Metraipolis › archive › dc_1e6552b587dd
TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration — arXiv:2608.10286
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.10286
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T06:30:10.907Z
- SHA-256 of the archived text
fd0bff30132af82aee7447cbf7d0fc194f033cfaf95956a2379af74c17e7ed2c- Stable URL of this page
https://metraipolis.com/documento/dc_1e6552b587dd
How to cite
TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration — arXiv:2608.10286 — arXiv (en), https://arxiv.org/abs/2608.10286 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_1e6552b587dd (Metraipolis archive dc_1e6552b587dd, sha256 fd0bff30132af82aee7447cbf7d0fc194f033cfaf95956a2379af74c17e7ed2c)
BibTeX
@misc{dc1e6552b587dd,
title = {TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration — arXiv:2608.10286},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.10286},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_1e6552b587dd; sha256 fd0bff30132af82aee7447cbf7d0fc194f033cfaf95956a2379af74c17e7ed2c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.10286. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We present TRACE-GS, an on-policy trajectory distillation framework that leverages privileged geometric conditioning at training time, thereby adapting a diffusion prior to sparse-view 3D Gaussian Splatting (3DGS) restoration. Rather than pursuing increasingly sophisticated restoration architectures, we identify a more fundamental limitation shared by existing diffusion-based approaches: supervision at independently noised states does not cover those reached during inference. In sparse-view 3DGS, under-constrained geometry biases denoising from the outset, and the resulting deviations compound along the rollout. TRACE-GS instead performs on-policy trajectory distillation: a teacher conditioned on richer geometry from additional training views supplies targets along the sparse-view student's own rollout, aligning denoising directions and cross-view responses at each visited state. This training-only geometry places TRACE-GS in the learning using privileged information (LUPI) setting. At deployment, only the sparse-view student is retained, and its restored renderings serve as pseudo-observations for 3DGS refinement. To the best of our knowledge, TRACE-GS is the first to derive on-policy supervision from privileged geometry for sparse-view 3DGS restoration, achieving consistent gains and strong generalization across datasets and sparse-view settings. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-12 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.10286 — 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 2026-10-19T06:25:27.238Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-12?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).