Coin3D: Controllable and Interactive 3D Assets Generation with Proxy-Guided Conditioning
This addresses the need for more accessible and efficient 3D modeling tools for content creators, though it appears incremental as it builds on existing diffusion models and 3D generation techniques.
The paper tackles the problem of controllable and interactive 3D asset generation, which lacks efficiency and user control compared to 2D methods, by introducing Coin3D, a framework that enables users to control generation using coarse geometry proxies and supports seamless local editing with responsive previews in seconds.
As humans, we aspire to create media content that is both freely willed and readily controlled. Thanks to the prominent development of generative techniques, we now can easily utilize 2D diffusion methods to synthesize images controlled by raw sketch or designated human poses, and even progressively edit/regenerate local regions with masked inpainting. However, similar workflows in 3D modeling tasks are still unavailable due to the lack of controllability and efficiency in 3D generation. In this paper, we present a novel controllable and interactive 3D assets modeling framework, named Coin3D. Coin3D allows users to control the 3D generation using a coarse geometry proxy assembled from basic shapes, and introduces an interactive generation workflow to support seamless local part editing while delivering responsive 3D object previewing within a few seconds. To this end, we develop several techniques, including the 3D adapter that applies volumetric coarse shape control to the diffusion model, proxy-bounded editing strategy for precise part editing, progressive volume cache to support responsive preview, and volume-SDS to ensure consistent mesh reconstruction. Extensive experiments of interactive generation and editing on diverse shape proxies demonstrate that our method achieves superior controllability and flexibility in the 3D assets generation task.