. A fusion module integrates the optical flow estimation with the corresponding video frames to enhance the representation of facial texture variations. We also design attentive intra- and inter-modal feature enhancement modules to further improve the richness and discriminability of video and audio representations. A detailed quantitative evaluation shows that our proposed model outperforms all existing methods on three benchmark datasets for both concrete and continuous emotion recognition. To encourage further research and ensure replicability, we will release our full code upon acceptance.

Understanding and Mitigating Human-Labelling Errors in Supervised Contrastive Learning

Human-annotated vision datasets inevitably contain a fraction of human mislabelled examples. While the detrimental effects of such mislabelling on supervised learning are well-researched, their influence on Supervised Contrastive Learning (SCL) remains largely unexplored. 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. Specifically, our results indicate they adversely impact the learning process in the ~99% of cases when they occur as false positive samples. Existing noise-mitigating methods primarily focus on synthetic label errors and tackle the unrealistic setting of very high synthetic noise rates (40-80%), but they often underperform on common image datasets due to overfitting. To address this issue, we introduce a novel SCL objective with robustness to human-labelling errors, SCL-RHE. SCL-RHE is designed to mitigate the effects of real-world mislabelled examples, typically characterized by much lower noise rates (<5%). We demonstrate that SCL-RHE consistently outperforms state-of-the-art representation learning and noise-mitigating methods across various vision benchmarks, by offering improved resilience against human-labelling errors.

Denoising Diffusion via Image-Based Rendering

Generating 3D scenes is a challenging open problem, which requires synthesizing plausible content that is fully consistent in 3D space. While recent methods such as neural radiance fields excel at view synthesis and 3D reconstruction, they cannot synthesize plausible details in unobserved regions since they lack a generative capability. Conversely, existing generative methods are typically not capable of reconstructing detailed, large-scale scenes in the wild, as they use limited-capacity 3D scene representations, require aligned camera poses, or rely on additional regularizers. In this work, we introduce the first diffusion model able to perform fast, detailed reconstruction and generation of real-world 3D scenes. To achieve this, we make three contributions. First, we introduce a new neural scene representation, IB-planes, that can efficiently and accurately represent large 3D scenes, dynamically allocating more capacity as needed to capture details visible in each image. Second, we propose a denoising-diffusion framework to learn a prior over this novel 3D scene representation, using only 2D images without the need for any additional supervision signal such as masks or depths. This supports 3D reconstruction and generation in a unified architecture. Third, we develop a principled approach to avoid trivial 3D solutions when integrating the image-based rendering with the diffusion model, by dropping out representations of some images. We evaluate the model on several challenging datasets of real and synthetic images, and demonstrate superior results on generation, novel view synthesis and 3D reconstruction.

Foveation in the Era of Deep Learning

In this paper, we tackle the challenge of actively attending to visual scenes using a foveated sensor. We introduce an end-to-end differentiable foveated active vision architecture that leverages a graph convolutional network to process foveated images, and a simple yet effective formulation for foveated image sampling. Our model learns to iteratively attend to regions of the image relevant for classification. We conduct detailed experiments on a variety of image datasets, comparing the performance of our method with previous approaches to foveated vision while measuring how the impact of different choices, such as the degree of foveation, and the number of fixations the network performs, affect object recognition performance. We find that our model outperforms a state-of-the-art CNN and foveated vision architectures of comparable parameters and a given pixel or computation budget

Elucidating and Overcoming the Challenges of Label Noise in Supervised Contrastive Learning

Image classification datasets exhibit a non-negligible fraction of mislabeled examples, often due to human error when one class superficially resembles another. This issue poses challenges in supervised contrastive learning (SCL), where the goal is to cluster together data points of the same class in the embedding space while distancing those of disparate classes. While such methods outperform those based on cross-entropy, they are not immune to labeling errors. However, while the detrimental effects of noisy labels in supervised learning are well-researched, their influence on SCL remains largely unexplored. Hence, we analyse the effect of label errors and examine how they disrupt the SCL algorithm's ability to distinguish between positive and negative sample pairs. Our analysis reveals that human labeling errors manifest as easy positive samples in around 99% of cases. We, therefore, propose D-SCL, a novel Debiased Supervised Contrastive Learning objective designed to mitigate the bias introduced by labeling errors. We demonstrate that D-SCL consistently outperforms state-of-the-art techniques for representation learning across diverse vision benchmarks, offering improved robustness to label errors.

