Metraipolis › archive › dc_2df1112a2e30

Cyc3D: Evaluating Cyclic Structural Stability and Asset Usability in Image-to-3D Generation — arXiv:2608.28080

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28080
License (as archived)
CC0-1.0
Archived
2026-10-17T11:33:08.757Z
SHA-256 of the archived text
0b6db448fa2a623958911a4685de9b6a3f54a174ed9685649e8e55724a9561fd
Stable URL of this page
https://metraipolis.com/documento/dc_2df1112a2e30

How to cite

Cyc3D: Evaluating Cyclic Structural Stability and Asset Usability in Image-to-3D Generation — arXiv:2608.28080 — arXiv (en), https://arxiv.org/abs/2608.28080 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2df1112a2e30 (Metraipolis archive dc_2df1112a2e30, sha256 0b6db448fa2a623958911a4685de9b6a3f54a174ed9685649e8e55724a9561fd)
BibTeX
@misc{dc2df1112a2e30,
  title = {Cyc3D: Evaluating Cyclic Structural Stability and Asset Usability in Image-to-3D Generation — arXiv:2608.28080},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28080},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2df1112a2e30; sha256 0b6db448fa2a623958911a4685de9b6a3f54a174ed9685649e8e55724a9561fd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28080. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Image-conditioned 3D generation has advanced rapidly, yet existing evaluation protocols largely judge rendered-view plausibility and semantic alignment, overlooking whether a generator forms a stable 3D interpretation and produces assets usable in graphics pipelines. We introduce Cyc3D, a multidimensional benchmark that evaluates image-to-3D generation along two complementary axes: Cross-View Object Consistency and Representation Quality. At the asset level, Cyc3D measures whether object identity remains semantically coherent across rendered viewpoints. At the model level, we propose View-Cycle Structural Consistency, a closed-loop render-regenerate-align protocol that repeatedly re-observes a generated asset from novel views and quantifies geometric, perceptual, and semantic drift across generations. To assess native asset usability beyond rendered appearance, Cyc3D further evaluates geometric structure, reference-image fidelity, mesh discretization and efficiency, and UV parameterization quality. Together, these diagnostics expose failures obscured by a single perceptual score and provide interpretable evidence of both model instability and representation defects. Experiments on five representative image-to-3D systems show that closed-source feed-forward models consistently outperform open-source optimization-based baselines in geometric fidelity, mesh quality, and cycle stability. Nevertheless, even the strongest methods achieve cycle-stability scores below 48, revealing a persistent gap between visually plausible generation and robust 3D object understanding.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-31 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.28080 — 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 2026-10-17T11:10:05.301Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-31?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).