- [pdf] [supp]
ConVol-E: Continuous Volumetric Embeddings for Human-Centric Dense Correspondence Estimation
We present Continuous Volumetric Embeddings (ConVol-E), a novel robust representation for dense correspondence-matching across RGB images of different human subjects in arbitrary poses and appearances under non-rigid deformation scenarios. Unlike existing represen-tations [8, 14], ConVol-E captures the deviation from the underlying parametric body model by choosing suitable anchor/key points on the underlying parametric body surface and then representing any point in the volume based on its euclidean relationship with the anchor points. It allows us to represent any arbitrary point around the parametric body (clothing details, hair, etc.) by an embedding vector. Subsequently, given a monocular RGB image of a person, we learn to predict per-pixel ConVol-E embedding, which carries a similar meaning across different subjects and is invariant to pose and appearance, thereby acting as a descriptor to establish robust dense correspondences across different images of humans. We empirically evaluate our proposed embedding using a novel metric and show superior performance compared to the state-of-the-art for the task of in-the-wild dense correspondence matching across different subjects, camera views, and appearance.