Towards Affordance-Aware Articulation Synthesis for Rigged Objects
This work addresses a novel and challenging problem in computer graphics and animation by automating the articulation of rigged objects, potentially reducing labor for artists, though it appears incremental as it builds on existing diffusion models and control techniques.
The paper tackles the problem of automatically generating realistic, affordance-aware articulation postures for rigged objects in 3D scenes, which typically requires manual effort from artists, and presents A3Syn, a method that synthesizes articulation parameters using a 2D inpainting diffusion model and control techniques, achieving plausible results on open-domain rigs and scenes in minutes.
Rigged objects are commonly used in artist pipelines, as they can flexibly adapt to different scenes and postures. However, articulating the rigs into realistic affordance-aware postures (e.g., following the context, respecting the physics and the personalities of the object) remains time-consuming and heavily relies on human labor from experienced artists. In this paper, we tackle the novel problem and design A3Syn. With a given context, such as the environment mesh and a text prompt of the desired posture, A3Syn synthesizes articulation parameters for arbitrary and open-domain rigged objects obtained from the Internet. The task is incredibly challenging due to the lack of training data, and we do not make any topological assumptions about the open-domain rigs. We propose using 2D inpainting diffusion model and several control techniques to synthesize in-context affordance information. Then, we develop an efficient bone correspondence alignment using a combination of differentiable rendering and semantic correspondence. A3Syn has stable convergence, completes in minutes, and synthesizes plausible affordance on different combinations of in-the-wild object rigs and scenes.