Research map / 3D vision / 3D generation
DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field
Chenyangguang Zhang, Yan Di, Ruida Zhang, Guangyao Zhai, Fabian Manhardt, Federico Tombari, Xiangyang Ji
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 |
|---|---|---|---|
| use DDF instead of SDF (ablation) | DDF-HO · ObMan | CD: almost an 80% decrease | Improved |
| add ray-based feature aggregation (RFA) (ablation) | DDF-HO · ObMan | F-5: 5% increase | Improved |
| add ray-based feature aggregation (RFA) (ablation) | DDF-HO · ObMan | F-10: 4% increase | Improved |
| add intersection-aware hand feature (IHF) (ablation) | DDF-HO with RFA · ObMan | F-5: 5% increase | Improved |
| add intersection-aware hand feature (IHF) (ablation) | DDF-HO with RFA · ObMan | F-10: 3% increase | Improved |
| add symmetry loss (SYM) (ablation) | DDF-HO with RFA and IHF · ObMan | F-5: 2% increase | Improved |
| add symmetry loss (SYM) (ablation) | DDF-HO with RFA and IHF · ObMan | F-10: 1% increase | Improved |
| add RFA, IHF and SYM (ablation) | DDF-HO · HO3D(v2) | F-5 | Improved |
| add Gaussian noise with σ=0.1 to predicted hand pose (ablation) | DDF-HO · ObMan | F-5: 0.55 -> 0.54 | Hurt |
| add Gaussian noise with σ=0.5 to predicted hand pose (ablation) | DDF-HO · ObMan | F-5: 0.55 -> 0.47 | Hurt |
| add Gaussian noise with σ=1.0 to predicted hand pose (ablation) | DDF-HO · ObMan | F-5: 0.55 -> 0.42 | Hurt |
| add Gaussian noise with σ=1.5 to predicted hand pose (ablation) | DDF-HO · ObMan | F-5: 0.55 -> 0.38 | Hurt |
Later papers that compared with this method
3 later accepted papers report DDF-HO as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Single-view Image to Novel-view Generation for Hand-Object Interactions (AAAI 2025 · better on 1 of 1 shared result)
- Coarse-to-Fine Implicit Representation Learning for 3D Hand-Object Reconstruction from a Single RGB-D Image (ECCV 2024 · better on 1 of 1 shared result)
- 3D Reconstruction of Objects in Hands without Real World 3D Supervision (ECCV 2024 · better on 0 of 1 shared result)
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
- HOISDF: Constraining 3D Hand-Object Pose Estimation with Global Signed Distance Fields (CVPR 2024 · similarity 0.89)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (AAAI 2024 · similarity 0.87)
- HOLD: Category-agnostic 3D Reconstruction of Interacting Hands and Objects from Video (CVPR 2024 · similarity 0.87)
- In-Hand 3D Object Reconstruction from a Monocular RGB Video (AAAI 2024 · similarity 0.87)
- Single-view Image to Novel-view Generation for Hand-Object Interactions (AAAI 2025 · similarity 0.87)
- EasyHOI: Unleashing the Power of Large Models for Reconstructing Hand-Object Interactions in the Wild (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.
