[2604.01447] Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars

Computer Science > Computer Vision and Pattern Recognition arXiv:2604.01447 (cs) [Submitted on 1 Apr 2026 (v1), last revised 3 Apr 2026 (this version, v2)] Title:Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars Authors:Derek Austin View a PDF of the paper titled Better Rigs, Not Bigger Networks: A Body Model Ablation for Gaussian Avatars, by Derek Austin View PDF HTML (experimental) Abstract:Recent 3D Gaussian splatting methods built atop SMPL achieve remarkable visual fidelity while continually increasing the complexity of the overall training architecture. We demonstrate that much of this complexity is unnecessary: by replacing SMPL with the Momentum Human Rig (MHR), estimated via SAM-3D-Body, a minimal pipeline with no learned deformations or pose-dependent corrections achieves the highest reported PSNR and competitive or superior LPIPS and SSIM on PeopleSnapshot and ZJU-MoCap. To disentangle pose estimation quality from body model representational capacity, we perform two controlled ablations: translating SAM-3D-Body meshes to SMPL-X, and translating the original dataset's SMPL poses into MHR both retrained under identical conditions. These ablations confirm that body model expressiveness has been a primary bottleneck in avatar reconstruction, with both mesh representational capacity and pose estimation quality contributing meaningfully to the full pipeline's gains. Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intell...