Related papers: SynopSet: Multiscale Visual Abstraction Set for Ex…
In several domains, data objects can be decomposed into sets of simpler objects. It is then natural to represent each object as the set of its components or parts. Many conventional machine learning algorithms are unable to process this…
Many motion-centric video analysis tasks, such as atomic actions, detecting atypical motor behavior in individuals with autism, or analyzing articulatory motion in real-time MRI of human speech, require efficient and interpretable temporal…
Data-driven methods such as convolutional neural networks (CNNs) are known to deliver state-of-the-art performance on image recognition tasks when the training data are abundant. However, in some instances, such as change detection in…
DNA methylation (DNAme) is a critical component of the epigenetic regulatory machinery and aberrations in DNAme patterns occur in many diseases, such as cancer. Mapping and understanding DNAme profiles offers considerable promise for…
The task of dimensionality reduction and visualization of high-dimensional datasets remains a challenging problem since long. Modern high-throughput technologies produce newer high-dimensional datasets having multiple views with relatively…
Dataset distillation compresses large training sets into compact synthetic datasets while preserving downstream performance. As modern systems increasingly operate on paired vision-language inputs, multimodal distillation must preserve…
Recovering 3D information from scenes via multi-view stereo reconstruction (MVS) and novel view synthesis (NVS) is inherently challenging, particularly in scenarios involving sparse-view setups. The advent of 3D Gaussian Splatting (3DGS)…
We propose VDL-Surrogate, a view-dependent neural-network-latent-based surrogate model for parameter space exploration of ensemble simulations that allows high-resolution visualizations and user-specified visual mappings. Surrogate-enabled…
Dense 3D reconstruction and tracking of dynamic scenes from monocular video remains an important open challenge in computer vision. Progress in this area has been constrained by the scarcity of high-quality datasets with dense, complete,…
Novel View Synthesis (NVS) from unconstrained photo collections is challenging in computer graphics. Recently, 3D Gaussian Splatting (3DGS) has shown promise for photorealistic and real-time NVS of static scenes. Building on 3DGS, we…
Phase-field modeling is an effective but computationally expensive method for capturing the mesoscale morphological and microstructure evolution in materials. Hence, fast and generalizable surrogate models are needed to alleviate the cost…
In the realm of object pose estimation, scenarios involving both dynamic objects and moving cameras are prevalent. However, the scarcity of corresponding real-world datasets significantly hinders the development and evaluation of robust…
When studying multi-body protein complexes, biochemists use computational tools that can suggest hundreds or thousands of their possible spatial configurations. However, it is not feasible to experimentally verify more than only a very…
We present MSeg, a composite dataset that unifies semantic segmentation datasets from different domains. A naive merge of the constituent datasets yields poor performance due to inconsistent taxonomies and annotation practices. We reconcile…
Various data visualization applications such as reverse engineering and interactive authoring require a vocabulary that describes the structure of visualization scenes and the procedure to manipulate them. A few scene abstractions have been…
Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Recent studies have…
Recently, Fully Convolutional Network (FCN) seems to be the go-to architecture for image segmentation, including semantic scene parsing. However, it is difficult for a generic FCN to discriminate pixels around the object boundaries, thus…
This paper proposes a technique for efficiently modeling dynamic humans by explicifying the implicit neural fields via a Neural Explicit Surface (NES). Implicit neural fields have advantages over traditional explicit representations in…
Satellite Image Time Series (SITS) representation learning is complex due to high spatiotemporal resolutions, irregular acquisition times, and intricate spatiotemporal interactions. These challenges result in specialized neural network…
Open-set semantic mapping enables language-driven robotic perception, but current instance-centric approaches are bottlenecked by context-depriving and computationally expensive crop-based feature extraction. To overcome this fundamental…