D-IF: Uncertainty-aware Human Digitization via Implicit Distribution Field
This work addresses the problem of scalable and realistic human digitization for industries such as metaverse and healthcare, representing an incremental advancement over existing implicit function methods.
The paper tackles the challenge of creating realistic virtual humans by proposing an uncertainty-aware method for 3D clothed human reconstruction, which replaces deterministic implicit values with adaptive uncertainty distributions to differentiate points based on surface proximity, resulting in significant improvements on baselines and capturing more intricate details like wrinkles and realistic limbs.
Realistic virtual humans play a crucial role in numerous industries, such as metaverse, intelligent healthcare, and self-driving simulation. But creating them on a large scale with high levels of realism remains a challenge. The utilization of deep implicit function sparks a new era of image-based 3D clothed human reconstruction, enabling pixel-aligned shape recovery with fine details. Subsequently, the vast majority of works locate the surface by regressing the deterministic implicit value for each point. However, should all points be treated equally regardless of their proximity to the surface? In this paper, we propose replacing the implicit value with an adaptive uncertainty distribution, to differentiate between points based on their distance to the surface. This simple ``value to distribution'' transition yields significant improvements on nearly all the baselines. Furthermore, qualitative results demonstrate that the models trained using our uncertainty distribution loss, can capture more intricate wrinkles, and realistic limbs. Code and models are available for research purposes at https://github.com/psyai-net/D-IF_release.