arXiv Computer Vision

Cyc3D: Evaluating Cyclic Structural Stability and Asset Usability in Image-to-3D Generation

Cyc3D is a new benchmark for image‑to‑3D generation that evaluates both Cross‑View Object Consistency and Representation Quality. It introduces a closed‑loop View‑Cycle Structural Consistency protocol to measure geometric, perceptual, and semantic drift across repeated render‑regenerate cycles, and also assesses asset usability through geometric structure, fidelity, mesh discretization, and UV quality. Experiments show that closed‑source models outperform open‑source baselines yet still score below 48 on cycle stability, highlighting a gap between visual plausibility and robust 3D understanding.

arXiv Computer Vision

3d ago

Orbia: Do Generated Videos Form a Consistent 3D World?

Orbia is a new benchmark that systematically evaluates 3D consistency in interactive video world models. It organizes evaluation into three dimensions—input preservation, generated‑content persistence, and 3D self‑consistency—using controlled exploration and revisit protocols. The benchmark covers 720 instances across indoor and outdoor scenes and tests 27 different models, providing a comprehensive framework for diagnosing and improving 3D consistency.

By Dongyue Lu, Guian Fang, Hur Lim, Yonggang Wu, Yanrong Wang, Hongshan Chen, Shengju Qian, Yue Liao, Wei Chow, Lingdong Kong, Tianxin Huang, Yu Yang, Hongji Yang, Junchao Huang, Ao Liang, Yihao Wang, Zihan Wang, Rong Li, Hanlin Chen, Xin Wang, Wei Tsang Ooi, Mike Zheng Shou, Shuicheng Yan

llms multimodal benchmarks

arXiv AI

4d ago

Feed-Forward 3D Scene Modeling: A Problem-Driven Perspective

arXiv:2604.14025v2 Announce Type: replace-cross Abstract: Reconstructing 3D representations from 2D inputs is a fundamental task in computer vision and graphics, serving as a cornerstone for understa...

By Weijie Wang, Qihang Cao, Sensen Gao, Donny Y. Chen, Haofei Xu, Wenjing Bian, Songyou Peng, Tat-Jen Cham, Chuanxia Zheng, Andreas Geiger, Jianfei Cai, Jia-Wang Bian, Bohan Zhuang

computer-vision benchmarks

arXiv Computer Vision

Oct 7

DB-3DME: From Dataset to Benchmark for Human-aligned Automatic 3D Mesh Evaluation

arXiv:2606.10142v2 Announce Type: replace Abstract: Recent advances in 3D generation have led to substantial improvements in realism, controllability, and efficiency, yet the evaluation of 3D assets...

By Nanshan Jia, Zhenyu Zhao, Junbo Peng, Sui Huang, Jingshen Wang, Zeyu Zheng

llms fine-tuning multimodal benchmarks safety

arXiv AI

Jun 19

CADBench: A Multimodal Benchmark for AI-Assisted CAD Program Generation

arXiv:2605. 10873v2 Announce Type: replace-cross Abstract: Recovering editable CAD programs from images or 3D observations is central to AI-assisted design, but progress is difficult to measure because existing evaluations are fragmented across datasets, modalities, and metrics.

By Anna C. Doris, Jacob Thomas Sony, Ghadi Nehme, Era Syla, Amin Heyrani Nobari, Faez Ahmed

multimodal benchmarks

arXiv AI

Jun 2

3DCodeBench: Benchmarking Agentic Procedural 3D Modeling Via Code

arXiv:2606. 01057v1 Announce Type: cross Abstract: Procedural 3D modeling through code is emerging as a versatile paradigm, offering deterministic, engine-ready, and precisely editable assets that neural 3D generators inherently lack.

