arXiv AI
OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 1
Geometry-Grounded Unified 3D Perception 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...
arXiv Computer Vision
Sep 3
Self-Geometry: GT-Free and Plug-and-Play Test-Time Adaptation for Geometrically Consistent 3D Vision Foundation Models
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.
arXiv AI
Jul 24
3D-Aware VLMs with Implicit and Explicit Geometries
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.
arXiv Computer Vision
Sep 7
ARC-Loc: Leveraging Azimuthal Ray Convergence as a Geometric Cue for Direct Cross-View Localization
ARC‑Loc introduces a new cross‑view localization method that bypasses heavy Bird’s‑Eye‑View transformations and external depth models. By converting ground keypoints into azimuthal rays on a satellite map and exploiting their convergence at the user’s location, the approach uses a minimal Azimuthal Ray Convergence solver and an ARC loss to directly match ground and satellite images. Experiments on VIGOR and KITTI show that ARC‑Loc achieves competitive accuracy while offering faster, memory‑efficient inference and easy integration with existing frameworks.
arXiv Computer Vision
Sep 1
OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction
arXiv:2608.16499v2 Announce Type: replace-cross Abstract: Active 3D Gaussian reconstruction fundamentally relies on selecting informative next-best views under limited sensing budgets. Existing activ...
arXiv AI
Jun 18
OneCanvas: 3D Scene Understanding via Panoramic Reprojection
arXiv:2606. 19253v1 Announce Type: cross Abstract: Existing approaches to 3D scene understanding in Vision-Language Models (VLMs) either rely on complex, model-specific geometry encoders or large training budgets in pursuit of spatial reasoning.