Research map / 3D vision / 3D generation
LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation
Jiaxiang Tang, Zhaoxi Chen, Xiaokang Chen, Tengfei Wang, Gang Zeng, Ziwei Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use four input views from multi-view diffusion instead of a single input view (ablation) | LGM · image-to-3D qualitative | back-view quality | Improved |
| add grid distortion and orbital camera jitter augmentation (ablation) | LGM · image-to-3D with diffusion-generated views | floaters and geometry quality | Improved |
| raise training resolution to 512 with 65,536 Gaussians instead of 256 with 16,384 Gaussians (ablation) | LGM · image-to-3D qualitative | detail quality: 16,384 -> 65,536 Gaussians | Improved |
| use LGM instead of DreamGaussian or TriplaneGaussian for image-to-3D | image-to-3D Gaussians · user study | overall quality (1-5): 2.67 -> 3.95 (vs TriplaneGaussian) | Improved |
| extract mesh via Gaussians-to-NeRF-to-mesh instead of opacity-based occupancy field | LGM mesh extraction · mesh extraction | surface smoothness | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- DreamGaussian — DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation (ICLR 2024) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- L4GM: Large 4D Gaussian Reconstruction Model (NeurIPS 2024 · similarity 0.90)
- MVGamba: Unify 3D Content Generation as State Space Sequence Modeling (NeurIPS 2024 · similarity 0.89)
- Prometheus: 3D-Aware Latent Diffusion Models for Feed-Forward Text-to-3D Scene Generation (CVPR 2025 · similarity 0.88)
- IT3D: Improved Text-to-3D Generation with Explicit View Synthesis (AAAI 2024 · similarity 0.88)
- IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation (ICML 2024 · similarity 0.88)
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
