11 papers
Differentiate the Solver, Not the Equation: Reverse-Sweep Adjoints for Block Implicit Simulation
Lei Shu, Ying Jiang, Kui Wu +3
Differentiable simulation is a key component in learning, control, and inverse problems, where gradients through nonlinear implicit solvers are required. Existing approaches either…
SuperFlex: Deformable Superquadrics for Point Cloud Decomposition
Gabriel Tavernini, Elisabetta Fedele, Tiago Novello +3
Superquadrics have proven to provide a compact, geometrically meaningful representation for 3D objects. However, existing methods suffer from limited reconstruction accuracy, are r…
Fishbone: From One 3D Asset to a Million Controllable Edits
Yumeng He, Xiaoying Wang, Peihao Li +7
Large-scale controllable 3D assets are critical for computer graphics, embodied AI, robotics, and interactive content creation, yet creating diverse 3D assets remains challenging d…
FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos
Alexandros Delitzas, Chenyangguang Zhang, Alexey Gavryushin +8
We present FunRec, a method for reconstructing functional 3D digital twins of indoor scenes directly from egocentric RGB-D interaction videos. Unlike existing methods on articulate…
SuperDec: 3D Scene Decomposition with Superquadric Primitives
Elisabetta Fedele, Boyang Sun, Leonidas Guibas +2
We present SuperDec, an approach for creating compact 3D scene representations via decomposition into superquadric primitives. While most recent works leverage geometric primitives…
CL-Splats: Continual Learning of Gaussian Splatting with Local Optimization
Jan Ackermann, Jonas Kulhanek, Shengqu Cai +5
In dynamic 3D environments, accurately updating scene representations over time is crucial for applications in robotics, mixed reality, and embodied AI. As scenes evolve, efficient…