Spline Deformation Field

TL;DR

This paper introduces a spline-based deformation field model for trajectory modeling that improves spatial coherence, enables efficient velocity derivation, and enhances temporal interpolation in dynamic scene reconstruction.

Contribution

The paper proposes a novel spline-based trajectory representation with explicit knots and a low-rank time-variant encoding, addressing limitations of neural implicit models.

Findings

Superior temporal interpolation performance with sparse inputs

Enhanced motion coherence without heuristic-based methods

Competitive scene reconstruction quality

Abstract

Trajectory modeling of dense points usually employs implicit deformation fields, represented as neural networks that map coordinates to relate canonical spatial positions to temporal offsets. However, the inductive biases inherent in neural networks can hinder spatial coherence in ill-posed scenarios. Current methods focus either on enhancing encoding strategies for deformation fields, often resulting in opaque and less intuitive models, or adopt explicit techniques like linear blend skinning, which rely on heuristic-based node initialization. Additionally, the potential of implicit representations for interpolating sparse temporal signals remains under-explored. To address these challenges, we propose a spline-based trajectory representation, where the number of knots explicitly determines the degrees of freedom. This approach enables efficient analytical derivation of velocities, preserving spatial coherence and accelerations, while mitigating temporal fluctuations. To model knot characteristics in both spatial and temporal domains, we introduce a novel low-rank time-variant spatial encoding, replacing conventional coupled spatiotemporal techniques. Our method demonstrates superior performance in temporal interpolation for fitting continuous fields with sparse inputs. Furthermore, it achieves competitive dynamic scene reconstruction quality compared to state-of-the-art methods while enhancing motion coherence without relying on linear blend skinning or as-rigid-as-possible constraints.