9 papers
Pantheon360: Taming Digital Twin Generation via 3D-Aware 360° Video Diffusion
Ting-Hsuan Chen, Ying-Huan Chen, Tao Tu +10
Generating complete digital twins from videos requires precise camera control, global scene coverage, and strict spatial-temporal consistency constraints that remain challenging fo…
Fiducial Exoskeletons: Image-Centric Robot State Estimation
Cameron Smith, Basile Van Hoorick, Vitor Guizilini +1
We introduce Fiducial Exoskeletons, an image-based reformulation of 3D robot state estimation that replaces cumbersome procedures and motor-centric pipelines with single-image infe…
VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
Hongyang Du, Junjie Ye, Xiaoyan Cong +7
While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deforma…
AnchorDream: Repurposing Video Diffusion for Embodiment-Aware Robot Data Synthesis
Junjie Ye, Rong Xue, Basile Van Hoorick +4
The collection of large-scale and diverse robot demonstrations remains a major bottleneck for imitation learning, as real-world data acquisition is costly and simulators offer limi…
Discriminately Treating Motion Components Evolves Joint Depth and Ego-Motion Learning
Mengtan Zhang, Zizhan Guo, Hongbo Zhao +6
Unsupervised learning of depth and ego-motion, two fundamental 3D perception tasks, has made significant strides in recent years. However, most methods treat ego-motion as an auxil…
SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images
Jiaxin Guo, Tongfan Guan, Wenzhen Dong +5
Recent advances in 3D Gaussian Splatting (3DGS) have enabled generalizable, on-the-fly reconstruction of sequential input views. However, existing methods often predict per-pixel G…
SIRE: SE(3) Intrinsic Rigidity Embeddings
Cameron Smith, Basile Van Hoorick, Vitor Guizilini +1
Motion serves as a powerful cue for scene perception and understanding by separating independently moving surfaces and organizing the physical world into distinct entities. We intr…
Neural Eulerian Scene Flow Fields
Kyle Vedder, Neehar Peri, Ishan Khatri +7
We reframe scene flow as the task of estimating a continuous space-time ODE that describes motion for an entire observation sequence, represented with a neural prior. Our method, E…
Towards Realistic Scene Generation with LiDAR Diffusion Models
Haoxi Ran, Vitor Guizilini, Yue Wang
Diffusion models (DMs) excel in photo-realistic image synthesis, but their adaptation to LiDAR scene generation poses a substantial hurdle. This is primarily because DMs operating…