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. However, most existing approaches do not explicitly capture high-level semantic relations between distant regions, which limits their performance. In this paper, we focus on representation learning for semi-supervised learning, by developing a novel Multi-Scale Cross Supervised Contrastive Learning (MCSC) framework, to segment structures in medical images. We jointly train CNN and Transformer models, regularising their features to be semantically consistent across different scales. Our approach contrasts multi-scale features based on ground-truth and cross-predicted labels, in order to extract robust feature representations that reflect intra- and inter-slice relationships across the whole dataset. To tackle class imbalance, we take into account the prevalence of each class to guide contrastive learning and ensure that features adequately capture infrequent classes. Extensive experiments on two multi-structure medical segmentation datasets demonstrate the effectiveness of MCSC. It not only outperforms state-of-the-art semi-supervised methods by more than 3.0% in Dice, but also greatly reduces the performance gap with fully supervised methods.

Simulating analogue film damage to analyse and improve artefact restoration on high-resolution scans

Digital scans of analogue photographic film typically contain artefacts such as dust and scratches. Automated removal of these is an important part of preservation and dissemination of photographs of historical and cultural importance. While state-of-the-art deep learning models have shown impressive results in general image inpainting and denoising, film artefact removal is an understudied problem. It has particularly challenging requirements, due to the complex nature of analogue damage, the high resolution of film scans, and potential ambiguities in the restoration. There are no publicly available high-quality datasets of real-world analogue film damage for training and evaluation, making quantitative studies impossible. 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. We construct a larger synthetic dataset of damaged images with paired clean versions using a statistical model of artefact shape and occurrence learnt from real, heavily-damaged images. We carefully validate the realism of the simulated damage via a human perceptual study, showing that even expert users find our synthetic damage indistinguishable from real. In addition, we demonstrate that training with our synthetically damaged dataset leads to improved artefact segmentation performance when compared to previously proposed synthetic analogue damage. Finally, we use these datasets to train and analyse the performance of eight state-of-the-art image restoration methods on high-resolution scans. We compare both methods which directly perform the restoration task on scans with artefacts, and methods which require a damage mask to be provided for the inpainting of artefacts.

RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation

Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support tasks required for 3D understanding, such as view-consistent 3D generation or single-view object reconstruction. In this paper, we present RenderDiffusion as the first diffusion model for 3D generation and inference that can be trained using only monocular 2D supervision. At the heart of our method is a novel image denoising architecture that generates and renders an intermediate three-dimensional representation of a scene in each denoising step. This enforces a strong inductive structure into the diffusion process that gives us a 3D consistent representation while only requiring 2D supervision. The resulting 3D representation can be rendered from any viewpoint. We evaluate RenderDiffusion on ShapeNet and Clevr datasets and show competitive performance for generation of 3D scenes and inference of 3D scenes from 2D images. Additionally, our diffusion-based approach allows us to use 2D inpainting to edit 3D scenes. We believe that our work promises to enable full 3D generation at scale when trained on massive image collections, thus circumventing the need to have large-scale 3D model collections for supervision.

Determining band structure parameters of two-dimensional materials by deep learning

The field of two-dimensional materials has mastered the fabrication and characterisation of a broad range of novel high-quality compounds that feature increasing complexity. Determination of the band structure parameters of such complex materials is a major ingredient required for quantitative theory. This task currently presents a formidable challenge: ab initio methods often do not provide quantitatively accurate values of parameters, whereas inferring band structure parameters from experiments is hindered by the complexity of the band structure and indirect nature of experimental probes. In this work we propose a general framework for determination of band structure parameters from experimental data based on deep neural networks. As a specific example we apply our method to the penetration field capacitance measurement of trilayer graphene that effectively probes its density of states. First, we demonstrate that a trained deep network gives accurate predictions for the penetration field capacitance as a function of tight-binding parameters. 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. We conclude by discussing potential applications of our method to other materials and experimental techniques beyond penetration field capacitance.