search

spla-tam / SplaTAM

SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)
https://spla-tam.github.io/
BSD 3-Clause "New" or "Revised" License
1.59k stars 174 forks source link

Question about 'forgetting' #67

Closed lif314 closed 8 months ago

lif314 commented 9 months ago

I noticed that during the training process, some frames are initially optimized very well, with PSNR values exceeding 30. However, when I perform evaluation after the entire map optimization process, the rendering results for the initial frames are not satisfactory. Is there any good way to alleviate this issue? (replica office2 result)

metrics

ljjTYJR commented 8 months ago

I think it is a trade-off between the efficiency and the accuray. One option might be enlarging the reply buffer; The other option would be adding some regularization terms to regularize the optimization of Gaussian parameters.

Nik-V9 commented 8 months ago

I believe that enlarging the mapping window and some updates to our keyframing similar to this paper (https://arxiv.org/abs/2402.03246) should help.

AutoSenseTech commented 4 months ago

I believe that enlarging the mapping window and some updates to our keyframing similar to this paper (https://arxiv.org/abs/2402.03246) should help.

What do you mean by "enlarging the mapping window"? Do you mean changing the parameter mapping_window_size in configs/splatam.py?