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
Local feature matching is a fundamental component of photogrammetry, enabling accurate image correspondence critical for tasks such as 3D reconstruction, stereo mapping, and visual localization. While recent detector-free matching methods, like LoFTR, have advanced the field, the global features obtained by leveraging the global-range modeling capacity of the unconstrained attention mechanism compromise the model's attention to the salient structures in certain scenarios.
arXiv:2608.03423v2 Announce Type: replace
Abstract: Local feature matching is a fundamental component of photogrammetry, enabling accurate image correspondence critical for tasks such as 3D reconstru...
By Zhihua Xu, Runyu Zhu, Rongjun Qin
arXiv:2608.21710v1 Announce Type: new
Abstract: With the advance of deep neural networks, the quality of disparity maps obtained through stereo matching has steadily improved. However, existing stere...
By Bohan Li
arXiv:2608.20788v1 Announce Type: new
Abstract: Deep learning-based Multi-View Stereo (MVS) has advanced significantly but often generalizes poorly to unseen scenes, particularly in occluded areas or...
By Byeonggwon Lee, Sanggi Lee, Siwoo Lee, Khang Truong Giang, Soohwan Song
E3Stereo improves stereo matching at depth boundaries by learning geometric edges from disparity supervision. It integrates these edges with backbone disparity and image details to predict full‑resolution disparity corrections, emphasizing boundary errors during training. On the Scene Flow dataset, E3Stereo reduces end‑point error at depth boundaries by 9.5%–14.3% across multiple models and improves all eleven metrics on ETH3D, KITTI 2012, and KITTI 2015 after fine‑tuning.
By Qi Xiong, Qinghua Zhao, Yongqiang Xi
Existing iterative stereo matching methods primarily adopt two types of correspondence representation: explicit matching search via correlation volumes and local residual refinement via warped features, yet the two remain separately modeled. We propose WAVE-Stereo, built on a core insight: correlation volumes and feature warping provide complementary matching cues.
arXiv:2608.28933v1 Announce Type: new
Abstract: Stereo reconstruction is one of the last remaining Computer Vision tasks where all state-of-the-art methods employ a heavy architectural inductive bias...
By Vage Taamazyan, Zhuowen Shen, Stefan Hinterstoisser, Alberto Dall'Olio, Agastya Kalra, Aarrushi Shandilya, Xin Li, Wenping Wang, Kartik Venkataraman
WHTMix replaces the global self‑attention stage in stereo transformers with a data‑independent Walsh‑Hadamard token mixer, achieving the same end‑point error on synthetic driving data while cutting model compute by 2.46× and single‑image inference latency by 2.65×. The log‑linear cost of the mixer is especially advantageous for high‑resolution stereo matching, as shown by a complexity analysis that links benefits to the ratio of sequence length to channel width. Additionally, a hybrid log‑disparity loss is introduced to up‑weight small‑disparity pixels, improving accuracy on distant objects without extra computational cost.
By Prathyush Sajith, Emadeldeen Hamdan, Ahmet Enis Cetin
arXiv:2508.10838v3 Announce Type: replace
Abstract: Learning disparity in occluded regions remains difficult for unsupervised stereo matching. Photometric supervision lacks valid target-view correspo...
By Peng Xu, Zhiyu Xiang
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.
The paper proposes a new sequence-to-sequence formulation for multi-view stereo (MVS) that jointly predicts 3D geometry for all input views using a global transformer architecture. It introduces ray‑map embeddings to inject camera parameters into image tokens and a unified global cost volume to capture 3D structure across all views. Experiments on public benchmarks demonstrate state‑of‑the‑art performance, outperforming both traditional MVS and feed‑forward reconstruction baselines.
By Aoxiang Fan, Corentin Dumery, Nicolas Talabot, Pascal Fua