Searcharxiv⌕ Search

arXiv subjects

Danielle Beaulieu

Publications and source records attributed to Danielle Beaulieu.

3 recordsLinked to original sources

X Marks the Spot: Diffusion for Image Geolocalization with Location Representations

Image geolocalization predicts the location at which a photo was taken. Accurate geolocalization requires discriminating between both physically and semantically adjacent areas on Earth. However, prior diffusion-based approaches predict locations by generating coordinates, which are semantically unstable over space. We avoid this limitation by learning geolocalization behavior in the pretrained representation spaces of location encoders, which provide both positional and semantic understanding. To make this space usable for coordinate prediction, we introduce a Location Autoencoder (LAE), which pairs a frozen location encoder with a learned decoder mapping embeddings back to coordinates with kilometer-level accuracy worldwide. In the LAE space, we train DIG, a latent diffusion model that transports noise to location embeddings conditioned on image features. DIG consistently outperforms coordinate-based generative models and sets a new state of the art for parametric geolocalization on three benchmarks: OSV-5M, Im2GPS3k, and YFCC4k. Notably, DIG is the first generative model to outperform retrieval-based methods, and further improves retrieve-and-rerank systems when used as a prior. Code and models will be released.

cs.CV↗

Trajectory-aware Cross-view Geo-localization with Sequential Observations

Cross-view geo-localization matches ground-level observations against geo-tagged satellite imagery. Recent methods show that sequential queries such as video clips yield richer spatiotemporal cues than single images, yet they overlook a complementary sequential modality: route descriptions -- which capture the same trajectory at a higher level of abstraction and are often the only input available (e.g., a user directing an autonomous vehicle to a pickup point). To bridge this gap, we introduce SeqGeo-VL, a dataset of $\sim$39K video-text-satellite triplets, and TrajLoc, a unified framework capable of processing both video clips and route descriptions. By leveraging both dense visual and abstract linguistic semantics, TrajLoc enables these modalities to mutually reinforce cross-view matching. We further propose TrajMod, a lightweight module that conditions query embeddings on trajectory geometry, yielding spatially-aware representations. Experiments show that TrajLoc achieves substantial gains over state-of-the-art methods on both video and text geo-localization. The project page is available at https://humblegamer.github.io/trajloc/.

cs.CV↗

The hidden sustainability bottleneck in high-entropy alloy design

Because of the enormous number of possible compositions, comparable to the number of stars in the universe, high-entropy alloys (HEAs) constitute a virtually inexhaustible materials space with highly versatile properties. Among these systems, HEAs are often proposed as potential substitutes for critical elements such as rare earths or platinum group metals. However, random or incremental exploration strategies are neither practical nor efficient at this scale. Targeted materials selection guided by sustainability considerations is therefore essential, yet identifying sustainable HEA compositions remains highly challenging. Here, we perform a comprehensive sustainability assessment of 30,201 equimolar HEA compositions and identify a resilient shortlist (approximately 5\%) that consistently exhibits favorable sustainability profiles across multiple evaluation schemes. Our analysis integrates complementary criteria including carbon footprint, environmental, social and governance (ESG) risks, production compatibility, and resource availability. The resulting sustainability-based ranking provides a strategic roadmap for HEA research, enabling experimental efforts to be focused on compositions that are not only functionally promising but also scalable and resource-responsible. By aligning materials discovery with sustainability and supply constraints, this framework supports more efficient use of experimental resources while contributing to long-term industrial sustainability goals.

physics.soc-ph↗