A multi-view transformer predicts dense perspective fields that feed a geometric optimizer to estimate camera intrinsics and gravity from arbitrary numbers of real-world views.
hub
Joint 2D-3D-Semantic Data for Indoor Scene Understanding
19 Pith papers cite this work. Polarity classification is still indexing.
19
Pith papers citing it
abstract
We present a dataset of large-scale indoor spaces that provides a variety of mutually registered modalities from 2D, 2.5D and 3D domains, with instance-level semantic and geometric annotations. The dataset covers over 6,000m2 and contains over 70,000 RGB images, along with the corresponding depths, surface normals, semantic annotations, global XYZ images (all in forms of both regular and 360{\deg} equirectangular images) as well as camera information. It also includes registered raw and semantically annotated 3D meshes and point clouds. The dataset enables development of joint and cross-modal learning models and potentially unsupervised approaches utilizing the regularities present in large-scale indoor spaces. The dataset is available here: http://3Dsemantics.stanford.edu/
hub tools
citation-role summary
dataset 3
background 1
citation-polarity summary
representative citing papers
HM3D offers 1000 building-scale 3D environments that are larger and higher-fidelity than existing datasets, enabling better-performing embodied AI agents for tasks like PointGoal navigation.
DepthMaster unifies metric monocular depth estimation for perspective and panoramic images by patching panoramas into perspective views, adding a consistency loss and virtual cameras, and training mostly on perspective data to reach SOTA zero-shot results on 13 datasets.
LangTail uses entity-level semantic priors from language models aligned via contrastive learning in a hierarchical clustering setup to resolve long-tail ambiguity, yielding +13.5, +12.9, and +8.9 mIoU gains on ScanNet-v2, S3DIS, and nuScenes.
VGGT-360 delivers geometry-consistent zero-shot panoramic depth by converting panoramas into multi-view 3D reconstructions via VGGT models and three plug-and-play correction modules, then reprojecting the result.
Presents a novel integer linear programming approach for automatic reconstruction of volumetric, parametric, multi-story building models from unstructured point clouds without requiring initial room segmentation.
PointGS achieves semantic-consistent unsupervised 3D point cloud segmentation by using 3D Gaussian Splatting to bridge discrete points and continuous 2D images for distilling SAM semantics.
A hybrid pipeline combines semantic segmentation of point clouds with topology-aware reconstruction to generate BIM models, introduces the vIoU evaluation metric, and releases the DeKH dataset with demonstrated gains over RANSAC baselines.
STRNet improves goal-conditioned visual navigation by replacing simplistic encoders and pooling with a spatio-temporal fusion module that performs spatial graph reasoning and hybrid temporal modeling.
FoundObj uses foundation-model priors as RL rewards to discover multi-class 3D objects from point clouds without scene-level labels.
PanoSAMic modifies SAM with multi-stage feature encoding, spatio-modal fusion, spherical attention, and dual-view fusion to achieve SOTA panoramic semantic segmentation on public RGB and RGB-D datasets.
PointCaM proposes a cut-and-mix mechanism with an Unknown-Point Simulator and Estimator to improve open-set recognition on point clouds by simulating out-of-distribution data and using multi-level features.
EvObj learns evolving object-centric representations for unsupervised 3D instance segmentation by dynamically refining object candidates and completing partial geometries to bridge the synthetic-to-real domain gap, outperforming baselines on real and synthetic datasets.
Gaussian and related cropping strategies for point cloud subclouds improve 3D neural network performance over spherical cropping on large outdoor scenes.
INSIGHT transfers 2D semantic understanding from foundation models and traditional CV tools into 3D point clouds and compressed scene graphs for indoor public-safety mapping without target-domain labels.
Survey organizing panoramic scene analysis literature by architectural design and training paradigm, identifying the absence of methods achieving both strict spherical equivariance and full reuse of perspective-pretrained weights, plus five evaluation protocol gaps and a six-point roadmap.
A survey of deep learning architectures for 3D sensed data classification covering RGB-D, multi-view, volumetric and end-to-end methods along with datasets and future directions.