Paper Detail

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

huggingface Score 5.4

Published 2026-09-08 · First seen 2026-09-09

General AI

Abstract

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

Workflow Status

Review status
pending
Role
unreviewed
Read priority
later
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@misc{pavlovic2026marigold,
  title = {Marigold V2: Revisiting Diffusion Transformers for Monocular Depth Estimation},
  author = {Igor Pavlovic and Thiemo Wandel and Anton Obukhov and Luca Bartolomei and Andrey Davydov and Fabio Tosi and Matteo Poggi and Sabine Süsstrunk and Dengxin Dai},
  year = {2026},
  abstract = {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 (Di},
  url = {https://huggingface.co/papers/2609.08084},
  keywords = {monocular depth estimation, diffusion transformer, DiT, flow-matching, quantization, Sinkhorn-based loss, two-stage fine-tuning, surface normals estimation, intrinsic image decomposition, code available, huggingface daily},
  eprint = {2609.08084},
  archiveprefix = {arXiv},
}

Metadata

{}