arXiv:2512. 16919v2 Announce Type: replace-cross Abstract: Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving.
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 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.
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.
The paper introduces GeoNeXt, a framework that repurposes pretrained video generative models for geometry estimation by framing it as a next‑frame prediction task. Unlike prior methods that either train separate depth/normal models or fine‑tune image diffusion backbones, GeoNeXt jointly models images and geometric targets, leveraging the structured knowledge of video models for more data‑efficient learning. Experiments show zero‑shot monocular depth and surface normal estimation that outperforms existing generative approaches and rivals discriminative state‑of‑the‑art methods while using far less training data.
The paper introduces Self-Geometry, a plug‑and‑play test‑time adaptation framework that enforces explicit multi‑view geometric constraints on Vision Foundation Models (VFMs) using 2D pixel correspondences as pseudo ground truth. It combines Geometric Disentanglement Optimization—mixing Multi‑View and Epipolar Consistency losses with Gradient Disentanglement—to avoid gradient conflicts, a Frame Angular‑Neighbor sampler based on SO(3) geodesic distances to select informative views, and a Lightweight TTA module that adapts VFMs via LoRA. Experiments on six VFMs and four benchmarks (7Scenes, ETH3D, ScanNet++, HiRoom) show consistent improvements in pose and geometry estimation.
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.
FlexMap is a vectorized high‑definition map construction framework that works with flexible camera configurations without needing calibrated rigs or explicit 2D‑to‑BEV transformations. It replaces geometric projection with a geometry foundation model that encodes cross‑view 3D structure, and uses a spatial‑temporal enhancement module and a camera‑aware decoder to separate spatial reasoning from temporal aggregation. Experiments on nuScenes and Argoverse 2 show that FlexMap outperforms pose‑dependent baselines and remains accurate even when camera views are missing or pose estimates are inaccurate.
arXiv:2606. 31585v1 Announce Type: cross Abstract: The remarkable scalability of Transformers has expanded their application to 3D computer vision, where camera-aware positional encoding is crucial for providing spatial cues in multi-view geometry.
arXiv:2605.13018v2 Announce Type: replace Abstract: Object-centric scene understanding is a fundamental challenge in computer vision. Existing approaches often rely on multi-stage pipelines that firs...
GS‑Net is a lightweight plug‑and‑play module that expands sparse Structure‑from‑Motion point clouds into dense Gaussian primitives, enabling cross‑sensor view synthesis for autonomous driving. It learns a generalizable initialization for 3D Gaussian Splatting, improving rendering quality for both interpolated and extrapolated camera viewpoints. The authors introduce CARLA‑NVS, a benchmark with 12 uniformly spaced cameras, and show that GS‑Net outperforms standard 3DGS by 2.08 dB PSNR on interpolated views and 1.86 dB on extrapolated views while being 50× faster to initialize.
arXiv:2609.23733v1 Announce Type: new Abstract: Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-v...
arXiv:2607. 21595v1 Announce Type: cross Abstract: Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning.