Metraipolis › archive › dc_caad97c77333
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation — arXiv:2609.08084
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08084
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T13:59:25.545Z
- SHA-256 of the archived text
85f3743450fc039ad8c8d7a9ae76afe18bca99c340ba6a28c5c8cf4e8cb87529- Stable URL of this page
https://metraipolis.com/documento/dc_caad97c77333
How to cite
Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation — arXiv:2609.08084 — arXiv (en), https://arxiv.org/abs/2609.08084 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_caad97c77333 (Metraipolis archive dc_caad97c77333, sha256 85f3743450fc039ad8c8d7a9ae76afe18bca99c340ba6a28c5c8cf4e8cb87529)
BibTeX
@misc{dccaad97c77333,
title = {Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation — arXiv:2609.08084},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08084},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_caad97c77333; sha256 85f3743450fc039ad8c8d7a9ae76afe18bca99c340ba6a28c5c8cf4e8cb87529},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08084. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Monocular depth estimation is a ubiquitous yet highly ill-posed computer vision task, with downstream applications in scene reconstruction, computational photography, and robotics, among others. Despite the field's maturity, recent models still struggle to generalize to out-of-distribution inputs and to produce sharp and detailed depth maps. In this paper, we revisit Marigold, a set of techniques for repurposing modern image generation and editing models, powered by the diffusion transformer (DiT) architecture, into state-of-the-art monocular depth estimators. Our recipes target single-step inference from pretrained multi-step flow-matching models, with quantization where needed, preserving model capacity while remaining cheap to run. We analyze the artifacts of naive training and identify two effective remedies: aligning the model's internal representations with semantic features extracted from ground-truth, and adopting a 2-stage fine-tuning protocol built around a novel Sinkhorn-based loss. The results are crisper, cleaner depth maps that generalize well out-of-distribution, with 16-26% improvement in AbsRel over the previous best on KITTI and ETH3D. Qualitatively, our model resolves fur, foliage, and hair-thin edges that have eluded prior models. Furthermore, Marigold V2 achieves state-of-the-art results when applied to other dense regression tasks, such as surface normals estimation and intrinsic image decomposition. Project website: this https URL Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.08084 — 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 2026-10-16T13:39:43.253Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).