Frozen Scenes, Shifting Winners: Configuration Fragility in Text-to-3D Evaluation

The paper investigates how changes in evaluation settings—such as camera angles and caption wording—affect the rankings of text-to-3D generators. Using 300 fixed scenes and varying eight render and caption factors, the authors find that configuration variance often exceeds generator variance, leading to frequent shifts in the top-scoring model across 19 alignment evaluators. They conclude that observed winner changes are descriptive rather than definitive, and recommend detailed reporting of generator, score, and protocol specifics to account for uncertainty.

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 AI.

• benchmarks
• safety