Jiayi Hong
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Jiayi Hong has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Wenjie Qin
School of Computer and Intelligent Education, Lingnan Normal University, Zhanjiang 524048, China
2 shared publications - Xuming Wu
College of Physical Science and Technology, Lingnan Normal University, 524048 Zhanjiang, China
2 shared publications - Yan Cao
College of Physics and Electronic Information, Luoyang Normal University, Luoyang 471934, China
2 shared publications - Yuan Zhang
School of Computer and Intelligent Education, Lingnan Normal University, Zhanjiang 524048, China
2 shared publications - Zhibin Shao
Physics Laboratory, Industrial Training Center, Shenzhen Polytechnic University, Shenzhen 518055, China
2 shared publications - Zhipeng Ye
School of Chemistry and Chemical Engineering, Lingnan Normal University, Zhanjiang 524048, China
2 shared publications
Latest Publications
- Open Access
- 28 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (17) , 3877
GeoTrack-GS: Track-Guided Geometry Refinement for Sparse-View 3D Gaussian Splatting
Three-dimensional Gaussian Splatting (3DGS) can degrade severely in sparse-view settings because the optimization is under-constrained. Monocular depth priors provide dense supervision, but their inconsistency across views can distort geometry. We propose GeoTrack-GS, a geometry-first framework. We use monocular depth as a fixed, dense weak regularizer for Gaussian geometry. Sparse feature tracks enforce macro-level reprojection consistency, while a micro-level K-NN PCA regularizer suppresses rank collapse. These constraints refine the Gaussian geometry during optimization without explicitly updating the input depth maps. On the optimized Gaussian geometry, GT-DCA captures view-dependent appearance; its geometry-conditioned query is stop-gradient isolated so that the GT-DCA branch does not introduce an additional appearance-to-geometry gradient path through query construction. A Decoupled Constraint Stabilization strategy modulates the geometric and pseudo-view constraints during training. Across LLFF and DTU with 3–9 input views, and Mip-NeRF 360 with 12 input views, GeoTrack-GS maintains competitive rendering quality. It also improves geometric metrics under the evaluated DTU protocol. This geometric conclusion is restricted to DTU, the benchmark in which ground-truth geometry is quantitatively evaluated.
- 28 August 2026
- Published by MDPI AG in Electronics
- Vol. 15 (17) , 3877
Open AccessGeoTrack-GS: Track-Guided Geometry Refinement for Sparse-View 3D Gaussian Splatting
Three-dimensional Gaussian Splatting (3DGS) can degrade severely in sparse-view settings because the optimization is under-constrained. Monocular depth priors provide dense supervision, but their inconsistency across views can distort geometry. We propose GeoTrack-GS, a geometry-first framework. We use monocular depth as a fixed, dense weak regularizer for Gaussian geometry. Sparse feature tracks enforce macro-level reprojection consistency, while a micro-level K-NN PCA regularizer suppresses rank collapse. These constraints refine the Gaussian geometry during optimization without explicitly updating the input depth maps. On the optimized Gaussian geometry, GT-DCA captures view-dependent appearance; its geometry-conditioned query is stop-gradient isolated so that the GT-DCA branch does not introduce an additional appearance-to-geometry gradient path through query construction. A Decoupled Constraint Stabilization strategy modulates the geometric and pseudo-view constraints during training. Across LLFF and DTU with 3–9 input views, and Mip-NeRF 360 with 12 input views, GeoTrack-GS maintains competitive rendering quality. It also improves geometric metrics under the evaluated DTU protocol. This geometric conclusion is restricted to DTU, the benchmark in which ground-truth geometry is quantitatively evaluated.
- Open Access
- 5 May 2026
- Published by MDPI AG in Preprints.org
GeoTrack-GS: Refining Depth Priors with Self-Supervised Geometric Constraints
3D Gaussian Splatting (3DGS) degrades severely in sparse-view scenarios, often collapsing into artifacts due to under-constrained optimization. While incorporating monocular depth priors provides dense supervision, their inherent multi-view inconsistency frequently distorts geometry. To address this, we propose GeoTrack-GS, a geometry-first framework that refines noisy depth priors using reliable self-supervised constraints. Specifically, we leverage sparse feature tracks to enforce macro-level reprojection consistency and introduce a micro-level anisotropic regularizer via K-NN PCA to suppress rank-collapse. On this corrected geometry, we design GT-DCA, a geometry-guided deformable cross-attention module that captures view-dependent appearance without compromising structure. A Decoupled Constraint Stabilization strategy further balances these heterogeneous signals during training. Experiments on LLFF and DTU under 3-9 input views, and on Mip-NeRF 360 under 12 input views, demonstrate that GeoTrack-GS achieves state-of-the-art geometric fidelity while maintaining competitive rendering quality compared to existing baselines, effectively reducing floaters and "waxy" surfaces.
- 5 May 2026
- Published by MDPI AG in Preprints.org
Open AccessGeoTrack-GS: Refining Depth Priors with Self-Supervised Geometric Constraints
3D Gaussian Splatting (3DGS) degrades severely in sparse-view scenarios, often collapsing into artifacts due to under-constrained optimization. While incorporating monocular depth priors provides dense supervision, their inherent multi-view inconsistency frequently distorts geometry. To address this, we propose GeoTrack-GS, a geometry-first framework that refines noisy depth priors using reliable self-supervised constraints. Specifically, we leverage sparse feature tracks to enforce macro-level reprojection consistency and introduce a micro-level anisotropic regularizer via K-NN PCA to suppress rank-collapse. On this corrected geometry, we design GT-DCA, a geometry-guided deformable cross-attention module that captures view-dependent appearance without compromising structure. A Decoupled Constraint Stabilization strategy further balances these heterogeneous signals during training. Experiments on LLFF and DTU under 3-9 input views, and on Mip-NeRF 360 under 12 input views, demonstrate that GeoTrack-GS achieves state-of-the-art geometric fidelity while maintaining competitive rendering quality compared to existing baselines, effectively reducing floaters and "waxy" surfaces.