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
Optimizing 3D shapes within the latent spaces of deep generative models is fundamental to computer assisted engineering, yet remains prone to a critical failure mode we term manifold drift: the tendency of gradient-based optimization to move latent vectors away from the manifold of valid shapes. This problem is exacerbated in state-of-the-art 3D shape generative models that operate in increasingly high-dimensional latent spaces where valid shapes occupy a vanishingly small fraction of the full space.
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.
arXiv:2608.23173v1 Announce Type: new
Abstract: Computer vision applications for 3D scene understanding in underwater environments remain challenging due to the lack of high-quality 3D data and the i...
By Joaqu\'in Figueira, Camile Lendering, Manfred Gonzalez-Hernandez, Giacomo D'Amicantonio, Erkut Akdag, Egor Bondarev
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
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
arXiv:2605.12957v2 Announce Type: replace
Abstract: Recent developments in generative models and large-scale datasets have substantially advanced 3D world generation, facilitating a broad range of do...
By Hanxin Zhu, Cong Wang, Peiyan Tu, Jiayi Luo, Tianyu He, Xin Jin, Zhibo Chen
arXiv:2606.23489v2 Announce Type: replace-cross
Abstract: Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains...
By Qi Sun, Kiyohiro Nakayama, Jing Nathan Yan, Qixing Huang, Alexander Rush, Leonidas Guibas, Gordon Wetzstein, Jing Liao, Guandao Yang
arXiv:2609.08153v1 Announce Type: new
Abstract: Generative diffusion models have emerged as a class of powerful techniques for various imaging applications, including but not limited to synthesis, re...
By Nian Wu, Nivetha Jayakumar, Jiarui Xing, Miaomiao Zhang
CoMVS‑GS is a surface‑reconstruction framework that fuses Multi‑View Stereo (MVS) with 3D Gaussian splatting. It initializes Gaussian primitives from dense MVS points, uses PatchMatch‑3DGS mutual supervision to refine depths and normals, and replaces voxel‑based meshing with a Delaunay graph‑cut pipeline. Experiments on DTU, GauU‑Scene V2, and MatrixCity demonstrate competitive object‑level results and improved geometric accuracy and mesh compactness in outdoor scenes while preserving high rendering quality.
Geometric foundation models, such as the Visual Geometry Grounded Transformer (VGGT), provide strong 3D priors from unposed images. However, such models operate purely in a feed-forward, deterministic regime, \ie~they cannot generate plausible geometry beyond what the input views directly support.
arXiv:2602. 07429v2 Announce Type: replace-cross Abstract: Boundary representation (B-rep) is the industry standard for computer-aided design (CAD).
By Yuanxu Sun, Yuezhou Ma, Haixu Wu, Guanyang Zeng, Muye Chen, Jianmin Wang, Mingsheng Long