Article

Adaptive Keyframe Selection and Reconstruction for Volumetric Density Field Sequences Using Structural Descriptors

2026-07-15

Abstract excerpt

<title>Abstract</title> <p>In this paper, we propose a structural descriptor-based optimal keyframe selection method for efficiently summarizing important temporal states in volumetric density field sequences. Conventional keyframe selection approaches are typically limited to data with explicit structural correspondences, such as human motion data with articulated skeletons, or rely on local features of individu...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 4b532903-c3b8-58b1-950e-acb52efeb656
DOI: 10.21203/rs.3.rs-10057198/v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Adaptive Keyframe Selection and Reconstruction for Volumetric Density Field Sequences Using Structural DescriptorsDOI 10.21203/rs.3.rs-10057198/v1Read

A Spatiotemporal Bidirectional Mamba Network with Global–Local Skeletal Enhancement for 3D Human Pose EstimationSemantic proximity Read

Towards Human-Centered and Efficient Video Synthesis: A Survey of Multimodal Diffusion ModelsSemantic proximity Read

Temporal Estimation of Non-Rigid Dynamic Point Cloud Sequence using 3D Skeleton-based Deformation for CompressionSemantic proximity Read

A Latent Space Diffusion Transformer for High-Quality Video Frame InterpolationSemantic proximity Read

Skeleton Motion Super-Resolution via Masked CP Decomposition in Latent Embedding SpaceSemantic proximity Read

Time-Varying Coronary Artery Deformation: A Dynamic Skinning Framework for Coronary Intervention Planning and TrainingSemantic proximity Read

A Novel Detection of Tibiofemoral Joint Kinematical Space using Graph-based Model of 3D Point Cloud SequencesSemantic proximity Read

DeepGaitLab: Accurate and Flexible Markerless Motion Tracking Powered by Synthetic DataSemantic proximity Read

Enhancing Human Motion Prediction through Joint-based Analysis and AVI Video ConversionSemantic proximity Read

OrthoFusion: A Super-Resolution Algorithm to Fuse Orthogonal CT VolumesSemantic proximity Read

VectorDiff: A Manifesto for a Differential, Semantically Rich Vector Animation Format for Scientific and AI-Driven VisualizationSemantic proximity Read

Monocular 3D Human Pose-Estimation Networks for Coherent Humanoid-Model DrivingSemantic proximity Read