CloseUpAvatar: High-Fidelity Animatable Full-Body Avatars with Mixture of Multi-Scale Textures

TL;DR

CloseUpAvatar introduces a novel avatar representation that adaptively switches texture detail based on camera distance, enabling high-quality, realistic rendering across diverse camera angles and positions.

Contribution

It proposes a new textured plane-based avatar model with automatic high-frequency detail switching for improved rendering quality and efficiency.

Findings

Outperforms existing methods in rendering quality from various camera angles.

Maintains high frame rates by limiting primitives used.

Demonstrates effectiveness on the ActorsHQ dataset.

Abstract

We present a CloseUpAvatar - a novel approach for articulated human avatar representation dealing with more general camera motions, while preserving rendering quality for close-up views. CloseUpAvatar represents an avatar as a set of textured planes with two sets of learnable textures for low and high-frequency detail. The method automatically switches to high-frequency textures only for cameras positioned close to the avatar's surface and gradually reduces their impact as the camera moves farther away. Such parametrization of the avatar enables CloseUpAvatar to adjust rendering quality based on camera distance ensuring realistic rendering across a wider range of camera orientations than previous approaches. We provide experiments using the ActorsHQ dataset with high-resolution input images. CloseUpAvatar demonstrates both qualitative and quantitative improvements over existing methods in rendering from novel wide range camera positions, while maintaining high FPS by limiting the number of required primitives.