smpl

Proposes StudioRecon, a method for 4D human-scene reconstruction from low-overlap camera captures, using separate priors for backgrounds (video diffusion) and humans (SMPL), with a recursive enhancement module. Accepted to SIGGRAPH 2026, outperforming prior methods by +1.5 to +5.0 dB PSNR.

PoseShield introduces neural collision constraints in SMPL pose space to resolve self-collisions in human pose estimation, achieving a 95.8% success rate on a new benchmark.