HOSNeRF: Dynamic Human-Object-Scene Neural Radiance Fields from a Single Video
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
RoHOI: Robustness Benchmark for Human-Object Interaction Detection
Locality-Aware Zero-Shot Human-Object Interaction Detection
HOI-PAGE: Zero-Shot Human-Object Interaction Generation with Part Affordance Guidance
InteractAnything: Zero-shot Human Object Interaction Synthesis via LLM Feedback and Object Affordance Parsing
MaskedManipulator: Versatile Whole-Body Control for Loco-Manipulation
Crossing the Human-Robot Embodiment Gap with Sim-to-Real RL using One Human Demonstration
토론
이 논문과 연결된 포럼 글이 아직 없습니다.