arXiv Computer Vision
OccamView: Object-Conditioned View Selection for Frame-Budgeted Active 3D Gaussian Reconstruction
Read the original on arXiv Computer Vision →The Flow has not summarised this story yet — read it at arXiv Computer Vision.
Related stories
arXiv Computer Vision
Oct 1
Matisse: Evidence-Space Reasoning for Active 3D Reconstruction
Matisse is a training‑free framework that combines active 3D reconstruction with keyframe selection by using evidence from a pretrained generative 3D model. It estimates evidential uncertainty via cross‑attention on 3D latent tokens and derives an evidential information gain to guide view acquisition and keyframe selection, reducing redundant observations and supporting multi‑object scenes with occlusion‑aware aggregation. On GSO30, YCB‑V, and Replica, Matisse improves Chamfer distance by 12.7%, 3.8%, and 9.2% respectively, and speeds up end‑to‑end reconstruction by 1.5× compared to the best baseline.
arXiv AI
Oct 5
OmniAct3D: Leveraging Foundation Geometry and Evidence-Grounded Reasoning for Panoramic 3D Detection
OmniAct3D is a framework that adapts Vision Foundation Model (VFM) detectors trained on perspective images to equirectangular projection (ERP) panoramic images for 3D detection. It introduces the ERP-Ray Geometry Adapter (ERGA-Ray) to model spherical rays, the Visual-Action Reasoning Chain (VARC) to ground hypotheses in panoramic evidence, and the Appearance-Guided Heading Expert (AGHE) to recover high‑resolution heading cues. The method achieves a 2.96 NDS improvement on Spheriverse and a 24.87 mAP gain on PanoMMOcc, while preserving most of the baseline’s performance across configurations.
arXiv Computer Vision
Oct 9
Look Where You Can: Active View Selection for CAD Reconstruction under Occlusion
The paper introduces SightCAD, a framework for parametric CAD reconstruction that explicitly handles view feasibility constraints in realistic indoor scenes. It learns a view selector to choose a small set of feasible viewpoints for a vision‑language model that generates executable CadQuery code, and jointly trains the selector and the VLM using a reward that depends on the final geometric fidelity. The approach outperforms baseline methods on several benchmarks, achieving higher intersection‑over‑union scores and a lower invalid‑code rate.
arXiv Computer Vision
Oct 2
HierGF: Hierarchical Gaussian Fields via Geometry-perception Message Passing for Sparse-view 3D Reconstruction
The paper introduces HierGF, a method for sparse‑view 3D reconstruction that uses a hierarchical geometry‑perception backbone to generate structured pseudo‑supervision from limited views. It incorporates a learnable confidence network to focus gradients on cross‑view consistent content and a geometrically consistent densification module to improve alignment and fill under‑sampled regions. This approach aims to overcome the challenges of few images and incomplete coverage that typically lead to overfitting and structural holes in existing methods.
arXiv AI
2d ago
Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification
Quo Vadis, Driving Scene Reconstruction? Occlusion-Aware Gaussian Densification introduces OccSplat, a feed-forward framework that addresses the limitation of single-observation 3D Gaussian Splatting methods in driving-scene reconstruction. OccSplat identifies occluded regions lacking Gaussian support via Gaussian Occlusion Mapping and then generates new Gaussian primitives for these areas through Gaussian Occlusion Completion. By integrating the predicted primitives into the original representation, OccSplat enhances novel-view synthesis without requiring per-scene optimization, achieving significant improvements on the nuScenes benchmark, especially in occluded regions.
arXiv Computer Vision
Oct 19
PanoBench: A Panoptic Occupancy Prediction Benchmark for Autonomous Driving
PanoBench is a new camera‑centric benchmark for panoptic occupancy prediction that unifies 3D geometry, semantics, and instance identities across synthetic and real‑world driving scenes. It combines three datasets—PanoBench‑CarlaOcc, PanoBench‑nuScenes, and PanoBench‑KITTI360—through canonical interfaces and unified evaluation protocols, providing multi‑resolution annotations with persistent instance identities. The benchmark introduces a novel reconstruction pipeline for real‑world data, a unified valid‑mask protocol, and analyses of observation fidelity, geometric completeness, spatial continuity, and temporal consistency, while also benchmarking methods on semantic, panoptic, and 4D occupancy forecasting. whyItMatters":"PanoBench addresses the scarcity of instance‑aware annotations in panoptic occupancy research by offering comprehensive, high‑quality annotations and evaluation protocols that enable more robust development and comparison of autonomous driving perception methods."