Research map / 3D vision / 3D generation
CoherenDream: Boosting Holistic Text Coherence in 3D Generation via Multimodal Large Language Models Feedback
Chenhan Jiang, Yihan Zeng, Dit-Yan Yeung
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 |
|---|---|---|---|
| fine-tune 3DLLaVA-CRITIC instead of off-the-shelf LLaVA-OV-0.5B (ablation) | critic · scene graph task | accuracy: 0.21 -> 0.76 | Improved |
| fine-tune critic instead of off-the-shelf (ablation) | critic · multi-label classification | accuracy: 0.34 -> 0.89 | Improved |
| fine-tune critic instead of off-the-shelf (ablation) | critic · view classification | accuracy: 0.72 -> 0.87 | Improved |
| add TCSD MLLM feedback to SDS (ablation) | MVDream distillation · qualitative (Fig 5) | text alignment | Improved |
| add LLM-Layout initialization (ablation) | CoherenDream · qualitative (Fig 6) | text alignment | Improved |
| use fine-tuned 3DLLaVA-CRITIC instead of LLaVA (ablation) | TCSD · qualitative (Fig 6) | text alignment | Improved |
| CoherenDream vs MVDream | text-to-3D · TIFA subset | TIFA score: 77.4 -> 81.4 | 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.
- JointDreamer — JointDreamer: Ensuring Geometry Consistency and Text Congruence in Text-to-3D Generation via Joint Score Distillation (ECCV 2024) · better on 3 of 3 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
- Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation (ICLR 2024 · similarity 0.90)
- Retrieval-Augmented Score Distillation for Text-to-3D Generation (ICML 2024 · similarity 0.89)
- CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models (ICML 2026 · similarity 0.89)
- Let Language Constrain Geometry: Vision–Language Models as Semantic and Spatial Critics for 3D Generation (ICML 2026 · similarity 0.89)
- A3D: Does Diffusion Dream about 3D Alignment? (ICLR 2025 · similarity 0.88)
- LucidDreamer: Towards High-Fidelity Text-to-3D Generation via Interval Score Matching (CVPR 2024 · similarity 0.88)
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.
