arXiv:2608.29819v1 Announce Type: new
Abstract: Accurate stereo matching remains challenging in ill-posed regions such as fine structures, reflective, or transparent objects, where appearance cues ar...
By Md Raqib Khan, Santosh Kumar Vipparthi, Subrahmanyam Murala
arXiv:2506.20756v4 Announce Type: replace
Abstract: Recent video depth estimation methods achieve great performance by following the paradigm of image depth estimation, i.e., typically fine-tuning pr...
By Haodong Li, Chen Wang, Jiahui Lei, Kostas Daniilidis, Lingjie Liu
3D Gaussian Splatting (3DGS) has achieved remarkable success in real-time novel view synthesis, yet it suffers from severe overfitting under sparse-view settings due to insufficient geometric constraints. While recent methods introduce monocular depth priors to mitigate this, they inherently struggle with scale ambiguity and cross-view inconsistency, leading to defective geometry.
Stereo matching is a fundamental task in 3D reconstruction. Despite remarkable advances, the prevailing paradigms formulate stereo matching as a deterministic regression problem, collapsing the multimodal distribution modeling into a single-point estimation.
SatUnreal is a synthetic dataset created with Unreal Engine that offers 10,000 high‑resolution (0.3 m GSD) satellite stereo pairs. It addresses key limitations of existing benchmarks by ensuring physical geometry simulation, spatio‑temporal consistency, topographic diversity, and mathematically precise occlusion masks via a two‑step line‑trace algorithm. Models trained solely on SatUnreal outperform those trained on real datasets when transferred to real‑world benchmarks such as US3D and WHU‑Stereo.
By Han-Gyeol Kim, JaeWan Park, Junmin Park, Darongsae Kwon
arXiv:2507.19738v2 Announce Type: replace
Abstract: While accurate LiDAR depth has been shown to improve stereo matching, high-end LiDAR remains costly and difficult to deploy at scale, motivating gu...
By Jinsu Yoo, Sooyoung Jeon, Zanming Huang, Tai-Yu Pan, Wei-Lun Chao