Research map / 3D vision / 3D generation
FlexGen: Flexible Multi-View Generation from Text and Image Inputs
Xinli Xu, Wenhang Ge, Jiantao Lin, Jiawei Feng, Lie Xu, Hanfeng Zhao, Shunsi Zhang, Ying-Cong Chen
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 |
|---|---|---|---|
| add 3D-aware caption conditioning (ablation) | FlexGen · GSO NVS and sparse-view reconstruction (300 samples) | PSNR: 21.12 -> 22.31 | Improved |
| add 3D-aware caption conditioning (ablation) | FlexGen · GSO NVS and sparse-view reconstruction (300 samples) | LPIPS: 0.14 -> 0.12 | Improved |
| add 3D-aware caption conditioning (ablation) | FlexGen · GSO NVS and sparse-view reconstruction (300 samples) | Chamfer Distance: 0.078 -> 0.076 | Improved |
| add 3D-aware caption conditioning (ablation) | FlexGen · GSO NVS and sparse-view reconstruction (300 samples) | FS@0.1: 0.921 -> 0.928 | Improved |
| use GPT-4V 3D-aware captions instead of Cap3D captions (ablation) | FlexGen · Text-controlled multi-view generation (qualitative) | text editing control | 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.
- SyncDreamer — SyncDreamer: Generating Multiview-consistent Images from a Single-view Image (ICLR 2024) · better on 4 of 4 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
- Flex3D: Feed-Forward 3D Generation with Flexible Reconstruction Model and Input View Curation (ICML 2025 · similarity 0.89)
- CoSER: Towards Consistent Dense Multiview Text-to-Image Generator for 3D Creation (CVPR 2025 · similarity 0.85)
- Learning Continuous 3D Words for Text-to-Image Generation (CVPR 2024 · similarity 0.85)
- ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models (CVPR 2024 · similarity 0.85)
- FlexiTex: Enhancing Texture Generation via Visual Guidance (AAAI 2025 · similarity 0.85)
- EfficientDreamer: High-Fidelity and Robust 3D Creation via Orthogonal-view Diffusion Priors (CVPR 2024 · similarity 0.85)
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.
