Research map / Detection and segmentation / 3D detection and driving
AffoGato: Open-Vocabulary Affordance Grounding with Automated Data Generation at Scale
Junha Lee, Eunha Park, Chunghyun Park, Dahyun Kang, Minsu Cho
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 |
|---|---|---|---|
| pretrain on Affogato-750K | Espresso-3D · LASO unseen | aIoU: 18.7 -> 20.8 | Improved |
| pretrain on Affogato-750K | PointRefer · LASO unseen | aIoU: 14.6 -> 18.6 | Improved |
| pretrain on Affogato-750K | OpenAD · LASO unseen | aIoU: 14.6 -> 15.5 | Improved |
| pretrain on Affogato-750K | PointRefer · LASO seen | aIoU: 20.8 -> 20.2 | Hurt |
| pretrain on Affogato-750K | Espresso-3D · LASO seen | MAE: 0.102 -> 0.116 | Hurt |
| add Affogato-750K pretraining before fine-tuning on AGD20K-Full | Espresso-2D · AGD20K supervised | KLD: 1.034 -> 0.974 | Improved |
| add Affogato-750K pretraining | AffordanceNet · AGD20K supervised | KLD: 1.871 -> 1.721 | Improved |
| add random background augmentation in 2D pretraining (ablation) | Espresso-2D · AGD20K unseen zero-shot | SIM: 31.3 -> 37.6 | Improved |
| add random background augmentation in 2D pretraining (ablation) | Espresso-2D · AGD20K-Full fine-tuning | SIM: 47.0 -> 51.9 | Improved |
| filter held-out categories from pretraining data (ablation) | Espresso-3D · LASO unseen | aIoU: 20.8 -> 20.2 | No clear effect |
| scale pretraining data from 50K to 750K (ablation) | Espresso-3D · LASO unseen | aIoU: 18.7 -> 20.8 | Improved |
| scale pretraining data from 50K to 400K (ablation) | Espresso-2D · AGD20K unseen | KLD: 1.064 -> 0.974 | Improved |
Closest papers by meaning
- Grounding 3D Object Affordance with Language Instructions, Visual Observations and Interactions (CVPR 2025 · similarity 0.89)
- GREAT: Geometry-Intention Collaborative Inference for Open-Vocabulary 3D Object Affordance Grounding (CVPR 2025 · similarity 0.88)
- 3D-AffordanceLLM: Harnessing Large Language Models for Open-Vocabulary Affordance Detection in 3D Worlds (ICLR 2025 · similarity 0.88)
- Weakly-Supervised Affordance Grounding Guided by Part-Level Semantic Priors (ICLR 2025 · similarity 0.88)
- SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model (CVPR 2025 · similarity 0.88)
- One-Shot Open Affordance Learning with Foundation Models (CVPR 2024 · similarity 0.87)
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.
