9 papers
NeoMap: Training-free Novel-View Synthesis from Single Images and Videos
Jinxi Li, Tianyi Zhang, Yafei Yang +4
We study the challenging problem of novel view video synthesis from single images or monocular videos. Existing methods, which operate under the assumption that pre-trained video m…
FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation
Zihui Zhang, Zhixuan Sun, Yafei Yang +3
We address the challenging task of 3D object segmentation in complex scene point clouds without relying on any scene-level human annotations during training. Existing methods are t…
EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
Jiahao Chen, Zihui Zhang, Yafei Yang +4
We introduce EvObj for unsupervised 3D instance segmentation that bridges the geometric domain gap between synthetic pretraining data and real-world point clouds. Current methods s…
EvFlow-GS: Event Enhanced Motion Deblurring with Optical Flow for 3D Gaussian Splatting
Feiyu An, Yufei Deng, Zihui Zhang +1
Achieving sharp 3D reconstruction from motion-blurred images alone becomes challenging, motivating recent methods to incorporate event cameras, benefiting from microsecond temporal…
PhysInOne: Visual Physics Learning and Reasoning in One Suite
Siyuan Zhou, Hejun Wang, Hu Cheng +36
We present PhysInOne, a large-scale synthetic dataset addressing the critical scarcity of physically-grounded training data for AI systems. Unlike existing datasets limited to mere…
LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds
Zihui Zhang, Weisheng Dai, Hongtao Wen +1
We study the problem of unsupervised 3D semantic segmentation on raw point clouds without needing human labels in training. Existing methods usually formulate this problem into lea…