PointCubeNet: 3D Part-level Reasoning with 3x3x3 Point Cloud Blocks
In this paper, we propose PointCubeNet, a novel multi-modal 3D understanding framework that achieves part-level reasoning without requiring any part annotations. PointCubeNet comprises global and local branches. The proposed local branch, structured into 3x3x3 local blocks, enables part-level analysis of point cloud sub-regions with the corresponding local text labels. Leveraging the proposed pseudo-labeling method and local loss function, PointCubeNet is effectively trained in an unsupervised manner. The experimental results demonstrate that understanding 3D object parts enhances the understanding of the overall 3D object. In addition, this is the first attempt to perform unsupervised 3D part-level reasoning and achieves reliable and meaningful results.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Geometrically-driven Aggregation for Zero-shot 3D Point Cloud Understanding
Zero-shot 3D point cloud understanding can be achieved via 2D Vision-Language Models (VLMs). Existing strategies directly map Vision-Language Models from 2D pixels of rendered or captured views to 3D points, overlooking …
SegmentationSemantic SegmentationDeformable Filter Convolution for Point Cloud Reasoning
Point clouds are the native output of many real-world 3D sensors. To borrow the success of 2D convolutional network architectures, a majority of popular 3D perception models voxelize the points, which can result in a los…
LIDAR Semantic Segmentationobject-detectionObject DetectionSemantic SegmentationDAL-PCQA: Enabling Distortion-Level and Language-Driven Reasoning for Point Cloud Quality Assessment
Point Cloud Quality Assessment (PCQA) methods typically predict scalar Mean Opinion Scores (MOS), which quantify overall perceptual degradation but do not reveal its causes. In contrast, human observers naturally reason …
Point Cloud Quality AssessmentPoint CloudsSpatially Invariant Unsupervised 3D Object-Centric Learning and Scene Decomposition
We tackle the problem of object-centric learning on point clouds, which is crucial for high-level relational reasoning and scalable machine intelligence. In particular, we introduce a framework, SPAIR3D, to factorize a 3…
ObjectRelational ReasoningSemantic Segmentation4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping
Point clouds provide a compact and expressive representation of 3D objects, and have recently been integrated into multimodal large language models (MLLMs). However, existing methods primarily focus on static objects, wh…
Action UnderstandingPoint Clouds