CORTEXA
← Browse
arxivcs.CV2026-07-06

ReCal3R: Reliability-Calibrated Learning Rates for Streaming 3D Reconstruction

Xinze Li, Yiyuan Wang, Pengxu Chen, Weifeng Su, Weisi Lin, Wentao Cheng

Streaming 3D reconstruction relies on a compact recurrent scene state to process long image streams in linear time and bounded memory. However, repeated updates can gradually corrupt this state, causing reliable historical information to be overwritten by noisy or ambiguous observations. We introduce ReCal3R, a reliability-calibrated learning rate method for recurrent 3D reconstruction. Instead of directly applying a candidate learning rate, our method estimates state token reliability from the maintained scene state and uses it to calibrate a candidate learning rate derived from token alignment, state reconstruction residual, and recent update pressure. The resulting token-wise learning rate interpolates between a conservative base rate and the candidate rate, suppressing aggressive updates on unreliable tokens while preserving adaptation to informative frames. Applied to CUT3R as a training-free calibration rule, ReCal3R reaches strong performance on long sequences in pose, depth, and reconstruction quality, including a 3.7$\times$ reduction in ATE, with comparable runtime and memory. Code is available at: https://github.com/Powertony102/ReCal3R.

View free PDFSource page

Related papers

arxivcs.CVcs.LG2026-07-15

DreamSat-Pose: Spacecraft Pose Estimation from Single-View 3D Reconstructions and Learned 2D-3D Feature Matching

Josiane Uwumukiza, Jocelyn Zhao, Giovanni Lavezzi, Giacomo Battaglia, Paolo Panicucci, Minduli C. Wijayatunga, et al.

6-DoF pose estimation is a critical task in autonomous rendezvous and proximity operations. In the case of an unknown target, this task becomes challenging as it shall be paired with the reconstruction of the target shape model. In this article, we propose a novel framework for s…

View free PDFSource page
arxivcs.CV2026-06-28

SAD-GS: Learning Reliable 3D Semantic Gaussian Fields via Dynamic Geo-Semantic Anchoring

Yufei Zhang, Chenlu Zhan, Gaoang Wang, Hongwei Wang

Open-vocabulary 3D semantic Gaussian field learning relies on multi-view 2D supervision, whose semantic targets and spatial assignments are often unreliable. Across varying viewpoints, view-dependent features cause semantic identity drift, while propagated tracker masks introduce…

View free PDFSource page
arxivcs.CV2026-07-23

WAT3R: Feedforward Underwater 3D Reconstruction

Jiayi Xu, Jiahao Lu, Ziqiang Zheng, Yihao Tan, Yaolong Zhu, Yuan Liu, et al.

Reliable feedforward underwater 3D reconstruction remains challenging due to severe light attenuation and backscattering, which degrade visual quality and disrupt feature consistency across views, leading to inaccurate multi-view geometry. To address this issue, we propose WAT3R,…

View free PDFSource page
arxivcs.CVcs.MAcs.MM2026-07-17

Toward Semantic Communication for Real-time Mobile 3D Reconstruction

Fangzhou Zhao, Yao Sun, Xuesong Liu, Runze Cheng, Shang Kai, Yi Sun

Real-time mobile 3D reconstruction is fundamental to many emerging applications such as autonomous navigation and digital twin construction, where a moving platform continuously captures an image stream and transmit to a computing server for scene understanding. Unlike offline re…

View free PDFSource page
arxivcs.CV2026-07-17

Event3R: Asynchronous-to-Global 3D Reconstruction from Event Camera via Spatial-Temporal Feature Aggregation

Jian Huang, Haotian Shen, Xinhao Lou, Chengrui Dong, Wenpu Li, Peidong Liu

Robust 3D reconstruction is essential for robotics and embodied perception. Recent feed-forward approaches such as DUSt3R have demonstrated impressive progress in dense 3D reconstruction from RGB images, achieving global geometric consistency and strong generalization. However, e…

View free PDFSource page
arxivcs.CVcs.LG2026-07-03

SAF3R: Dynamic Sparse Attention for Feed-Forward 3D Reconstruction Transformers

Jianing Deng, Yuanzhe Li, Jialu Wang, Song Wang, Tianlong Chen, Huanrui Yang, et al.

Feed-forward 3D reconstruction (F3R) transformers have recently achieved remarkable success. However, scaling them to long image sequences remains challenging, as the quadratic complexity of cross-view global attention quickly becomes the dominant computational bottleneck. While…

View free PDFSource page