Search

Modern machine learning techniques have shown tremendous potential, especially for object detection on camera images. For this reason, they are also used to enable safety-critical automated processes such as autonomous drone flights. We present a study on object detection for Detect and Avoid, a safety critical function for drones that detects air traffic during automated flights for safety reasons. An ill-posed problem is the generation of good and especially large data sets, since detection itself is the corner case. Most models suffer from limited ground truth in raw data, \eg recorded air traffic or frontal flight with a small aircraft. It often leads to poor and critical detection rates. We overcome this problem by using inpainting methods to bootstrap the dataset such that it explicitly contains the corner cases of the raw data. We provide an overview of inpainting methods and generative models and present an example pipeline given a small annotated dataset. We validate our method by generating a high-resolution dataset, which we make publicly available and present it to an independent object detector that was fully trained on real data.

We derive methods to compute higher order differentials (Hessians and Hessian-vector products) of the rendering operator. Our approach is based on importance sampling of a convolution that represents the differentials of rendering parameters and shows to be applicable to both rasterization and path tracing. We further suggest an aggregate sampling strategy to importance-sample multiple dimensions of one convolution kernel simultaneously. We demonstrate that this information improves convergence when used in higher-order optimizers such as Newton or Conjugate Gradient relative to a gradient descent baseline in several inverse rendering tasks.

Decomposing 3D assets into material parts is a common task for artists and creators, yet remains a highly manual process. In this work, we introduce Select Any Material (SAMa), a material selection approach for various 3D representations. Building on the recently introduced SAM2 video selection model, we extend its capabilities to the material domain. We leverage the model's cross-view consistency to create a 3D-consistent intermediate material-similarity representation in the form of a point cloud from a sparse set of views. Nearest-neighbour lookups in this similarity cloud allow us to efficiently reconstruct accurate continuous selection masks over objects' surfaces that can be inspected from any view. Our method is multiview-consistent by design, alleviating the need for contrastive learning or feature-field pre-processing, and performs optimization-free selection in seconds. Our approach works on arbitrary 3D representations and outperforms several strong baselines in terms of selection accuracy and multiview consistency. It enables several compelling applications, such as replacing the diffuse-textured materials on a text-to-3D output, or selecting and editing materials on NeRFs and 3D-Gaussians., Comment: Project Page: https://mfischer-ucl.github.io/sama

The quadrupole coupling constant $C_{\text{Q}}$ and the asymmetry parameter $\eta$ of the aluminium nuclei in two polymorphs of the complex aluminium hydride CsAlH4 are determined from both $^{27}$Al MAS NMR spectra and $^{27}$Al NMR spectra recorded for stationary samples by using the Solomon echo sequence. The accuracy with which these parameters can be determined from the static spectra (CsAlH4(o): $C_{\text{Q}}=(1.42\pm0.01)$ MHz, $\eta=(0.62\pm0.01)$ and CsAlH4(t): $C_{\text{Q}}=(1.43\pm0.02)$ MHz, $\eta<0.03$) seems to be slightly higher than via the MAS approach. The experimentally determined parameters ($\delta_{\text{iso}}$, $C_{\text{Q}}$ and $\eta$) are compared with those obtained from DFT-GIPAW (density functional theory - gauge-including projected augmented wave) calculations. When using DFT-optimized structures, the magnitude of the quadrupole coupling constant is overestimated by about 45% for both polymorphs. Further calculations in which the geometry of the AlH4 tetrahedra was varied show a high sensitivity of $C_{\text{Q}}$ on the H--Al--H angles in particular. Modest changes in the angles on the order of one to three degrees are sufficient to achieve near-perfect agreement between GIPAW calculations and experiment. The deviations found for the DFT-optimized structures are explained with the neglect of thermal motion, which typically leads to a reduction of distortions of the AlH4 tetrahedra. From a broader perspective, the uncertainty in the positions of the hydrogen atoms renders the accurate reproduction or prediction of quadrupole coupling constants for aluminium hydrides challenging., Comment: 30 pages, 8 figures

A Neural Radiance Field (NeRF) encodes the specific relation of 3D geometry and appearance of a scene. We here ask the question whether we can transfer the appearance from a source NeRF onto a target 3D geometry in a semantically meaningful way, such that the resulting new NeRF retains the target geometry but has an appearance that is an analogy to the source NeRF. To this end, we generalize classic image analogies from 2D images to NeRFs. We leverage correspondence transfer along semantic affinity that is driven by semantic features from large, pre-trained 2D image models to achieve multi-view consistent appearance transfer. Our method allows exploring the mix-and-match product space of 3D geometry and appearance. We show that our method outperforms traditional stylization-based methods and that a large majority of users prefer our method over several typical baselines., Comment: Project page: https://mfischer-ucl.github.io/nerf_analogies/