Leveraging Local Neighborhood Features to Enhance 3D Point Cloud Classification
Incorporating radius-normalized distance and directional vectors as additional local neighborhood features can significantly improve the classification accuracy of 3D point cloud models, particularly on real-world datasets.
Enhancing 3D Object Detection with Limited LiDAR Data by Reconstructing Dense Point Clouds from Sparse Inputs
A novel transformer-based approach that reconstructs a high-resolution 3D point cloud from a single image and a small set of 3D points, enabling accurate 3D object detection with limited sensor data.
3D Geometry-aware Deformable Gaussian Splatting for Improved Dynamic View Synthesis
The proposed method leverages 3D geometry-aware features extracted from 3D Gaussian distributions to enable improved modeling of complex 3D deformations, leading to enhanced dynamic view synthesis and 3D dynamic reconstruction.
Exploiting Structural Similarities for Reliable and Informative 3D Semantic Segmentation
The proposed hierarchical multi-label classification (HMC) training strategy enables 3D LiDAR semantic segmentation models to learn structural relationships between classes, allowing them to provide confident high-level information and well-calibrated detailed classifications in uncertain situations.
Fully Sparse 3D Occupancy Prediction: A Novel Approach for Efficient and Accurate Scene Understanding
SparseOcc, the first fully sparse occupancy network, achieves state-of-the-art performance on the Occ3D-nuScenes benchmark while maintaining real-time inference speed by exploiting the inherent sparsity of 3D scenes.
Segment Anything for NeRF in High Quality: Achieving Accurate and Consistent 3D Object Segmentation
SANeRF-HQ leverages the Segment Anything Model (SAM) and Neural Radiance Fields (NeRF) to achieve high-quality 3D segmentation of any target object in a given scene, producing accurate segmentation boundaries and consistent multi-view results.
GS-SLAM: Real-Time Dense Visual SLAM with Efficient 3D Gaussian Splatting
GS-SLAM utilizes a 3D Gaussian scene representation coupled with a real-time differentiable splatting rendering pipeline to achieve a better balance between efficiency and accuracy in dense visual SLAM.
Single-View Reconstruction of Articulated 3D Object Shapes without Category-Specific Priors
SAOR, a novel self-supervised approach, can estimate the 3D shape, texture, and viewpoint of an articulated object from a single image without requiring any category-specific 3D templates or skeletons.
Efficient Non-Parametric Networks for Few-shot 3D Scene Segmentation
The authors propose efficient non-parametric and parametric frameworks, Seg-NN and Seg-PN, for few-shot 3D scene segmentation. Seg-NN is a training-free encoder that can extract discriminative representations without any learnable parameters, while Seg-PN further improves performance with a lightweight query-support transferring module.
Unified Spatio-Temporal Tri-Perspective View Representation for Enhancing 3D Semantic Occupancy Prediction
Introducing S2TPVFormer, a unified spatiotemporal transformer architecture that leverages temporal cues to generate temporally coherent 3D semantic occupancy embeddings, outperforming the state-of-the-art TPVFormer by a significant 4.1% improvement in mean Intersection over Union (mIoU).