홈 › Papers

Need for Speed: Zero-Shot Depth Completion with Single-Step Diffusion

2026-03-11 · Jakub Gregorek, Paraskevas Pegios, Nando Metzger, Konrad Schindler, Theodora Kontogianni, Lazaros Nalpantidis arxiv

We introduce Marigold-SSD, a single-step, late-fusion depth completion framework that leverages strong diffusion priors while eliminating the costly test-time optimization typically associated with diffusion-based methods. By shifting computational burden from inference to finetuning, our approach enables efficient and robust 3D perception under real-world latency constraints. Marigold-SSD achieves significantly faster inference with a training cost of only 4.5 GPU days. We evaluate our method across four indoor and two outdoor benchmarks, demonstrating strong cross-domain generalization and zero-shot performance compared to existing depth completion approaches. Our approach significantly narrows the efficiency gap between diffusion-based and discriminative models. Finally, we challenge common evaluation protocols by analyzing performance under varying input sparsity levels. Page: https://dtu-pas.github.io/marigold-ssd/

📄 PDF Abstract BibTeX arXiv:2603.10584

Code (0)

등록된 구현이 없습니다.

Tasks

Domain Generalization Depth Completion

Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion

2024-12-18 · Massimiliano Viola, Kevin Qu, Nando Metzger, Bingxin Ke 외

Depth completion upgrades sparse depth measurements into dense depth maps guided by a conventional image. Existing methods for this highly ill-posed task operate in tightly constrained settings and tend to struggle when …

Denoising Depth Completion Depth Estimation Monocular Depth Estimation+1

GenPC: Zero-shot Point Cloud Completion via 3D Generative Priors

2025-02-27 · CVPR 2025 1 · An Li, Zhe Zhu, Mingqiang Wei

Existing point cloud completion methods, which typically depend on predefined synthetic training datasets, encounter significant challenges when applied to out-of-distribution, real-world scans. To overcome this limitati…

3D Generation Image to 3D Point Cloud Completion

Cross-View Completion Models are Zero-shot Correspondence Estimators

2024-12-12 · CVPR 2025 1 · Honggyu An, Jinhyeon Kim, Seonghoon Park, Jaewoo Jung 외

In this work, we explore new perspectives on cross-view completion learning by drawing an analogy to self-supervised correspondence learning. Through our analysis, we demonstrate that the cross-attention map within cross…

Decoder Depth Estimation Geometric Matching

Efficient Test-Time Optimization for Depth Completion via Low-Rank Decoder Adaptation

2026-03-02 · Minseok Seo, Wonjun Lee, Jaehyuk Jang, Changick Kim arxiv

Zero-shot depth completion has gained attention for its ability to generalize across environments without sensor-specific datasets or retraining. However, most existing approaches rely on diffusion-based test-time optimi…

Test-time Adaptation Depth Completion

SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps

2024-09-16 · Jakub Gregorek, Lazaros Nalpantidis

Even if the depth maps captured by RGB-D sensors deployed in real environments are often characterized by large areas missing valid depth measurements, the vast majority of depth completion methods still assumes depth va…

Denoising Depth Completion valid