🌅
🌅
Old Age
PhysDiff: Physics-Guided Human Motion Diffusion Model
December 05, 2022 · 🏛 IEEE International Conference on Computer Vision
"No code URL or promise found in abstract"
"HuggingFace models found (backfill)"
Evidence collected by the PWNC Scanner
Authors
Ye Yuan, Jiaming Song, Umar Iqbal, Arash Vahdat, Jan Kautz
arXiv ID
2212.02500
Category
cs.CV: Computer Vision
Cross-listed
cs.AI,
cs.GR,
cs.LG
Citations
371
Venue
IEEE International Conference on Computer Vision
Repository
https://huggingface.co/sujimenon/mmm-diffusion
Last Checked
9 days ago
Abstract
Denoising diffusion models hold great promise for generating diverse and realistic human motions. However, existing motion diffusion models largely disregard the laws of physics in the diffusion process and often generate physically-implausible motions with pronounced artifacts such as floating, foot sliding, and ground penetration. This seriously impacts the quality of generated motions and limits their real-world application. To address this issue, we present a novel physics-guided motion diffusion model (PhysDiff), which incorporates physical constraints into the diffusion process. Specifically, we propose a physics-based motion projection module that uses motion imitation in a physics simulator to project the denoised motion of a diffusion step to a physically-plausible motion. The projected motion is further used in the next diffusion step to guide the denoising diffusion process. Intuitively, the use of physics in our model iteratively pulls the motion toward a physically-plausible space, which cannot be achieved by simple post-processing. Experiments on large-scale human motion datasets show that our approach achieves state-of-the-art motion quality and improves physical plausibility drastically (>78% for all datasets).
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
📜 Similar Papers
In the same crypt — Computer Vision
🌅
🌅
Old Age
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
🌅
🌅
Old Age
SSD: Single Shot MultiBox Detector
🌅
🌅
Old Age
Squeeze-and-Excitation Networks
🌅
🌅
Old Age
Fast R-CNN
🌅
🌅
Old Age