HHMR: Holistic Hand Mesh Recovery by Enhancing the Multimodal Controllability of Graph Diffusion Models
This work addresses the need for a unified approach to hand mesh recovery, which could benefit applications like gesture recognition and mesh editing, though it appears incremental as it builds on existing generative and reconstruction paradigms.
The paper tackles the problem of performing multiple hand mesh recovery tasks (generation, inpainting, reconstruction, and fitting) within a single framework, achieving this by enhancing the multimodal controllability of a graph diffusion model, with experiments showing it outperforms existing methods across different tasks.
Recent years have witnessed a trend of the deep integration of the generation and reconstruction paradigms. In this paper, we extend the ability of controllable generative models for a more comprehensive hand mesh recovery task: direct hand mesh generation, inpainting, reconstruction, and fitting in a single framework, which we name as Holistic Hand Mesh Recovery (HHMR). Our key observation is that different kinds of hand mesh recovery tasks can be achieved by a single generative model with strong multimodal controllability, and in such a framework, realizing different tasks only requires giving different signals as conditions. To achieve this goal, we propose an all-in-one diffusion framework based on graph convolution and attention mechanisms for holistic hand mesh recovery. In order to achieve strong control generation capability while ensuring the decoupling of multimodal control signals, we map different modalities to a shared feature space and apply cross-scale random masking in both modality and feature levels. In this way, the correlation between different modalities can be fully exploited during the learning of hand priors. Furthermore, we propose Condition-aligned Gradient Guidance to enhance the alignment of the generated model with the control signals, which significantly improves the accuracy of the hand mesh reconstruction and fitting. Experiments show that our novel framework can realize multiple hand mesh recovery tasks simultaneously and outperform the existing methods in different tasks, which provides more possibilities for subsequent downstream applications including gesture recognition, pose generation, mesh editing, and so on.