arXiv Computer Vision

MeshSplatBench: A Unified Benchmark for Triangle-Based Neural Rendering

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

Jul 21

CaT-GS: Efficient 3DGS Rendering for Large Scale Scenes via Inter-frame Caching and Tile Scheduling

arXiv:2607. 17842v1 Announce Type: cross Abstract: Recent breakthroughs in 3D Gaussian Splatting (3DGS) have advanced neural rendering with high fidelity and speed.

By Tingjia Zhang, Bo Chen, Shengzhong Liu, Fan Wu, Guihai Chen

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 Computer Vision

Aug 26

ExMesh++: From Multi-View Images to Relightable UV-PBR Mesh Assets via Topology-Adaptive Reconstruction and Decomposition

arXiv:2608.24109v1 Announce Type: cross Abstract: Multi-view reconstruction extends beyond surface recovery to editable and relightable mesh assets. Such assets require well-formed topology, valid UV...

By Chuanjin Fan, Lifan Wu, Wenjie Chang, Hanzhi Chang, Wenfei Yang, Tianzhu Zhang

arXiv AI

Jul 15

1D-Bench: A Benchmark for Iterative UI Code Generation with Visual Feedback in Real-World

arXiv:2602. 18548v2 Announce Type: replace-cross Abstract: Design-to-code translates high-fidelity UI designs into executable front-end implementations, but progress remains hard to compare due to inconsistent datasets, toolchains, and evaluation protocols.

By Qiao Xu, Yipeng Yu, Chengxiao Feng, Xu Liu

reinforcement-learning multimodal benchmarks

arXiv Machine Learning

Aug 10

Symbolic Graphics Programming with Large Language Models

arXiv:2509. 05208v2 Announce Type: replace-cross Abstract: Large language models (LLMs) excel at program synthesis, yet their ability to produce symbolic graphics programs (SGPs) that render into precise visual content remains underexplored.

By Yamei Chen, Haoquan Zhang, Yangyi Huang, Zeju Qiu, Kaipeng Zhang, Yandong Wen, Weiyang Liu

llms reinforcement-learning multimodal benchmarks

arXiv Computer Vision

3d ago

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.

By Liwen Zhang

benchmarks safety

arXiv Computer Vision

Aug 24

TopoSurfel: Closing the Loop between Gaussian Surfels and Meshes for Surface Reconstruction

arXiv:2608.20687v1 Announce Type: new Abstract: 3D Gaussian Splatting has achieved remarkable success in novel view synthesis. However, extracting high-fidelity surfaces directly from 3DGS remains ch...

By Chuanjin Fan, Wenjie Chang, Bohao Liao, Yujia Chen, Wenfei Yang, Tianzhu Zhang

safety

arXiv Machine Learning

Jun 30

RenderFormer++: Scalable and Physically Grounded Feed-Forward Neural Rendering

arXiv:2606. 30380v1 Announce Type: cross Abstract: We present RenderFormer++, a scalable and physically grounded feed-forward neural rendering framework for global illumination in mesh scenes.

By Huangsheng Du, Haoran Zhu, Youcheng Cai, Jinyang Meng, Ligang Liu

llms nlp

arXiv Computer Vision

3d ago

Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning

arXiv:2604.06079v2 Announce Type: replace Abstract: Graphics Program Synthesis is pivotal for interpreting and editing visual data, effectively facilitating the reverse-engineering of static visuals...

By Juekai Lin, Yun Zhu, Honglin Lin, Sijing Li, Tianwei Lin, Zheng Liu, Xiaoyang Wang, Wenqiao Zhang, Lijun Wu

llms reinforcement-learning multimodal benchmarks safety data-engineering

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 AI

Jun 2

WorldCoder-Bench: Benchmarking Physically Grounded 3D World Synthesis

arXiv:2606. 01869v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly asked not only to write static interfaces, but to construct executable interactive worlds from natural language.

By Shuo Lu, Yinuo Xu, Kecheng Yu, Siru Jiang, Yongcan Yu, Yubin Wang, Haitao Yang, Yuxiang Zhang, Bin Wang, Ran He, Jian Liang

llms agents benchmarks

Related stories