Lune

CVPR Findings2026

Native3D: End-to-End 3D Scene Generation via Unified Mesh-Texture Modeling and Semantic Alignment

Yibo Liu, Ziwei Zhang, Haozhou Pang, Menghao Li, Lanshan He, Gan Qi

Abstract

To address these limitations, we design a unified mesh-texture joint representation that simultaneously models both geometric structures and texture features through a Transformer-based scene encoder, effectively maintaining spatial relationships and visual consistency among objects within scenes. We further propose the 3D Representation Alignment Loss (3D REPA Loss), which employs an improved contrastive learning mechanism to align multi-level semantic representations in the latent space, significantly enhancing geometric and textural fidelity. Experimental results demonstrate that Native3D outperforms existing methods in both generation quality and editing flexibility, providing a novel solution for 3D scene editing.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation cites High-Resolution Image Synthesis with Latent Diffusion Models
  • ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation cites Learning Transferable Visual Models From Natural Language Supervision
  • CLIPScore: A Reference-free Evaluation Metric for Image Captioning cites Learning Transferable Visual Models From Natural Language Supervision
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on23

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
  3. Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou et al.ICCV 2021 · 8,921 citations
  4. ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score DistillationZhengyi Wang, Cheng Lu, Yikai Wang, Fan Bao et al.NeurIPS 2023 · 1,498 citations
  5. CLIPScore: A Reference-free Evaluation Metric for Image CaptioningJack Hessel, Ari Holtzman, Maxwell Forbes, Ronan Le Bras et al.EMNLP 2021 · 937 citations

Related papers

  1. UniLat3D: Geometry-Appearance Unified Latents for Single-Stage 3D GenerationGuanjun Wu, Jiemin Fang, Chen Yang, Sikuang Li, Taoran Yi, Jia Lu, Zanwei Zhou, Jiazhong Cen, Lingxi Xie, Xiaopeng Zhang, Wei Wei, Wenyu Liu, Xinggang Wang, Qi TianCVPR Findings 2026
  2. NaTex: Seamless Texture Generation as Latent Color DiffusionZeqiang Lai, Yunfei Zhao, Zibo Zhao, Xin Yang et al.CVPR 2026 · 11 citations
  3. RELATE3D: REfocusing Latent Adapter for Targeted local Enhancement and Editing in 3D GenerationXiao-Lei Li, Hao-Xiang Chen, Yanni Zhang, Kai Ma et al.SIGGRAPH 2025 · 2 citations
  4. Interp3D: Correspondence-aware Interpolation for Generative Textured 3D MorphingXiaolu Liu, Yicong Li, Qiyuan He, Jiayin Zhu et al.ICLR 2026 · 6 citations
  5. Vinedresser3D: Towards Agentic Text-guided 3D EditingYankuan Chi, Xiang Li, Zixuan Huang, James M.CVPR 2026
Dusk over the sea between two cliffs drawn in fine vertical lines