HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video
This enables 360° free-viewpoint rendering of complex interactions from in-the-wild videos, advancing applications in VR/AR and content creation.
The paper tackles the problem of reconstructing dynamic human-object-scene neural radiance fields from a single monocular video, achieving a 40% to 50% improvement in LPIPS over state-of-the-art methods.
We introduce HOSNeRF, a novel 360° 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° free-viewpoint renderings from single videos will be released in https://showlab.github.io/HOSNeRF.