Metraipolis › archive › dc_a9eb1960caea

Counterfactual Route Optimization for Gaussian Head Avatar Modeling — arXiv:2610.09791

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.09791
License (as archived)
CC0-1.0
Archived
2026-10-08T12:47:37.162Z
SHA-256 of the archived text
f6b2f686ed8c01422e8027029d5c606fabc932325bc86c53deb1791ba4282089
Stable URL of this page
https://metraipolis.com/documento/dc_a9eb1960caea

How to cite

Counterfactual Route Optimization for Gaussian Head Avatar Modeling — arXiv:2610.09791 — arXiv (en), https://arxiv.org/abs/2610.09791 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a9eb1960caea (Metraipolis archive dc_a9eb1960caea, sha256 f6b2f686ed8c01422e8027029d5c606fabc932325bc86c53deb1791ba4282089)
BibTeX
@misc{dca9eb1960caea,
  title = {Counterfactual Route Optimization for Gaussian Head Avatar Modeling — arXiv:2610.09791},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.09791},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a9eb1960caea; sha256 f6b2f686ed8c01422e8027029d5c606fabc932325bc86c53deb1791ba4282089},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.09791. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Head avatar modeling requires jointly optimizing multiple objectives with different dominant effects on geometry, appearance, and cross-view consistency. However, their relative effectiveness varies across training states, while existing pipelines typically rely on fixed loss weights or handcrafted stage-wise schedules. A central challenge is therefore to identify which optimization direction is more beneficial at each training state. We propose a counterfactual route optimization framework for Gaussian head avatar modeling, which characterizes state-dependent optimization preference from the realized effects of alternative updates rather than predefined heuristic weighting. Starting from the same training state, we perform short-horizon route-restricted lookahead over geometry, appearance, and joint update routes and evaluate their outcomes under a unified utility. The resulting counterfactual evidence is factorized into a geometry--appearance preference and a residual joint advantage, separately capturing the relative preference between individual update directions and the additional benefit of coordinated optimization. We further amortize this offline evidence into a lightweight controller that directly estimates the current optimization preference and applies bounded modulation to the training objectives during full avatar optimization. Experiments on the NeRSemble dataset validate the effectiveness of the proposed design, consistently outperforming existing methods while preserving clearer local facial structures and finer details.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.09791 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-08T12:18:15.415Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).