PixCuboid: Room Layout Estimation from Multi-view Featuremetric Alignment
Coarse room layout estimation provides important geometric cues for many downstream tasks. Current state-of-the-art methods are predominantly based on single views and often assume panoramic images. We introduce PixCuboid, an optimization-based approach for cuboid-shaped room layout estimation, which is based on multi-view alignment of dense deep features. By training with the optimization end-to-end, we learn feature maps that yield large convergence basins and smooth loss landscapes in the alignment. This allows us to initialize the room layout using simple heuristics. For the evaluation we propose two new benchmarks based on ScanNet++ and 2D-3D-Semantics, with manually verified ground truth 3D cuboids. In thorough experiments we validate our approach and significantly outperform the competition. Finally, while our network is trained with single cuboids, the flexibility of the optimization-based approach allow us to easily extend to multi-room estimation, e.g. larger apartments or offices. Code and model weights are available at https://github.com/ghanning/PixCuboid.
Code (0)
등록된 구현이 없습니다.
Tasks
Room Layout EstimationSimilar Papers 제목 키워드 기반
PolyLayout: Multi-room Manhattan Layout Estimation
Estimating room layouts from multi-view imagery is a core task for indoor scene understanding. Existing methods are typically limited either by poor generalization to new datasets or restrictive geometric assumptions of …
Room Layout EstimationScene UnderstandingUnposed Sparse Views Room Layout Reconstruction in the Age of Pretrain Model
Room layout estimation from multiple-perspective images is poorly investigated due to the complexities that emerge from multi-view geometry, which requires muti-step solutions such as camera intrinsic and extrinsic estim…
3D ReconstructionRoom Layout EstimationSelf-training Room Layout Estimation via Geometry-aware Ray-casting
In this paper, we introduce a novel geometry-aware self-training framework for room layout estimation models on unseen scenes with unlabeled data. Our approach utilizes a ray-casting formulation to aggregate multiple est…
Room Layout EstimationZillow Indoor Dataset: Annotated Floor Plans With 360deg Panoramas and 3D Room Layouts
We present Zillow Indoor Dataset (ZInD): A large indoor dataset with 71,474 panoramas from 1,524 real unfurnished homes. ZInD provides annotations of 3D room layouts, 2D and 3D floor plans, panorama location in the f…
Room Layout EstimationFlat2Layout: Flat Representation for Estimating Layout of General Room Types
This paper proposes a new approach, Flat2Layout, for estimating general indoor room layout from a single-view RGB image whereas existing methods can only produce layout topologies captured from the box-shaped room. The p…