MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos
This addresses the need for editable and manipulatable human avatars in graphics and animation, though it is incremental as it builds on existing implicit field and rendering techniques.
The paper tackles the problem of creating high-quality triangular human avatars from multi-view videos, overcoming limitations of neural radiance fields by using an explicit mesh representation with physics-based rendering, resulting in avatars that support editing and manipulation.
We present a novel pipeline for learning high-quality triangular human avatars from multi-view videos. Recent methods for avatar learning are typically based on neural radiance fields (NeRF), which is not compatible with traditional graphics pipeline and poses great challenges for operations like editing or synthesizing under different environments. To overcome these limitations, our method represents the avatar with an explicit triangular mesh extracted from an implicit SDF field, complemented by an implicit material field conditioned on given poses. Leveraging this triangular avatar representation, we incorporate physics-based rendering to accurately decompose geometry and texture. To enhance both the geometric and appearance details, we further employ a 2D UNet as the network backbone and introduce pseudo normal ground-truth as additional supervision. Experiments show that our method can learn triangular avatars with high-quality geometry reconstruction and plausible material decomposition, inherently supporting editing, manipulation or relighting operations.