13 papers · 1 filter
Unsupervised Discovery of Object-Centric Neural Fields
Rundong Luo, Hong-Xing Yu, Jiajun Wu
We study inferring 3D object-centric scene representations from a single image. While recent methods have shown potential in unsupervised 3D object discovery from simple synthetic…
PhysDreamer: Physics-Based Interaction with 3D Objects via Video Generation
Tianyuan Zhang, Hong-Xing Yu, Rundi Wu +5
Realistic object interactions are crucial for creating immersive virtual experiences, yet synthesizing realistic 3D object dynamics in response to novel interactions remains a sign…
Partial-View Object View Synthesis via Filtered Inversion
Fan-Yun Sun, Jonathan Tremblay, Valts Blukis +11
We propose Filtering Inversion (FINV), a learning framework and optimization process that predicts a renderable 3D object representation from one or few partial views. FINV address…
Reconstruction and Simulation of Elastic Objects with Spring-Mass 3D Gaussians
Licheng Zhong, Hong-Xing Yu, Jiajun Wu +1
Reconstructing and simulating elastic objects from visual observations is crucial for applications in computer vision and robotics. Existing methods, such as 3D Gaussians, model 3D…
Controllable Human-Object Interaction Synthesis
Jiaman Li, Alexander Clegg, Roozbeh Mottaghi +3
Synthesizing semantic-aware, long-horizon, human-object interaction is critical to simulate realistic human behaviors. In this work, we address the challenging problem of generatin…
Seeing a Rose in Five Thousand Ways
Yunzhi Zhang, Shangzhe Wu, Noah Snavely +1
What is a rose, visually? A rose comprises its intrinsics, including the distribution of geometry, texture, and material specific to its object category. With knowledge of these in…