4DPV: 4D pet from videos by coarse-to-fine non-rigid radiance fields

Abstract

Lecture Notes in Computer Science (LNCS, volume 15480). © 2025 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

We present a coarse-to-fine neural deformation model to simultaneously recover the camera pose and the 4D reconstruction of an unknown object from multiple RGB sequences in the wild. To that end, our approach does not consider any pre-built 3D template nor 3D training data as well as controlled illumination conditions, and can sort out the problem in a self-supervised manner. Our model exploits canonical and image-variant spaces where both coarse and fine components are considered. We introduce a neural local quadratic model with spatio-temporal consistency to encode fine details that is combined with canonical embeddings in order to establish correspondences across sequences. We thoroughly validate the method on challenging scenarios with complex and real-world deformations, providing both quantitative and qualitative evaluations, an ablation study and a comparison with respect to competing approaches.

Work produced with the support of a 2023 Leonardo Grant for Scientific Research and Cultural Creation, BBVA Foundation.

Peer Reviewed

Postprint (published version)