The authors built a library of 141 articulated assets with pre-modeled parts, joints, and physical parameters.
Retrieval replaces generation for building simulation-ready articulated objects from a single photo
AffordCraft matches an RGB image and task instruction against a library of pre-verified part-decomposed assets, producing a physically valid simulation object 85% of the time.
Top University
Haoyun Yang · Xueyang Zhou · Ziyi Xie · Yongchao Chen
Tsinghua University · Chongqing University · Huazhong University of Science and Technology · National University of Singapore
Research Digest··3 min read
The authors present AffordCraft, a method that constructs a physically valid articulated simulation asset from a single RGB image and a task instruction by retrieving and adapting a matching entry from a library of pre-built assets, rather than estimating parts and joints from scratch.
Why this paper
From Tsinghua University and 3 others
In one line
Retrieving and adapting a library of pre-verified articulated assets generates physically valid simulation objects from single images.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ✓Compute or model size stated (hardware RTX 5090)
- ✓Limitations stated by the authors (2 noted)
- ✓Reports numbers on named benchmarks (6 benchmarks)
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§