← Back to all news
arXiv Computer Vision By Shuanglin Li, Jiaying Lin, Shuquan Ye

Grounding Generative Verification in 3D Content

Read the original on arXiv Computer Vision →

The paper introduces 3DVerifierBench, a benchmark covering ten tasks that evaluates 3D content generation for correctness, rejection explanations, and responsiveness to specification changes. It highlights a significant performance gap between humans and current models, and presents a scalable pipeline that generates over 14,000 training examples with contradiction explanations. The study also demonstrates how verification can improve 3D generation via candidate selection and recursive refinement, raising factual success rates dramatically.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
3d ago

3DCodeVerse: Exploring 3D Worlds as Code

The paper introduces 3DCodeVerse, a research ecosystem that allows coding agents to generate editable and verifiable 3D content at scale. It comprises a large curated dataset of 3D executable code (3DCodeVerse‑2M), a multi‑agent harness that automatically evaluates and refines generated programs using execution checks and spatial measurements, and empirical studies that establish baselines and practical guidance for 3D coding. Experiments show that fine‑tuning on the dataset improves open‑source models’ 3D coding abilities, and the harness outperforms Claude Design in pairwise human evaluations when used with Claude Opus 5.5.

By Yipeng Gao, Ziyao Zeng, Jinfa Huang, Yijiang Li, Haolin Xiong, Wang Qin, Xinlei Yu, Youheng Yao, Jie Zhang, Kun-Yu Lin, Rong Liu, Yinyuan Zhao, Yajie Zhao, Meiqi Guo, Jiebo Luo, Lei Shu, Yunhao Ge, Xinyu Hu, Laurent Itti
llmsagentsfine-tuning
More like this →
arXiv Computer Vision
Aug 27

Towards Fine-Grained Text-to-3D Quality Assessment: A Benchmark and A Two-Stage Rank-Learning Metric

The paper introduces T23D-CompBench, a new benchmark for fine‑grained text‑to‑3D quality assessment that includes 3,600 textured meshes generated from ten state‑of‑the‑art models and 129,600 human ratings. It also proposes Rank2Score, a two‑stage rank‑learning metric that first trains with supervised contrastive regression and curriculum learning, then refines predictions using mean opinion scores to better align with human judgments. Experiments show Rank2Score outperforms existing metrics and can be used as a reward function for generative model optimization.

By Bingyang Cui, Yujie Zhang, Qi Yang, Zhu Li, Yiling Xu
benchmarkssafety
More like this →