Gaussian Garments: Reconstructing Simulation-Ready Clothing with Photorealistic Appearance from Multi-View Video
This work addresses the challenge of creating realistic digital clothing assets for applications like animation and virtual reality, representing an incremental advancement in garment reconstruction.
The authors tackled the problem of reconstructing realistic, simulation-ready garments from multi-view videos by introducing Gaussian Garments, which combine a 3D mesh and a Gaussian texture to achieve accurate geometry registration and disentangle albedo from lighting, resulting in photorealistic appearance and animatable outfits.
We introduce Gaussian Garments, a novel approach for reconstructing realistic simulation-ready garment assets from multi-view videos. Our method represents garments with a combination of a 3D mesh and a Gaussian texture that encodes both the color and high-frequency surface details. This representation enables accurate registration of garment geometries to multi-view videos and helps disentangle albedo textures from lighting effects. Furthermore, we demonstrate how a pre-trained graph neural network (GNN) can be fine-tuned to replicate the real behavior of each garment. The reconstructed Gaussian Garments can be automatically combined into multi-garment outfits and animated with the fine-tuned GNN.