Peer-reviewed veterinary case report
How two photos can create a 3D human model
By Chen Y et al.·2026·View original on Europe PMC →
PetCaseFinder translated the abstract of this peer-reviewed paper into plain English so pet owners can read it. We do not publish original research — every detail traces back to the citation above. How we work →
Original publication title: DuetGS: Two-Stage Controllable 3D Human Reconstruction from Dual Images.
Plain-English summary
This research focuses on creating realistic 3D models of humans using just two images, one from the front and one from the back. The challenge is that having only two views makes it hard to get accurate depth and color details. The researchers developed a new method called DuetGS, which works in two steps: first, it builds the shape of the body using a special computer program, and then it adds color details. They tested their method on several datasets and found that it produced better results than previous techniques in both accuracy and appearance.
Abstract
Creating realistic and fully detailed 3D human models using a minimal number of views has long been a challenging goal in 3D human reconstruction. Reconstructing a realistic human model from only two images (front and back) is particularly difficult due to the limited 3D information available, leading to two major challenges: (1) it is difficult to establish spatial consistency for reconstruction due to the lack of sufficient images for reliable matching, and (2) incomplete field of view results in missing color information. To address these challenges, we propose DuetGS, a novel pipeline that divides the reconstruction process into two stages: geometry reconstruction and color reconstruction. For geometry reconstruction, we employ a data-driven neural network to recover a full-body mesh from the front and back images, providing the spatial positioning for Gaussians. For color reconstruction, we adapt Gaussian Splatting and integrate our proposed unsupervised color propagation method to establish the color details of the Gaussians. Furthermore, our Gaussians are directly mapped to the mesh, allowing us to control their rotation and translation through mesh manipulation. This mapping ensures compatibility with various animation techniques. Extensive experiments on the THUman, CustomHumans, and PeopleSnapshot datasets demonstrate that our approach outperforms existing methods in terms of reconstruction accuracy and visual quality.
Find similar cases for your pet
PetCaseFinder finds other peer-reviewed reports of pets with the same symptoms, plus a plain-English summary of what was tried across them.
Search related cases →Original publication on Europe PMC: https://europepmc.org/article/MED/42013276