arXiv:2609.22896v1 Announce Type: new Abstract: Autonomous vehicles operating in open-world scenarios are inevitably confronted with previously unknown objects, such as exotic animals or loose cargo....
We present FoundationGeo, a two-stage framework that explicitly bridges relative and metric prediction via spatial calibration and principled data design. Stage 1 learns a high-fidelity, affine-invariant geometry model by initializing with DINOv3 and training on a curated 10.
arXiv:2608.30820v1 Announce Type: new Abstract: Occlusion boundaries (OBs) are pixel-level image boundaries corresponding to surface visibility discontinuities caused by occlusion. Through precise bo...
arXiv:2607. 12433v1 Announce Type: cross Abstract: Diffusion models have recently become the dominant paradigm for monocular depth estimation (MDE).
The paper introduces AffineGS, a method that improves the geometric accuracy of 3D Gaussian Splatting (3DGS) by applying a spatially varying affine rectification to monocular depth estimates. It identifies that monocular depth networks suffer from region-dependent, piecewise-linear distortions, rendering global alignment ineffective. By employing edge-aware, regionally smooth fields and a normal-aware regularizer, AffineGS aligns disparity with 3DGS depth and normals, achieving strong photometric quality while significantly enhancing geometry across diverse experiments.
PXDepth is a monocular depth estimation model that separates global context modeling from pixel-level depth prediction. It uses a large-patch Vision Transformer to capture scene context and a pixel-space predictor with Context‑Modulated Pixel Transformer blocks to preserve high‑resolution spatial details. The approach maintains fine structures and sharp boundaries while achieving competitive global depth accuracy in zero‑shot benchmarks.
arXiv:2510.18714v3 Announce Type: replace Abstract: This paper addresses metric 3D reconstruction of indoor scenes by exploiting their inherent geometric regularities with compact representations. Us...
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...
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:2608.30870v1 Announce Type: new Abstract: Semantic segmentation in 3D Gaussian Splatting (3DGS) is crucial for advancing 3D scene understanding. Existing methods predominantly rely on feature d...
arXiv:2611.05874v1 Announce Type: new Abstract: Humans can easily recognize the same objects across different viewpoints of a 3D scene, whereas teaching models such multi-view-consistent perception t...
PePESeg3D introduces perception priors into a multi‑scale 3D Gaussian segmentation pipeline, integrating monocular depth and mask constraints during geometry reconstruction and dense depth‑color cues with view‑consistent centroid supervision during contrastive feature learning. This dual‑stage approach aligns geometry with semantic structure and compensates for incomplete mask supervision from 2D foundation models. Experiments on SPIn‑NeRF, LERF‑Mask, and NVOS benchmarks show state‑of‑the‑art performance in both multi‑scale segmentation and scene reconstruction.