arXiv:2608. 19894v1 Announce Type: new Abstract: Multi-view computer vision pipelines typically rely on accurate sparse keypoints and robust descriptors.
By Fran\c{c}ois Costa, Raphael Kreft, Eckhard Goedeke, Felix M\"oller, Hardik Shah, Ramanathan Rajaraman, Shaohui Liu, R\'emi Pautrat, Marc Pollefeys
GALoc is a geometry-first approach for indoor localization that replaces depth prediction with gravity-aligned wireframes, ensuring verticality and coplanarity by construction. Using monocular RGB, camera intrinsics, relative poses, and IMU orientation, it builds a linear constraint matrix and finds the camera gauge that minimizes its smallest singular value through a global search. The resulting wireframes are projected into bird’s-eye-view layouts and matched against floorplans via a metric-free SE(2) search, achieving up to 88% sequential localization success on Gibson datasets and outperforming depth-based baselines when sufficient wall geometry is visible.
arXiv:2605.31577v2 Announce Type: replace
Abstract: Recent feedforward 3D reconstruction methods predict point maps and estimate global 3D geometry remarkably well. However, their predictions still e...
By Karim Knaebel, Gonzalo Martin Garcia, Christian Schmidt, Ilya Fradlin, Lucas Nunes, Daan de Geus, Bastian Leibe
GAPrompt++ is a multi-granular geometry-aware prompting method designed to adapt pre-trained 3D vision models to downstream tasks efficiently. It introduces a Point Shift Prompter for multi-scale geometric feature extraction, a Keypoint Prompter for local geometric saliency, and a Prompt Propagation mechanism to embed these cues throughout the model hierarchy. Experiments demonstrate that GAPrompt++ outperforms other prompting-based PEFT methods and even surpasses full fine-tuning while using less than 2% trainable parameters, and the authors provide two new challenging benchmarks for future research.
By Zixiang Ai, Zhenyu Cui, Yufei Guo, Wenwen Qiang, Lei Chen, Jiwen Lu, Jiahuan Zhou
arXiv:2610.03717v1 Announce Type: cross
Abstract: This paper examines the role of Novel View Synthesis (NVS) in geometric representation learning. In principle, NVS should reason about 3D scene struc...
By Keerthi Kaashyap, Dennis Anthony, Akshay Krishnan, Nhi Ngoc Nguyen, Jeremy Collins, James Hays, Shreyas Kousik, Animesh Garg
The paper introduces Epipolar Distillation (EpiDistill), a method that transfers scale‑aware geometric priors from multi‑view models to monocular depth foundation models using Rectified Stereo Tokens. By preserving epipolar attention patterns, the single‑view model maintains geometric consistency without needing multi‑view inputs during inference. Experiments show significant improvements in zero‑shot metric depth estimation on challenging datasets such as ETH3D and DIODE, and the approach consistently boosts performance of state‑of‑the‑art ViT‑based models like UniDepthV2 and DepthPro.
By Jung-Hee Kim, Xiaoming Liu