Spline Deformation Field
This addresses trajectory modeling challenges in computer vision/graphics, offering a more interpretable and coherent alternative to neural network-based deformation fields, though it appears incremental in improving existing techniques.
The paper tackles the problem of modeling dense point trajectories by proposing a spline-based representation that explicitly controls degrees of freedom with knots, enabling efficient analytical derivation of velocities and accelerations while preserving spatial coherence. The method achieves superior temporal interpolation with sparse inputs and competitive dynamic scene reconstruction quality compared to state-of-the-art methods.
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.