ToCo-Mesh is a dynamic mesh reconstruction framework that preserves topology consistency while achieving high‑fidelity geometry from multi‑view temporal images. It uses a dual‑mesh representation, coupling a canonical template mesh to time‑varying coarse guide meshes via barycentric parameterization, and applies error‑driven split‑and‑merge operations on the template to refine detail. A Surface‑Aligned 2DGS module anchors flattened Gaussians to mesh faces, using rendered normals to guide fine‑tuning and suppress surface irregularities, resulting in photorealistic rendering.
By Chuanjin Fan, Wenjie Chang, Aibing Li, Bingzhou Wang, Wenfei Yang, Tianzhu Zhang
arXiv:2606.07288v2 Announce Type: replace
Abstract: Reconstructing surface meshes from multi-view images has remained a core challenge in recent years. Most existing methods, whether implicit or expl...
By Chuanjin Fan, Lifan Wu, Wenjie Chang, Hanzhi Chang, Wenfei Yang, Tianzhu Zhang
MeshSuite is the first benchmark designed to systematically evaluate triangle- and mesh-based neural rendering methods in both standard and dedicated engine deployment settings. It compares how different methods perform when using a conventional opaque mesh pipeline versus method-specific engine implementations, and also audits exported surfaces for topological and geometric integrity. The benchmark reveals that engine deployment generally degrades image quality, with MeshSplatting performing best under standard deployment, while dedicated deployment preserves fidelity at a higher computational cost.
By Kaixuan Zhang, Minxian Li, Mingwu Ren, Xiatian Zhu
arXiv:2610.01148v1 Announce Type: new
Abstract: Generating compact and geometrically faithful 3D meshes directly from point clouds remains a fundamental challenge. Point clouds are unordered and spar...
By Mazhar Iqbal, Naoya Chiba, Xuanmeng Sha, Tomohiro Mashita, Yuki Uranishi
arXiv:2608.29106v1 Announce Type: new
Abstract: While neural rendering methods such as 3D Gaussian Splatting achieve remarkable visual fidelity, traditional polygonal meshes remain the backbone of es...
By Tian Shi, Shenhan Qian, Daniel Cremers
MeshSplatBench is the first benchmark designed to evaluate triangle- and mesh-based neural rendering methods from native rendering to deployment in graphics engines such as Unity and Blender. It introduces a hierarchical deployment protocol with standard and dedicated options, and a structural audit for mesh splatting to assess topological and geometric integrity. The benchmark’s evaluations show that graphics engine deployment degrades quality, dedicated deployment preserves fidelity at a significant speed cost, and current mesh splatting methods lack sufficient connectivity for manifoldness.
By Kaixuan Zhang, Minxian Li, Mingwu Ren, Xiatian Zhu
Generating high-quality triangle meshes is essential for film, gaming, and interactive 3D applications. Mainstream methods rely on mesh serialization and autoregressive processes, which stuggles in effective inference and is sensitive to error accumulation.
MeshOctave introduces a novel approach to native mesh generation that replaces sequential autoregressive or heuristic flow models with a parallel, coarse-to-fine paradigm. By defining scales through dyadic spatial grid resolutions, it collapses vertices deterministically and then performs split-and-rewire operations to reconstruct fine topology without serialization. The method employs a scale-conditioned masked-uniform discrete diffusion model, achieving higher geometric fidelity and topological validity while supporting adaptive resolution refinement and mesh subdivision tasks.
By Junkai Lin, Tianhao Zhao, Hang Long, Huipeng Guo, Jielei Zhang, Youjia Zhang, Jiale Xu, Wenbing Li, Rendong Liang, Jozef Hladk\'y, Matthias Nie{\ss}ner, Yuanming Hu, Wei Yang
Real-time texture transfer expands the creative horizon for interactive applications, enabling seamless detail projection in scenarios that range from digital character cosmetics to procedural automotive texturing. Yet, its practical application is governed by inherent trade-offs between processing speed and suppression of artifacts.
TriFlow introduces a generative method for creating compact 3D meshes with artist‑like triangle topology directly from input geometry such as signed distance fields. It represents mesh topology as a nearest‑vertex vector field (NVF) over the surface, trains a latent flow‑matching model to synthesize this field, and then clusters surface regions to guide a constrained quadric error metric simplification. The resulting meshes closely match the input geometry while exhibiting structured, artist‑like connectivity, achieving 90% lower Chamfer Distance and an 8× speedup over state‑of‑the‑art learning‑based approaches.
By Haoxuan Li, Ziya Erko\c{c}, Daniele Sirigatti, Vladislav Rosov, Lei Li, Angela Dai, Matthias Nie{\ss}ner
arXiv:2609.37139v1 Announce Type: new
Abstract: 3D content generation technology has significantly advanced the work of designers, as well as the 3D printing and gaming industries. However, it remain...
By Xianze Fang, Qiyuan Feng, Dongfang Sun, Yan Zhang, Xiuchao Wu, Jingnan Gao, Jiangjing Lyu, Chengfei Lyu, Gang Yu
arXiv:2608.20687v1 Announce Type: new
Abstract: 3D Gaussian Splatting has achieved remarkable success in novel view synthesis. However, extracting high-fidelity surfaces directly from 3DGS remains ch...
By Chuanjin Fan, Wenjie Chang, Bohao Liao, Yujia Chen, Wenfei Yang, Tianzhu Zhang