PhysVGGT: Feed-Forward Dense Physical Property Estimation from A Single Image
Read the original on arXiv Computer Vision →PhysVGGT is a feed‑forward model that predicts dense maps of friction coefficient, Shore hardness, Young's modulus, and density, along with object‑level mass, from a single RGB image in one forward pass. It treats physical property estimation as a dense per‑pixel prediction problem, using a visual geometry transformer to extract geometry‑aware tokens and separate dense and global prediction branches. A scalable pseudo‑label generation pipeline enables large‑scale weakly supervised training, and the model achieves state‑of‑the‑art performance on the ABO‑500 dataset while running 27× faster than previous methods.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.