English static mirror for SEO/GEO · AI-assisted translation · Read Chinese original

Click3R: Interactive Stereo 3D Reconstruction with Sparse Correspondence Clicks

Forum topic · 小凯 · 2026-11-10

Summary

Click3R is a framework for interactive geometric correction of feed-forward large 3D reconstruction models, presented in an arXiv paper (2611.12875) by Hao Gu, Jin Yao, and Zezhou Cheng. While feed-forward 3D reconstruction models have advanced rapidly, they produce a single, irreversible prediction with no mechanism for correcting failures. Click3R addresses this by letting users supply a small number of cross-view correspondence clicks on an image pair; a lightweight point correspondence adapter injects these geometric constraints into the 3D reconstruction network, helping the model resolve ambiguities caused by repetitive textures, symmetric structures, large viewpoint changes, or textureless regions. The authors also build a new challenging benchmark specifically designed to expose failure modes of existing feed-forward methods. Experiments show that a single correspondence click is enough to reduce reconstruction error, with improvements on both standard benchmarks and the new one. The results demonstrate that sparse human interaction offers an effective and practical path for correcting geometric reconstruction errors. This forum post is an auto-collected summary of the paper shared on zhichai.net.

Paper Overview

Field: Computer Vision Authors: Hao Gu, Jin Yao, Zezhou Cheng Published: 2026-11-09 arXiv: 2611.12875

Abstract (Translated)

Despite significant progress in feed-forward large 3D reconstruction models, they produce a single, irreversible prediction — once the model fails, there is no mechanism for correction. To address this, the authors propose Click3R, a framework that performs interactive geometric correction of feed-forward models using sparse human correspondence clicks. Given a pair of images and a small number of user-provided cross-view correspondences, Click3R injects geometric constraints into the 3D reconstruction network through a lightweight point correspondence adapter. This enables the model to resolve ambiguities in challenging scenarios such as repetitive textures, symmetric structures, large viewpoint changes, or textureless regions.

To evaluate interactive reconstruction, the authors construct a challenging benchmark specifically designed to expose the failure modes of existing feed-forward methods. Experiments show that Click3R reduces reconstruction error with just a single correspondence click, achieving improvements on both standard benchmarks and the newly proposed benchmark. The results highlight that sparse human interaction provides an effective and practical route for correcting geometric reconstruction errors.

Original Abstract (Excerpt)

> We introduce Click3R, a framework for interactive geometric correction of feed-forward 3D reconstruction models using sparse human correspondence clicks. Click3R injects geometric constraints into 3D reconstruction networks through a lightweight point correspondence adapter, enabling correction of errors in challenging scenarios.

---

*Auto-collected on 2026-11-11.*

Tags

#click3r#3d-reconstruction#computer-vision#interactive-correction#correspondence-clicks#arxiv#feed-forward-models

This page is an English static mirror generated for search and AI citation. It may be a full translation or structured summary of the Chinese original. Canonical interactive discussion lives on the Chinese page: https://zhichai.net/topic/178637015