Research map / 3D vision / 3D generation
H2OFlow: Grounding Human-Object Affordances with 3D Generative Models and Dense Diffused Flows
Harry Zhang, Luca Carlone
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 |
|---|---|---|---|
| learn dense diffused flows instead of direct SMPL parameters (ablation) | H2OFlow · OMOMO | SIM-H (%): 57.3 -> 72.3 | Improved |
| add cross-attention weights to affordance aggregation (ablation) | H2OFlow · OMOMO | SIM-H (%): 67.3 -> 72.3 | Improved |
| add orientational affordance to contact (ablation) | H2OFlow · HOI region retrieval | mAP@10: 0.66 -> 0.69 | Improved |
| add spatial affordance to contact (ablation) | H2OFlow · HOI region retrieval | mAP@10: 0.66 -> 0.68 | Improved |
| use all three affordances (contact, orientation, spatial) (ablation) | H2OFlow · HOI region retrieval | mAP@10: 0.66 -> 0.76 | Improved |
| shuffle orientational or spatial affordances (ablation) | H2OFlow · HOI pose selection | Top-5 accuracy: 0.64 -> 0.44 | Hurt |
| occlude 50% of the object point cloud (ablation) | H2OFlow · OMOMO | SIM-H (%): 72.3 -> 70.9 | No clear effect |
| reconstruct mesh from point cloud for COMA input (ablation) | COMA · OMOMO | SIM-H (%): 41.3 -> 20.7 | Hurt |
| fine-tune H2OFlow on BEHAVE objects (ablation) | H2OFlow · BEHAVE | SIM-H (%): 55.3 -> 74.4 | Improved |
Closest papers by meaning
- Learning 2D Invariant Affordance Knowledge for 3D Affordance Grounding (AAAI 2025 · similarity 0.90)
- Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions (CVPR 2025 · similarity 0.90)
- EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views (NeurIPS 2024 · similarity 0.90)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.89)
- IAAO: Interactive Affordance Learning for Articulated Objects in 3D Environments (CVPR 2025 · similarity 0.89)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.89)
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.
