VISER is a new visually realistic simulation benchmark for robot manipulation tasks that uses PBR materials and MLLM-assisted asset generation, achieving 0.92 Pearson correlation with real-world policy performance.
UnCommon Objects in 3D
3 Pith papers cite this work. Polarity classification is still indexing.
citation-role summary
citation-polarity summary
years
2026 3verdicts
UNVERDICTED 3representative citing papers
TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.
citing papers explorer
-
Toward Visually Realistic Simulation: A Benchmark for Evaluating Robot Manipulation in Simulation
VISER is a new visually realistic simulation benchmark for robot manipulation tasks that uses PBR materials and MLLM-assisted asset generation, achieving 0.92 Pearson correlation with real-world policy performance.
-
TrianguLang: Geometry-Aware Semantic Consensus for Pose-Free 3D Localization
TrianguLang achieves state-of-the-art feed-forward text-guided 3D localization and segmentation by using predicted geometry to gate cross-view semantic correspondences without ground-truth poses.
-
From Visual Synthesis to Interactive Worlds: Toward Production-Ready 3D Asset Generation
The paper surveys 3D asset generation methods and organizes them around the full production pipeline to assess which outputs meet engine-level requirements for interactive applications.