Research map / 3D vision / 3D generation
HiSC4D: Human-Centered Interaction and 4D Scene Capture in Large-Scale Space Using Wearable IMUs and LiDAR
Yudi Dai, Zhiyong Wang, Xiping Lin, Chenglu Wen, Lan Xu, Siqi Shen, Yuexin Ma, Cheng Wang
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add LiDAR localization to IMU-only capture | IMU-based motion capture · HiSC4D first person GLE | GLE (mm): 2602.1 -> 49.6 | Improved |
| add multi-stage joint optimization to Baseline2 | IMU+LiDAR baseline · HiSC4D first person GLE | GLE (mm): 49.6 -> 41.1 | Improved |
| add ICP alignment to human point clouds | IMU baseline · HiSC4D second person | CD_v2p (mm): 569.7 -> 65.1 | Improved |
| add joint optimization to Baseline2 | IMU+LiDAR baseline · HiSC4D second person | CD_v2p (mm): 65.1 -> 31.0 | Improved |
| add joint optimization to Baseline2 | IMU+LiDAR baseline · HiSC4D first person | ACC (m/s^2): 2.5 -> 1.8 | Improved |
| add scene-aware terms L_scene (ablation) | HiSC4D · HiSC4D first person | CD_foot (mm): 26.6 -> 10.9 | Improved |
| add physical terms L_phy (ablation) | HiSC4D · HiSC4D first person | GLE (mm): 236.7 -> 41.1 | Improved |
| add physical terms L_phy (ablation) | HiSC4D · HiSC4D second person | CD_v2p (mm): 122.9 -> 31.0 | Improved |
| add scene-aware terms L_scene (ablation) | HiSC4D · HiSC4D second person | CD_v2p (mm): 36.9 -> 31.0 | Improved |
| add scene-aware terms L_scene (ablation) | HiSC4D · HiSC4D first person | GLE (mm): 35.2 -> 41.1 | Hurt |
| add self, scene and physical terms to smoothness-only loss (ablation) | HiSC4D · HiSC4D first person | ACC (m/s^2): 0.8 -> 1.8 | Hurt |
| add multi-stage optimization strategy (ablation) | HiSC4D optimization · Sequence S4 first person | runtime (h): 2.13 -> 0.73 | Improved |
Closest papers by meaning
- RELI11D: A Comprehensive Multimodal Human Motion Dataset and Method (CVPR 2024 · similarity 0.87)
- CORE4D: A 4D Human-Object-Human Interaction Dataset for Collaborative Object REarrangement (CVPR 2025 · similarity 0.86)
- Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions (NeurIPS 2024 · similarity 0.85)
- LiveHPS: LiDAR-based Scene-level Human Pose and Shape Estimation in Free Environment (CVPR 2024 · similarity 0.85)
- HOI-M^3: Capture Multiple Humans and Objects Interaction within Contextual Environment (CVPR 2024 · similarity 0.85)
- Neighborhood-Enhanced 3D Human Pose Estimation with Monocular LiDAR in Long-Range Outdoor Scenes (AAAI 2024 · similarity 0.84)
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.
