arXiv Computer Vision
Nov 9

Frontier3DBench: Benchmarking Coding Agents for 3D Creation across Objects, Scenes, and Interactive Open Worlds

Frontier3DBench is a unified benchmark for coding agents that generate, reconstruct, and edit 3D content, comprising 145 tasks across nine categories covering objects, scenes, and interactive open worlds. The benchmark evaluates appearance, structure, and behavior, revealing that GPT‑6.1‑sol excels at object and scene construction while GPT‑6‑astra leads interactive world building. Results show that agents perform better at text‑driven generation than at precise reference reconstruction, and that coordinated activity completion remains a significant challenge.

By Xinjie Lin, Qingle Liu, Wenyi Li, John Lam, Xiaoqiu Wang, Deyao Hong, Mingju Gao, Zheng Jiang, Yizhe Chi, Youjie Zheng, Calvin Xiao, Kaisen Yang, Huan-ang Gao
arXiv Computer Vision
Oct 28

Learning to Code the World: Harness Evolution for Compositional 3D Reconstruction

The paper introduces SceneEvolve, a framework that represents 3D scenes as executable code and improves reconstruction by evolving a harness around a small open‑source agent. SceneEvolve combines a compositional semantic action interface (SceneAct) with a harness evolution process (SceneHarness‑RSI) that uses a stronger teacher agent for iterative refinement. The resulting harness allows the small Qwen3.8‑27B model to reconstruct unseen scenes without parameter updates, achieving higher reconstruction quality and lower inference time than larger proprietary models across multiple datasets.

By Haoyu Yao, Chenguo Lin, Ruize Du, Yadong Mu
arXiv Computer Vision
Sep 23

HARMONY: Hierarchical Agentic Reasoning for MONocular Image-to-Scene Synthesis

HARMONY is a hierarchical chain-of-thought framework that reconstructs complete 3D indoor scenes from a single monocular image. It combines agentic reasoning with visual geometry foundation models, starting with camera calibration and semantic layout recovery, then placing objects hierarchically while refining geometry with point cloud estimations. The method achieves semantically consistent scenes that align perceptually with the input image, outperforming existing baselines on synthetic and real-world data.

By Shufan Sun, Chen Wang, Enxin Song, Jiatao Gu, Lingjie Liu
arXiv Computer Vision
Sep 7

WorldSculpt: Generating Compositional Worlds from Grounded Videos

WorldSculpt presents a method for generating compositional 3D representations of cluttered scenes with hundreds of objects by adapting a single-object 3D generative prior to multi-view observations. The approach, built on Pixal3D with a multi-view conditioning pathway, can generalize to highly occluded scenes without scene-level training. The authors also introduce the UE-MeshyScene benchmark and demonstrate that their method outperforms prior approaches across various evaluation settings, including converting existing 3DGS worlds into compositional mesh scenes.

By Muyao Niu, Jixuan He, Ruihan Yu, Lian Fu, Yonghao Yu, Zheng-Hui Huang, Yifan Zhan, Fengbo Lan, Yongtao Ge, Yinqiang Zheng, Kaipeng Zhang, Zhixiang Wang