paper-with-me

홈 › Papers

HiFi-Mesh: High-Fidelity Efficient 3D Mesh Generation via Compact Autoregressive Dependence

2026-01-29 · Yanfeng Li, Tao Tan, Qingquan Gao, Zhiwen Cao, Xiaohong liu, Yue Sun arxiv

High-fidelity 3D meshes can be tokenized into one-dimension (1D) sequences and directly modeled using autoregressive approaches for faces and vertices. However, existing methods suffer from insufficient resource utilization, resulting in slow inference and the ability to handle only small-scale sequences, which severely constrains the expressible structural details. We introduce the Latent Autoregressive Network (LANE), which incorporates compact autoregressive dependencies in the generation process, achieving a $6\times$ improvement in maximum generatable sequence length compared to existing methods. To further accelerate inference, we propose the Adaptive Computation Graph Reconfiguration (AdaGraph) strategy, which effectively overcomes the efficiency bottleneck of traditional serial inference through spatiotemporal decoupling in the generation process. Experimental validation demonstrates that LANE achieves superior performance across generation speed, structural detail, and geometric consistency, providing an effective solution for high-quality 3D mesh generation.

📄 PDF Abstract BibTeX arXiv:2601.21314

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Scaling Mesh Generation via Compressive Tokenization

2024-11-11 · CVPR 2025 1 · Haohan Weng, Zibo Zhao, Biwen Lei, Xianghui Yang 외

We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise index…

8k

HiFiVe: High-Fidelity Vehicle Generation Leveraging Auto-Regressive 2D Generative Priors

2026-06-24 · Hongli Xiao, Youjian Zhang, Qi Zheng, Zhaohui Hu 외 arxiv

Existing 3D vehicle generation methods often suffer from low geometric fidelity and blurry textures, hindering their downstream applications. While recent works adopt multi-view diffusion models for high-fidelity texture…

HiFiHR: Enhancing 3D Hand Reconstruction from a Single Image via High-Fidelity Texture

2023-08-25 · Jiayin Zhu, Zhuoran Zhao, Linlin Yang, Angela Yao

We present HiFiHR, a high-fidelity hand reconstruction approach that utilizes render-and-compare in the learning-based framework from a single image, capable of generating visually plausible and accurate 3D hand meshes w…

FlashMesh: Faster and Better Autoregressive Mesh Synthesis via Structured Speculation

2025-11-19 · Tingrui Shen, Yiheng Zhang, Chen Tang, Chuan Ping 외 arxiv

Autoregressive models can generate high-quality 3D meshes by sequentially producing vertices and faces, but their token-by-token decoding results in slow inference, limiting practical use in interactive and large-scale a…

DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation

2024-09-11 · Haibo Yang, Yang Chen, Yingwei Pan, Ting Yao 외

Learning radiance fields (NeRF) with powerful 2D diffusion models has garnered popularity for text-to-3D generation. Nevertheless, the implicit 3D representations of NeRF lack explicit modeling of meshes and textures ove…

3D Architecture3D GenerationNeRFText to 3D