Related papers: Thermoxels: a voxel-based method to generate simul…
We present a novel way of approaching image-based 3D reconstruction based on radiance fields. The problem of volumetric reconstruction is formulated as a non-linear least-squares problem and solved explicitly without the use of neural…
Fracture produces new mesh fragments that introduce additional degrees of freedom in the system dynamics. Existing finite element method (FEM) based solutions suffer from an explosion in computational cost as the system matrix size…
A study on a parametrized model of a composite barrier FTJ (three-interface system, with a non-polar dielectric layer) under an external bias voltage and at room temperature, using FEM-based simulations, was performed. The approach involves…
We introduce a new machine learning approach for image segmentation that uses a neural network to model the conditional energy of a segmentation given an image. Our approach, combinatorial energy learning for image segmentation (CELIS)…
A new approach is introduced to significantly improve the performance of thermophotovoltaic (TPV) systems by using low-dimensional thermal emitters and photovoltaic (PV) cells. By reducing the thickness of both the emitter and the PV cell,…
Vision processing on traditional architectures is inefficient due to energy-expensive off-chip data movement. Many researchers advocate pushing processing close to the sensor to substantially reduce data movement. However, continuous…
Finite Element Analysis (FEA) is a powerful but computationally intensive method for simulating physical phenomena. Recent advancements in machine learning have led to surrogate models capable of accelerating FEA. Yet there are still…
In this work, we reveal the limitations of visual tokenizers and VAEs in preserving fine-grained features, and propose a benchmark to evaluate reconstruction performance for two challenging visual contents: text and face. Visual tokenizers…
Replica exchange (REX) is one of the most widely used enhanced sampling methodologies, yet its efficiency is limited by the requirement for a large number of intermediate temperature replicas. Here we present Generative Replica Exchange…
Accurate face recognition systems are increasingly important in sensitive applications like border control or migration management. Therefore, it becomes crucial to quantify the quality of facial images to ensure that low-quality images are…
In this report, we introduce UltraShape 1.0, a scalable 3D diffusion framework for high-fidelity 3D geometry generation. The proposed approach adopts a two-stage generation pipeline: a coarse global structure is first synthesized and then…
Ultra-high-resolution image generation poses great challenges, such as increased semantic planning complexity and detail synthesis difficulties, alongside substantial training resource demands. We present UltraPixel, a novel architecture…
Accurate thermal analysis is crucial for modern spacecraft, driving demand for reliable modeling tools. This research advances space thermal modeling by improving the simulation accuracy and efficiency of radiative heat transfer, the…
We present VoxScene, a novel anchor-conditioned voxel diffusion framework tailored for 3D scene synthesis. Current data-driven layout generation techniques typically rely on bounding proxies or implicit representations, which overlook…
Buildings rarely perform as designed/simulated and and there are numerous tangible benefits if this gap is reconciled. A new scientific yet pragmatic methodology - called Enhanced Parameter Estimation (EPE) - is proposed that allows…
The Copernicus Regional Reanalysis for Europe, CERRA, is a high-resolution regional reanalysis dataset for the European domain. In recent years it has shown significant utility across various climate-related tasks, ranging from forecasting…
Recent generative video models achieve impressive visual quality but remain constrained by limited physical consistency and controllability. Existing video generation methods provide minimal physical control, and single-image-to-3D…
Over the last few decades, image-based building surface reconstruction has garnered substantial research interest and has been applied across various fields, such as heritage preservation, architectural planning, etc. Compared to the…
We present a novel pipeline for learning the conditional distribution of a building roof mesh given pixels from an aerial image, under the assumption that roof geometry follows a set of regular patterns. Unlike alternative methods that…
Recent advances in bioimaging have provided scientists a superior high spatial-temporal resolution to observe dynamics of living cells as 3D volumetric videos. Unfortunately, the 3D biomedical video analysis is lagging, impeded by resource…