AncesTrA: Streamable Long-Horizon Volumetric Reconstruction via Canonical Transport Lineages and Asymmetric Basis Lifting

Long-horizon volumetric video reconstruction requires compact and temporal modeling that remains faithful as scene evolution grows increasingly complex. Existing streamable representations either recursively propagate reconstructed states, coupling temporal continuity with accumulated errors, or rely on persistent references whose validity deteriorates as scenes diverge; symmetric Gaussian bases further limit local expressivity near discontinuities. We introduce $\text{AncesTrA}$, a streamable volumetric representation that recasts long-horizon evolution as $\text{structured inheritance along canonical transport lineages}$. $\text{Canonical Transport Inheritance with Entropy-Coded Residuals (CiTER)}$ separates reconstruction from temporal propagation by evolving compact transport states over a shared canonical representation, enabling efficient temporal $\text{compression}$. $\text{Transport-regime-aware Canonical Expiration and Reanchoring (TraCER)}$ regulates canonical validity by reanchoring evolution when transport dynamics indicate expiration, preserving long-horizon $\text{stability}$. $\text{Conditional Asymmetric Basis Lifting for Expressivity (CaBLE)}$ selectively lifts symmetric Gaussian bases into asymmetric forms around geometric and appearance discontinuities, increasing local expressivity without increasing anchor density. Extensive experiments demonstrate state-of-the-art reconstruction fidelity: $\text{AncesTrA}$ outperforms Recon-GS by approximately $\text{2 dB}$ with $9\times$ lower storage on short sequences, and by approximately $\text{5 dB}$ with $6\times$ lower storage on long-horizon sequences. The widening advantage with temporal extent substantiates canonical transport lineages as a principled alternative to recursive scene-state propagation, positioning $\text{AncesTrA}$ as a substantive reformulation of how temporal evolution is organized in streamable volumetric representations.