By Yipeng Gao, Lei Shu, Genzhi Ye, Xi Xiong, Ameesh Makadia, Meiqi Guo, Laurent Itti, Jindong Chen

llms agents multimodal benchmarks

arXiv AI

Jul 2

Interact3D: Compositional 3D Generation of Interactive Objects

arXiv:2603. 16085v2 Announce Type: replace-cross Abstract: Recent breakthroughs in 3D generation have enabled the synthesis of high-fidelity individual assets.

By Hui Shan, Keyang Luo, Ming Li, Sizhe Zheng, Yanwei Fu, Zhen Chen, Xiangru Huang

llms agents multimodal safety

arXiv Computer Vision

4d ago

P3D-Bench: Benchmarking MLLMs for Parametric 3D Generation and Structural Reasoning

arXiv:2606.11152v4 Announce Type: replace Abstract: Multimodal large language models can write code to produce complex programs as well as use programs to do 3D modeling, which opens up a new avenue...

By Yikang Yang, Zhanpeng Hu, Youtian Lin, Mengqi Zhou, Jingxi Xu, Feihu Zhang, Jiaheng Liu, Yao Yao

llms multimodal benchmarks safety

arXiv AI

Oct 9

HI3D 3.0 (Twinkle3D): Object-specific 3D Asset Generation with High Resolution

Hi3D 3.0, also called Twinkle3D, is an image‑to‑3D generation system that produces watertight triangle meshes at a resolution of 2048³. It improves on previous methods by maintaining high representational precision while fixing surface quality and non‑watertight issues, scaling diffusion generation to 300K geometric tokens, strengthening global shape and local detail in a single stage, and adding a fine‑grained image‑3D cross‑modal interaction to better recover object‑specific structures such as inscriptions. The system outperforms four commercial competitors, recovering 82.1 % of inscribed characters with 98.2 % precision versus 21.7 % recall for the best rival.

By Ziying Li, Shengchu Zhao, Huiang He, Yiyang Chen, Jianwen Huang, Bailin Li, Changhao Li, Jianhui Li, Jie Li, Ruiyang Liu, Yibo Luo, Tengjiao Sun, Pei Tang, Shiwen Wang, Jiaqi Wu, Kang Wu, Kaiqiao Yang, Zherui Yang, Hu Zhang, Xuezhi Zhao, Xinhe Zheng, Yukun Li, Heliang Zheng, Rongfei Jia

diffusion multimodal safety

arXiv Computer Vision

Sep 16

Unlocking Zero-shot Potential of Semi-dense Image Matching via Gaussian Splatting

arXiv:2511.21265v2 Announce Type: replace Abstract: Learning-based image matching critically depends on large-scale, diverse, and geometrically accurate training data. 3D Gaussian Splatting (3DGS) en...

By Juncheng Chen, Chao Xu, Yanjun Cao

benchmarks safety

arXiv AI

Jul 10

LSRM: High-Fidelity Object-Centric Reconstruction via Scaled Context Windows

arXiv:2604. 05182v2 Announce Type: replace-cross Abstract: We introduce the Large Sparse Reconstruction Model to study how scaling transformer context windows affects feed-forward 3D reconstruction.

By Zhengqin Li, Cheng Zhang, Jakob Engel, Zhao Dong

llms benchmarks

arXiv Computer Vision

Oct 7

RenderBench: Benchmarking Render-to-Real Video Transfer with Reconstructed Digital Twins

arXiv:2610.08684v1 Announce Type: new Abstract: Modern video models can generate realistic videos from real appearance references and proxy renders that specify scene structure, viewpoint changes, an...

By Dicong Qiu, Zhiyuan Xu, Yaosheng Liu, Feng Han, Bo Ye

benchmarks

arXiv AI

Jul 2

Pano2World: End-to-End 3D Generation via Unified Multi-View Sequences

arXiv:2607. 00832v1 Announce Type: cross Abstract: A single panorama captures the full visual sphere from one camera center, yet confines users to looking around in place without enabling true scene exploration.

By Zhenjia Li, Jinrang Jia, Yifeng Shi

diffusion benchmarks

Related stories