GeoCond is a lightweight reliability adapter that enhances frozen feed‑forward 3D reconstruction backbones by reading their predicted geometry to produce pose‑level uncertainty and a refinement gate. It can be trained using permutation‑orbit variance, ground‑truth pose error, or cycle residuals from unlabeled pose graphs, and at inference requires only a single backbone pass plus a small MLP. On the VGGT backbone, GeoCond reduces out‑of‑distribution AUSE from 0.32 to 0.20, transfers zero‑shot to outdoor extreme‑view scenes, and prevents collapse from uniform bundle adjustment, while also enabling gated refinement, pose‑graph weighting, calibration, curation, and capture decisions.
By David Ahmedt-Aristizabal, Mohammad Ali Armin, Russell Tsuchida, Lars Petersson
The paper introduces Self-Geometry, a plug‑and‑play test‑time adaptation framework that enforces explicit multi‑view geometric constraints on Vision Foundation Models (VFMs) using 2D pixel correspondences as pseudo ground truth. It combines Geometric Disentanglement Optimization—mixing Multi‑View and Epipolar Consistency losses with Gradient Disentanglement—to avoid gradient conflicts, a Frame Angular‑Neighbor sampler based on SO(3) geodesic distances to select informative views, and a Lightweight TTA module that adapts VFMs via LoRA. Experiments on six VFMs and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom) show consistent improvements in pose and geometry estimation.
By Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae, Jihyong Oh
arXiv:2609.15795v2 Announce Type: replace
Abstract: Streaming geometric foundation models are emerging as a compelling alternative to SLAM systems. Yet this streaming nature introduces a fundamental...
By Mingkai Liu, Hao Zhao, Xingxing Zuo
arXiv:2609.15795v1 Announce Type: new
Abstract: Streaming geometric foundation models are emerging as a compelling alternative to SLAM systems. Yet this streaming nature introduces a fundamental issu...
By Mingkai Liu, Hao Zhao, Xingxing Zuo
arXiv:2608.29680v1 Announce Type: new
Abstract: Feed-forward 3D foundation models reconstruct perspective scenes in one pass. Satellite photogrammetry needs a different product, one that domain adapt...
By Zhe Dong, Wanqing Wu, Yuzhe Sun, Haochen Jiang, Yuchen Ma, Lecheng Ren, Tianzhu Liu, Yanfeng Gu
arXiv:2610.07883v1 Announce Type: new
Abstract: A correctly reconstructed distant point appears uncertain even when a frozen 3D model processes equivalent inputs because its output frame rotates frac...
By Sammam Mahdi, Fariha Binta Salim, Rakin Bin Rabbani, Aniqua Nusrat Zereen
arXiv:2610.09173v1 Announce Type: new
Abstract: 3D foundation models enable efficient novel view synthesis by carrying a Gaussian head on the representation they already use for reconstruction. Howev...
By Zhijie Zheng, Xinhao Xiang, Jiawei Zhang
arXiv:2610.23039v1 Announce Type: new
Abstract: Feed-forward Gaussian models have made novel view synthesis almost instantaneous. Feed-forward methods predict Gaussians directly, either in two stages...
By Viruthshaan Vinasirajan, Ranga Rodrigo
arXiv:2610.35361v1 Announce Type: new
Abstract: 3D Gaussian Splatting (3DGS) has become a promising representation for real-time novel view synthesis and 3D scene reconstruction. For practical deploy...
By Xiaohan Lu, Jiaqi Zhang, Weijia Jiang, Siwei Ma
The paper introduces CELL, a confidence-weighted event-camera localization method that learns per-correspondence confidence end-to-end using a differentiable probabilistic PnP. It reweights flow supervision, drives probabilistic correspondence selection at test time, and refines edge matching, while also proposing a partial-completion depth representation. Experiments on M3ED and DSEC show significant reductions in median translation and rotation errors compared to the LEAR baseline.
By Panagiotis Kiousis, Kuangyi Chen, Jun Zhang, Friedrich Fraundorfer
GeoState introduces a view‑decoupled geometry representation for predictive 3D world modeling, separating scene‑state evolution from camera‑dependent observation. It aggregates multi‑view geometry foundation model features into a scene tokenizer, then uses a geometry decoder to query this state with camera rays. An autoregressive world model predicts future scene states while modeling camera motion independently, enabling consistent decoding under any camera and maintaining a single context‑derived scale throughout rollouts.
By Hongchang Liu, Jian Liu, Yujuan Ding, Liang Peng, Xun Jiang, Fei Ma, Xing Xu, Yi Bin
GeoState introduces a view‑decoupled geometry representation for predictive 3D world modeling, separating scene‑state evolution from camera‑dependent observation. It aggregates multi‑view geometry foundation model features into a scene tokenizer, then uses a geometry decoder with camera rays to query the state. An autoregressive world model predicts future scene states while modeling camera motion separately, enabling consistent decoding under any camera and maintaining a single context‑derived scale throughout the rollout.