Metraipolis › archive › dc_451a85d22216
TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation — arXiv:2609.06665
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.06665
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T15:09:18.119Z
- SHA-256 of the archived text
e108cb4014fff7fc5ee6547eda59543a30237ae6bfd9d243a3e0351b1c22ec57- Stable URL of this page
https://metraipolis.com/documento/dc_451a85d22216
How to cite
TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation — arXiv:2609.06665 — arXiv (en), https://arxiv.org/abs/2609.06665 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_451a85d22216 (Metraipolis archive dc_451a85d22216, sha256 e108cb4014fff7fc5ee6547eda59543a30237ae6bfd9d243a3e0351b1c22ec57)
BibTeX
@misc{dc451a85d22216,
title = {TransNormal-2: Geometry-Grounded Rectified Flow with Edge-Aware Decoding for Precise Normal Estimation — arXiv:2609.06665},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.06665},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_451a85d22216; sha256 e108cb4014fff7fc5ee6547eda59543a30237ae6bfd9d243a3e0351b1c22ec57},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06665. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Diffusion-based models enable monocular geometry estimation, yet their pixel-space precision is limited by a shared, under-studied error source: VAE reconstruction degradation. The 8x spatial compression in the VAE encoder-decoder degrades surface normals at object boundaries; even encoding and decoding ground-truth normals introduces 1.3--8.5° of mean angular error (MAE), with edge MAE reaching 2.8x the global MAE. We present TransNormal-2, a FLUX.2-based rectified-flow framework with single-step deterministic inference that addresses this degradation on both sides of the VAE decoder: in how latent predictions are supervised during training, and in how decoded normals are corrected at inference. First, geometry-aware pixel-space losses, including inverse rendering self-consistency, von~Mises-Fisher angular loss, and wavelet edge-aware regularization, complement latent MSE by enforcing spherical normal geometry and diffuse image-formation cues after VAE decoding. Second, a lightweight Geometric Refinement Module (GRM) applies an RGB-guided residual correction to reduce boundary-localized decoding errors without freely rewriting the coarse prediction. On general-scene benchmarks, TransNormal-2 matches or exceeds MoGe-2 on all eight reported metrics while using only 1.4% as many task-specific normal annotations. The gains are clearest for transparent objects, reducing MAE by 4.2° on ClearGrasp and 3.1° on ClearPose over the strongest prior baselines. Code will be released at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.06665 — 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 2026-10-16T14:49:57.115Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).