Closed jinmaodaomaye2021 closed 2 years ago
Hi! I think there are several reasons causing this problem.
Thanks @ghy0324 for your reply.
1) The PSNR for VolSDF is slightly lower than NeRF, but the rendered images are visually close to GT without blur. 2) It is a little bit weird to me since these rendered images are at training poses instead of novel poses. The network should at least fit to the training data. There might be some losses which block other losses to converge (I am not sure) ? 3) Scannet images are blurry for some views. Does it become better to render training images with other non-blurry dataset ?
Thanks @ghy0324 for your reply.
- The PSNR for VolSDF is slightly lower than NeRF, but the rendered images are visually close to GT without blur.
- It is a little bit weird to me since these rendered images are at training poses instead of novel poses. The network should at least fit to the training data. There might be some losses which block other losses to converge (I am not sure) ?
- Scannet images are blurry for some views. Does it become better to render training images with other non-blurry dataset ?
Hi @ghy0324 ,
Thanks for your answer. Would you mind sharing the piece of code to generate 3D reconstruction using texture mapping as shown in your project ?
I am using the Open3D for texture mapping, but unfortunately it was not successful in Scannet.
email: jinyang717@gmail.com
Thanks.
Hi @ghy0324 ,
Thanks for your answer. Would you mind sharing the piece of code to generate 3D reconstruction using texture mapping as shown in your project ?
I am using the Open3D for texture mapping, but unfortunately it was not successful in Scannet.
email: jinyang717@gmail.com
Thanks.
Hi! We recommend you to use mvs-texturing.
嗨,
感谢您分享您的预训练模型。
我测试了一个模型 (0050_00.pth) 以在训练相机姿势下渲染图像。
请查看下面的同一张图片。左图是 GT 图像,右图是渲染图像。
使用预训练模型渲染的图像仍然非常模糊。我只是由于机器上的内存问题而更改的。用图像损失(或方程 5)换取更好的几何形状是否符合设计?
N_rays = 512``L_img
知道为什么会发生这个问题吗?
谢谢。
How do you generate rendered images? I couldn't find the code for rendering images.
Hi @ghy0324,
Thanks for sharing your pre-trained model.
I tested one model (0050_00.pth) to render images at training camera poses.
Please check the same image below. The left figure is the GT image and the right figure is the rendered image.
The rendered image is still very blurry using your pre-trained model. I only changed
N_rays = 512
due to memory issues on my machine. Is it by-design to trade image loss (orL_img
in Eq 5) for a better geometry ?Any idea why this issue happens ?
Thanks.