CGuangyan-BIT / PointGPT

[NeurIPS 2023] PointGPT: Auto-regressively Generative Pre-training from Point Clouds
MIT License
179 stars 18 forks source link

No scaling factor for RDP. #15

Closed nikolai-franke closed 8 months ago

nikolai-franke commented 8 months ago

In the paper you describe the relative direction prompt in equation 5 as $RDPi = \textrm{PE}((\mathbf{C}{i+1}^s - \mathbf{C}i^s) / \parallel \mathbf{C} {i+1}^s - \mathbf{C} _i^s \parallel_2), \quad i \in \{ 1, \dots, n' \}$.

However, in the code I cannot find such scaling factor and it looks like you actually just do $RDPi = \textrm{PE}(\mathbf{C} {i+1}^s - \mathbf{C} _i^s)$.

The relevant lines of code are https://github.com/CGuangyan-BIT/PointGPT/blob/a8bdf85ad469615b3e462a187474d36929a6bbfb/models/PointGPT.py#L380C1-L386C57 and https://github.com/CGuangyan-BIT/PointGPT/blob/a8bdf85ad469615b3e462a187474d36929a6bbfb/models/PointGPT.py#L642C1-L647C1

Does this mean you actually use a relative position prompt instead of a relative direction prompt? Is there a mistake in the paper, is there a mistake in the code, or am I missing something?

CGuangyan-BIT commented 8 months ago

Hi! Thanks for pointing out this error, it was caused by a version error when we were organizing the code, which has now been updated!