SIREN
![](https://mscvprojects.ri.cmu.edu/f23team6/wp-content/uploads/sites/83/2023/05/img2_2-1024x434.png)
![](https://mscvprojects.ri.cmu.edu/f23team6/wp-content/uploads/sites/83/2023/05/img3_2-1024x437.png)
Although pure neural network (SIREN) demonstrated effective regularization, it tended to oversmooth the reconstruction results.
[+] Fine regularization
[-] Oversmoothing
SHINE-Mapping
![](https://mscvprojects.ri.cmu.edu/f23team6/wp-content/uploads/sites/83/2023/12/img2_3-1024x435.png)
![](https://mscvprojects.ri.cmu.edu/f23team6/wp-content/uploads/sites/83/2023/12/img3_3.png)
While Poisson reconstruction exhibited a generally satisfactory level of reconstruction quality, it was prone to floating artifacts and exhibited limited adaptability to sparse regions.
[+] Good global quality
[+] Adaptive to Input
[-] Strong local artifacts in certain scenes
Puma
![](https://mscvprojects.ri.cmu.edu/f23team6/wp-content/uploads/sites/83/2023/12/img2-1024x435.png)
![](https://mscvprojects.ri.cmu.edu/f23team6/wp-content/uploads/sites/83/2023/12/img3-1-1024x467.png)
The combination of neural network and octree (SHINE) yielded impressive overall quality that adapted well to the input. However, the resulting reconstruction still exhibited notable strong local artifacts.
[+] Overall good reconstruction result
[-] Floating artifacts
Future Works
- Exploit sequential information for better empty space
- Trim away the vertices in the reconstructed global mesh where the density is below a certain threshold
- Extend our method and test them on outdoor scenes