EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation

Igor Pavlovic, Thiemo Wandel, Anton Obukhov, Luca Bartolomei, Andrey Davydov, Fabio Tosi, Matteo Poggi, Sabine Süsstrunk, Dengxin Dai

ACM Transactions on Graphics · 09.11.2026 · 45 (6) · 1-15

DOI: 10.1145/3842528 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Graphics, online erschienen am 09.11.2026. Verfasst von Igor Pavlovic und 8 weiteren Autor:innen. Die Arbeit nennt 98 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

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 naïve 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: https://hf.co/spaces/huawei-bayerlab/marigold-v2-web.

Zitieren

APA

Pavlovic, I., Wandel, T., Obukhov, A., Bartolomei, L., Davydov, A., Tosi, F., Poggi, M., Süsstrunk, S., & Dai, D. (2026). Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation. ACM Transactions on Graphics, 45(6), 1-15. https://doi.org/10.1145/3842528

Vancouver

Pavlovic I, Wandel T, Obukhov A, Bartolomei L, Davydov A, Tosi F, et al. Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation. ACM Transactions on Graphics. 2026;45(6):1-15. doi:10.1145/3842528

BibTeX
@article{Pavlovic2026,
  author = {Pavlovic, Igor and Wandel, Thiemo and Obukhov, Anton and Bartolomei, Luca and Davydov, Andrey and Tosi, Fabio and Poggi, Matteo and Süsstrunk, Sabine and Dai, Dengxin},
  title = {Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation},
  journal = {ACM Transactions on Graphics},
  year = {2026},
  volume = {45},
  number = {6},
  pages = {1--15},
  doi = {10.1145/3842528}
}
Kostenlos starten →