5 papers
MATE4D: Matrix-Guided Editable 4D Generation from a Single Image
Xiaotian Chen, Dongfu Yin
Generative models have rapidly pushed content creation be-yond 2D imagery toward dynamic 3D and 4D scene synthesis. Yet pro-ducing realistic and temporally stable 4D content from a…
Partition-Invariant Tuning for 3D Scene Understanding
Hongqiang Lin, Tianle Wang, Shuiwang Li +4
Scene-level point cloud understanding remains challenging due to diverse geometries and spatial layouts. While pre-trained 3D point cloud foundation models (PFMs) offer strong tran…
ARD-REFSM: Enhancing Reflection Symmetry Detection with Asymmetric Denoising and Rotation Equivariance
Dongfu Yin, Rourou Su, Cong Zhao +1
Reflection symmetry detection remains challenging due to interference from asymmetric regions and arbitrary orientations of symmetric patterns. Asymmetric regions introduce backgro…
Point-Selection Fine-Tuning Framework for Robust Point Cloud Classification
Da Li, Chang Ma, Dongfu Yin
Noisy and corrupted points can substantially degrade point cloud recognition performance, especially under challenging corruption settings. In particular, full fine-tuning of 3D pr…
MVG4D: Image Matrix-Based Multi-View and Motion Generation for 4D Content Creation from a Single Image
DongFu Yin, Xiaotian Chen, Fei Richard Yu +2
Advances in generative modeling have significantly enhanced digital content creation, extending from 2D images to complex 3D and 4D scenes. Despite substantial progress, producing…