How Far Can an Agentic Research Loop Push a Standard Computer Graphics Baseline?

Sun, 26 Jul 2026 00:00:00 +0000

Computer graphics papers often carry the same baseline numbers from one comparison table to the next. This is reasonable because reproducing every established method would consume time better spent evaluating the proposed contribution. It also leaves an interesting question unanswered. How much headroom remains in a mature baseline if it receives sustained attention from an agentic research loop?

This study explores that question through point-cloud surface normal estimation, continuing earlier work on smoothing splines and adaptive neighborhood selection. The PCPNet benchmark is a useful case because PCA has remained a standard reference across years of normal-estimation papers. Its published average angular RMSE is 16.25°. The learned PCPNet method reports 14.58°, while the recent state of the art, PFF-Net, reports 9.38°.

PCPNet on Ante Kapetanovic

How Far Can an Agentic Research Loop Push a Standard Computer Graphics Baseline?