The paper introduces VISTA-GS, a visibility‑guided structured measure flow framework for generating class‑conditioned 3D Gaussian Splatting (3DGS) objects. It treats a 3DGS object as a structured Gaussian measure weighted by opacity, anisotropic covariance, and multi‑view visibility, and employs a visibility‑aware VAE to learn permutation‑invariant, variable‑size, rendering‑aware latent representations. The method includes a renderer‑consistent measure flow and structure‑preserving patch transport, achieving 60–72% improvements over the strongest baseline on the VISTA‑Obj30 dataset in geometry, appearance, view‑consistency, and speed.
By Yizhao Wang
SemEllipsoid introduces a semantic‑aware shape abstraction method that uses ellipsoidal primitives to represent 3D shapes. Unlike prior geometry‑only approaches, it enforces that each primitive lies entirely within a single semantic part by incorporating semantic constraints derived from large‑scale foundation models. The fully differentiable projection‑blending‑evaluation framework allows iterative optimization of both primitive placement and semantic assignment without requiring training data, and the method supports adjustable abstraction levels across diverse shape categories.
By Kuankuan Cheng, Haocheng Yuan, Changjian Li
SeamFlow is a new generative framework for 3D surface cutting and UV unwrapping that reformulates the discrete mesh‑cutting problem as continuous flow matching in a high‑dimensional edge‑probability space. By learning a deterministic mapping from a Gaussian prior to a target seam‑probability distribution and using an evolution network to couple local topological tokens with global shape priors, SeamFlow guides smooth probability flow through ODE solving. Compared with existing autoregressive generative methods, SeamFlow improves topology awareness, eliminates 3D spatial projection errors and artificial sequential‑order bias, and achieves exceptional semantic coherence with remarkably low parameterization distortion.
By Yuming Zhao, Zangyueyang Xian, Qijian Zhang, Rendong Liang, Qin Jia, Ying He, Junhui Hou
arXiv:2608. 02306v1 Announce Type: cross Abstract: We introduce a mathematical framework for shape comparison based on mapping functions from the shape domain to a common reference domain.
By Roua Rouatbi, Juan-Esteban Suarez Cardona, Ivo F. Sbalzarini
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
GraphCAD introduces a geometry-aware generative framework for Computer-Aided Design (CAD) that models CAD construction using an Edge-Adjacency Graph (EAG), a novel graph-based representation. The method employs a hybrid graph diffusion process to jointly capture discrete topological connectivity and continuous spatial geometry, and incorporates a geometry-aware denoising mechanism that maps node attributes to SE(3)-equivariant encoded point sets. Experiments on the newly created EAGBench dataset demonstrate that GraphCAD can generate complex CAD models with more than 50 faces, achieving state‑of‑the‑art geometric fidelity and distributional alignment compared to sequence‑based baselines.
By Wenhao Zheng, Xianggen Liu, Li Yue, Jiancheng Shi, Jiancheng Lv
arXiv:2502. 08884v3 Announce Type: replace-cross Abstract: We present ShapeLib, the first method that uses the priors of Large Language Models (LLMs) to design libraries of programmatic 3D shape abstractions.
By R. Kenny Jones, Paul Guerrero, Niloy J. Mitra, Daniel Ritchie
arXiv:2605. 10873v2 Announce Type: replace-cross Abstract: Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existing evaluations are fragmented across datasets, modalities, and metrics.
By Anna C. Doris, Jacob Thomas Sony, Ghadi Nehme, Era Syla, Amin Heyrani Nobari, Faez Ahmed
arXiv:2605. 01171v2 Announce Type: replace-cross Abstract: Despite recent progress, recovering parametric CAD construction sequences from geometric input, such as meshes or point clouds, is a key challenge for design and manufacturing, as existing CAD reconstruction and generation methods are largely restricted to difficult-to-edit formats like meshes or Breps or editable simple sketch-and-extrude pipelines and low-complexity datasets.
By Ghadi Nehme, Eamon Whalen, Faez Ahmed
We introduce a mathematical framework for shape comparison based on mapping functions from the shape domain to a common reference domain. This Push-Forward Transform enables invariant and robust comparison of shapes, preserving intrinsic geometric information.
TokenMatch is a transformer-based model that estimates 3D shape correspondences by adaptively tokenising meshes into curvature-guided patches. Trained only on the BeCoS partial-to-partial dataset, it generalises to full-shape matching without retraining, using self‑ and cross‑attention to learn patch‑ and point‑level relations. Evaluated on CP2P, PSMAL, BeCoS, FAUST, SCAPE, and SHREC'19, TokenMatch consistently outperforms existing methods in mean geodesic error and intersection‑over‑union while achieving sub‑second inference speeds.
By Adeela Islam, Zorah L\"ahner, Vittorio Murino, Vladislav Golyanik
MeshCarve introduces a flow‑matching approach that generates artisan meshes entirely within compact latent spaces, separating vertex positions and edge connections to avoid joint encoding issues. It employs a hierarchical sparse transformer backbone with VertexVAE and EdgeVAE, which anchor on discrete vertices to drastically shorten token sequences and use spatial‑aware compression without sacrificing reconstruction quality. The method outperforms state‑of‑the‑art autoregressive and flow‑matching techniques on Objaverse and generalizes to Toys4K, representing one of the first fully compressed latent artisan mesh generators.
By Xiyu Wang, Ruocheng Wu, Yufei Wang, Zhihao Li, Lanqing Guo, Bihan Wen