Research map / 3D vision / Face and shape
LoRD: Local 4D Implicit Representation for High-Fidelity Dynamic Human Modeling
Boyan Jiang, Xinlin Ren, Mingsong Dou, Xiangyang Xue, Yanwei Fu, Yinda Zhang
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 inner body refining (ablation) | LoRD · CAPE 4D reconstruction (noise sigma=3) | Chamfer distance L2 (x1e-4 m^2): 1.980 -> 0.628 | Improved |
| add inner body refining (ablation) | LoRD · CAPE 4D reconstruction (noise sigma=4) | Chamfer distance L2 (x1e-4 m^2): 5.469 -> 0.896 | Improved |
| add inner body refining (ablation) | LoRD · CAPE 4D reconstruction (noise sigma=5) | Chamfer distance L2 (x1e-4 m^2): 6.815 -> 0.753 | Improved |
| add inner body refining (ablation) | LoRD · CAPE 4D reconstruction (noise sigma=5) | F-Score: 0.528 -> 0.733 | Improved |
| use part radius 5cm instead of 3cm (ablation) | LoRD · CAPE 4D reconstruction (part radius study) | F-Score: 0.858 -> 0.908 | Improved |
| use part radius 5cm instead of 8cm (ablation) | LoRD · CAPE 4D reconstruction (part radius study) | F-Score: 0.905 -> 0.908 | No clear effect |
| vary sequence length L (ablation) | LoRD · CAPE instance-level sparse reconstruction | F-Score: 0.945 (L=17) vs 0.718 (L=30) | Mixed |
| pretrain on 100 sequences before test-time optimization (ablation) | LoRD · CAPE 4D reconstruction | time: about 50 mins per sequence | Mixed |
| use local 4D part representation instead of global DeepSDF latent | LoRD · CAPE 4D human fitting (one sequence) | Chamfer distance L2 (x1e-4 m^2): 0.846 -> 0.075 | Improved |
| use local 4D parts with tracked motion instead of OFlow | LoRD · CAPE 4D human fitting (one sequence) | Chamfer distance L2 (x1e-4 m^2): 0.317 -> 0.075 | Improved |
| use LoRD instead of framewise NPMs for moving-camera depth fusion | LoRD · CAPE monocular depth fusion, moving camera | F-Score: 0.429 -> 0.750 | Improved |
Later papers that compared with this method
1 later accepted paper reports LoRD† as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow (NeurIPS 2023 · better on 2 of 3 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DeepSDF — DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (CVPR 2019) · better on 2 of 2 shared results
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
- SCALE: Modeling Clothed Humans with a Surface Codec of Articulated Local Elements (CVPR 2021 · similarity 0.89)
- 4D-DRESS: A 4D Dataset of Real-World Human Clothing With Semantic Annotations (CVPR 2024 · similarity 0.88)
- VS: Reconstructing Clothed 3D Human from Single Image via Vertex Shift (CVPR 2024 · similarity 0.88)
- D^3-Human: Dynamic Disentangled Digital Human from Monocular Video (CVPR 2025 · similarity 0.87)
- SurMo: Surface-based 4D Motion Modeling for Dynamic Human Rendering (CVPR 2024 · similarity 0.87)
- MultiGO: Towards Multi-level Geometry Learning for Monocular 3D Textured Human Reconstruction (CVPR 2025 · similarity 0.86)
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.
