Despite all recent progress, it is still challenging to edit and manipulate natural images with modern generative models. When using Generative Adversarial Network (GAN), one major hurdle is in the inversion process mapping a real image to its corresponding noise vector in the latent space, since it is necessary to be able to reconstruct an image to edit its contents. Likewise for Denoising Diffusion Implicit Models (DDIM), the linearization assumption in each inversion step makes the whole deterministic inversion process unreliable. Existing approaches that have tackled the problem of inversion stability often incur in significant trade-offs in computational efficiency. In this work we propose an Accelerated Iterative Diffusion Inversion method, dubbed AIDI, that significantly improves reconstruction accuracy with minimal additional overhead in space and time complexity. By using a novel blended guidance technique, we show that effective results can be obtained on a large range of image editing tasks without large classifier-free guidance in inversion. Furthermore, when compared with other diffusion inversion based works, our proposed process is shown to be more robust for fast image editing in the 10 and 20 diffusion steps’ regimes.

Neural radiance fields (NeRF) have garnered significant attention, with recent works such as Instant-NGP accelerating NeRF training and evaluation through a combination of hashgrid-based positional encoding and neural networks. However, effectively leveraging the spatial sparsity of 3D scenes remains a challenge. To cull away unnecessary regions of the feature grid, existing solutions rely on prior knowledge of object shape or periodically estimate object shape during training by repeated model evaluations, which are costly and wasteful. To address this issue, we propose HollowNeRF, a novel compression solution for hashgrid-based NeRF which automatically sparsifies the feature grid during the training phase. Instead of directly compressing dense features, HollowNeRF trains a coarse 3D saliency mask that guides efficient feature pruning, and employs an alternating direction method of multipliers (ADMM) pruner to sparsify the 3D saliency mask during training. By exploiting the sparsity in the 3D scene to redistribute hash collisions, HollowNeRF improves rendering quality while using a fraction of the parameters of comparable state-of-the-art solutions, leading to a better cost-accuracy trade-off. Our method delivers comparable rendering quality to Instant-NGP, while utilizing just 31% of the parameters. In addition, our solution can achieve a PSNR accuracy gain of up to 1dB using only 56% of the parameters.

We introduce a precise deterministic approach for pixel-wise change detection in images taken of a scene of interest over time. Our motivation is for applications such as artefact condition monitoring and structural inspection, where a common problem is the need to efficiently and accurately identify subtle signs of damage and deterioration. The approach we describe is designed to compensate for the three most common sources of nuisance variation encountered when tackling the problem of change detection, namely: viewpoint variation due to camera motion between images, photometric variation due to lighting differences, and changes in image resolution/focal settings. To tackle viewpoint variation, particularly in areas of low texture, we propose the use of the generalised PatchMatch (PM) correspondence algorithm to compute a dense flow field. The flow field is regularized using a Thin Plate Spline (TPS) model which assumes a smooth underlying geometry and allows registration to be interpolated precisely through areas of low texture or uncertain flow. To compensate for low-frequency lighting variation, we fit a second TPS model to the photometric differences between registered images. Finally, to account for changes in focal settings, we estimate and apply a blurring kernel via optimisation over image differences. We provide a thorough evaluation of the performance of our method on an illustrative toy dataset and on two recent, real-world inspection datasets. Our approach performs favourably versus state-of-the-art baselines in both cases, while remaining relatively transparent to understand and simple to compute.

We describe a system for the detection of changes in multiple views of a tunnel surface. From data gathered by a robotic inspection rig, we use a structure-from-motion pipeline to build panoramas of the surface and register images from different time instances. Reliably detecting changes such as hairline cracks, water ingress and other surface damage between the registered images is a challenging problem: achieving the best possible performance for a given set of data requires sub-pixel precision and careful modelling of the noise sources. The task is further complicated by factors such as unavoidable registration error and changes in image sensors, capture settings and lighting. Our contribution is a novel approach to change detection using a two-channel convolutional neural network. The network accepts pairs of approximately registered image patches taken at different times and classifies them to detect anomalous changes. To train the network, we take advantage of synthetically generated training examples and the homogeneity of the tunnel surfaces to eliminate most of the manual labelling effort. We evaluate our method on field data gathered from a live tunnel over several months, demonstrating it to outperform existing approaches from recent literature and industrial practice.

We present a completely automated Structure and Motion pipeline capable of working with uncalibrated images with varying internal parameters and no ancillary information. The system is based on a novel hierarchical scheme which reduces the total complexity by one order of magnitude. We assess the quality of our approach analytically by comparing the recovered point clouds with laser scans, which serves as ground truth data.

We present a novel operator to be applied at raw matching costs in the context of low level vision tasks such as stereo matching or optical flow. It aims at improving matching reliability by efficiently modulating pixel-wise pairing costs, injecting a confidence backed bias before the aggregation step. It works analyzing a noisy estimate of the correspondances in order to favor or prune potential matches. We test the operator by developing a local, realtime stereo matching algorithm and showing that our solution can drastically clean the resulting depth map while also reducing border bleeding. Its good performance is also evaluated quantitavely by testing the algorithm against the popular Middlebury benchmark where our local greedy implementation is able to obtain results comparable to those of naive global approaches.