GS-ASM: 2DGS-Supervised Active Stereo Matching

Zhengling Wu Rongfeng Lu Quan Chen Longjian Zeng Ming Lu Yaoqi Sun Ya-Hong Chen Baofeng Ji Chenggang Yan

· 0 citations · 61 references

TL;DR

A novel framework is proposed that synthesizes proxy labels to enable supervised training of deep active stereo networks without requiring any ground-truth depth, and develops an active 2D Gaussian Splatting- based synthesis method that explicitly models the scene geometry and the projected active pattern.

Semantic Scholar

View source

Similar papers

Jul 2026

WAVE-Stereo: Warp-Aligned Volume Encoding for Stereo Matching

WAVE-Stereo is proposed, built on a core insight: correlation volumes and feature warping provide complementary matching cues, and achieves competitive zero-shot generalization accuracy without any external foundation model prior.

Zehan Liu, Ya-Ge He, Xian-Wu Gong · arXiv.org · 0 citations

Preprint Jul 2026

Revisiting Matching Response and Swept Feature Volumes for Wide-baseline Omnidirectional Stereo

In this paper, we propose a training strategy for confidence estimation in omnidirectional stereo, targeting the ambiguous matches that frequently occur in wide-baseline setups. Reinterpreting the matching responses produced by the 3D encoder decoder block, we show that their expectation values provide intrinsic confid...

Seungjin Jeon, Jongwoo Lim, Changhee Won · 0 citations

Jul 2026

StereoSplat+: Feed-Forward Stereo Gaussian Splatting with Diffusion-Assisted Progressive Inference

Experiments show that StereoSplat+ improves novel-view rendering quality and geometry accuracy, especially in occluded regions and under strong view extrapolation, outperforming recent feed-forward 3DGS baselines.

Zi-Hua Liu, Masatoshi Okutomi · arXiv.org · 0 citations

Open access Jul 2026

Learning-based Monocular Depth Estimation for Photogrammetric 3D Reconstruction

This paper employs sparse point clouds of Structure-from-Motion (SfM) as extra geometric constraints and proposes a framework that achieves photogrammetric 3D reconstruction using off-the-shelf learning-based MDE models without the need for additional fine-tuning.

Chunyu Dou, Yifei Yu, Xin Wang et al. · The International Archives o... · 0 citations

Preprint Aug 2026

Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models

Recent Vision Foundation Models (VFMs) predict depth, camera pose, and pointmap in a single forward pass without per-scene optimization, achieving strong generalization. However, enforcing explicit multi-view geometric consistency, e.g., through bundle adjustment, is computationally costly and is thus not imposed durin...

Seokhyun Youn, Dahyeon Kye, Sung-Ho Bae et al. · 0 citations

Preprint Aug 2026

SpatialCrafter: Single Image World Modeling with Generative 3D Proxies

SpatialCrafter is presented, a novel two-stage framework that addresses explorable image-to-scene generation issues by introducing a global 3D proxy for high-fidelity image-to-scene generation and appearance refinement and introduces Parallel Geometry Injection and Proxy-Aware Corruption training strategies.

Chuan Fang, Lingteng Qiu, Yixun Liang et al. · 1 citation