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.
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...
arXiv:2512. 16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving.
The paper introduces X‑VGGT, a feed‑forward cross‑view geometry transformer that jointly processes ground‑level images and a georeferenced satellite image to predict ground‑view camera poses, dense 3D point maps, and a scene‑level transform (gravity, scale, yaw, translation). This transform projects the local reconstruction into the satellite plane, achieving geo‑registration of all ground images with the satellite image. The authors also propose an evaluation protocol and demonstrate that X‑VGGT outperforms prior cross‑view geo‑localization and multi‑view 3D reconstruction models across multiple datasets.
arXiv:2610.07381v1 Announce Type: new Abstract: Modeling 3D scene geometry and its evolution over time is essential for autonomous driving and robotics. A common paradigm is to use world models to pr...
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.
arXiv:2608.13147v2 Announce Type: replace Abstract: Camera-based autonomous driving perception requires a shared representation that preserves metric 3D structure across synchronized multi-camera str...
The paper addresses the lack of standardized evaluation for single‑view novel view synthesis by highlighting the importance of aligning a method’s reference frame with the ground‑truth camera pose. It proposes using traditional 2D‑to‑2D and 2D‑to‑3D image matching to align 3D reconstructions and restricts evaluation to co‑visible regions where a correct ground truth exists. Experiments show that with proper alignment, 3D Gaussian‑based methods reach state‑of‑the‑art performance, and a simple baseline using a video generator and geometry estimator matches specialized novel‑view synthesis models without task‑specific training.
CrossDepth introduces geometry-constrained attention for multi-view surround depth estimation, addressing cross-image inconsistencies caused by varying camera intrinsics and limited receptive fields. The method conditions features on per-pixel camera-aware ray embeddings and extends pixel context via cross-image attention limited to geometrically plausible regions. Trained self-supervised with photometric consistency, it achieves better depth accuracy and consistency on DDAD and nuScenes compared to existing self-supervised approaches.
Georeferenced 3D reconstruction from ground images requires recovering not only the local scene geometry, but also localizing every camera center and 3D point in a geographic coordinate frame. Existin...
arXiv:2604.14025v2 Announce Type: replace-cross Abstract: Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understa...
arXiv:2605.14315v2 Announce Type: replace Abstract: Recent feed-forward 3D reconstruction methods, such as visual geometry transformers, have substantially advanced the traditional per-scene optimiza...
The paper presents a motion- and gravity-aware framework for feed-forward transformer models in multi-view 3D reconstruction. By providing residual optical flow and gravity direction as privileged signals during training, the model learns stronger geometric representations while remaining efficient at inference. Experiments demonstrate consistent accuracy gains, particularly in dynamic scenes and challenging camera motions, with the optimal integration stage depending on the backbone architecture.