AI Paper Atlas

Research map / 3D vision / 3D generation

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

Jia-Wei Liu, Yan-Pei Cao, Tianyuan Yang, Zhongcong Xu, Jussi Keppo, Ying Shan, Xiaohu Qie, Mike Zheng Shou

ICCV 2023 · 3D vision › 3D generation · approach: Monocular 3D object reconstruction · 28 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add state embeddings to the base model (ablation)HOSNeRF base · HOSNeRF dataset, BackpackLPIPS: 0.271 -> 0.252Improved
add object bones to the base model (without state embeddings) (ablation)HOSNeRF base · HOSNeRF dataset, BackpackLPIPS: 0.271 -> 0.269No clear effect
add object bones on top of state embeddings (ablation)HOSNeRF · HOSNeRF dataset, SuitcaseLPIPS: 0.390 -> 0.386Improved
add foreground mask separation (ablation)HOSNeRF · HOSNeRF dataset, BackpackLPIPS: 0.253 -> 0.245Improved
add optical flow and cycle consistency supervision (ablation)HOSNeRF · HOSNeRF dataset, BackpackLPIPS: 0.245 -> 0.243Improved
add state embeddings, object bones, mask, flow and cycle versus base on Lounge scene (ablation)HOSNeRF · HOSNeRF dataset, LoungeLPIPS: 0.243 -> 0.227Improved
use HOSNeRF instead of NeuMan on collected datasetdynamic human-object scenes · HOSNeRF dataset, BackpackLPIPS: 0.478 -> 0.243Improved
use HOSNeRF (without objects) instead of NeuMan on NeuMan datasetdynamic human-scene · NeuMan dataset, SeattleLPIPS: 0.26 -> 0.14Improved
use HOSNeRF instead of NeuMan on PSNR for Lounge and Citron scenesdynamic human-object-scene · HOSNeRF Lounge / NeuMan CitronPSNR: 28.40 -> 27.74 (Lounge); 24.71 -> 24.44 (Citron)Hurt

Later papers that compared with this method

1 later accepted paper reports HOSNeRF as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy