HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video

TL;DR

HOSNeRF is a novel method that reconstructs dynamic human-object-scene neural radiance fields from a single monocular video, enabling detailed 360-degree free-viewpoint rendering of complex interactions.

Contribution

It introduces object bones and learnable object state embeddings to effectively model large deformations and interactions in dynamic scenes from monocular videos.

Findings

Outperforms SOTA by 40-50% in LPIPS

Enables pausing and viewing from arbitrary angles

Handles complex human-object interactions

Abstract

We introduce HOSNeRF, a novel 360{\deg} free-viewpoint rendering method that reconstructs neural radiance fields for dynamic human-object-scene from a single monocular in-the-wild video. Our method enables pausing the video at any frame and rendering all scene details (dynamic humans, objects, and backgrounds) from arbitrary viewpoints. The first challenge in this task is the complex object motions in human-object interactions, which we tackle by introducing the new object bones into the conventional human skeleton hierarchy to effectively estimate large object deformations in our dynamic human-object model. The second challenge is that humans interact with different objects at different times, for which we introduce two new learnable object state embeddings that can be used as conditions for learning our human-object representation and scene representation, respectively. Extensive experiments show that HOSNeRF significantly outperforms SOTA approaches on two challenging datasets by a large margin of 40% ~ 50% in terms of LPIPS. The code, data, and compelling examples of 360{\deg} free-viewpoint renderings from single videos will be released in https://showlab.github.io/HOSNeRF.