EscherNet

EscherNet copied to clipboard

3D Reconstruction for text-to-3D

5

when come?

kszpxxzmc

Question about intrinsics for 3D reconstruction

8

Hi! really nice work I'm using Eschernet 6Dof and in my dataset I would need to use different intrinsics for different images, I guess it's not an issue for NeuS...

AlbertoRemus

Gradio Demo

1

Hi, great work! Do you plan to release the code to do inference on real word objects?

SSamDav

Training details

3

Hello! Congratulations for the great work. I have one question about the training process. In Section 3.1 you say "It builds upon an existing 2D diffusion model, inheriting its strong...

fradif96

Performance Degradation with T_out set to 2

3

I reduce the oputput views to 2 in the demo case and observe a significant performance drop. I wonder why performance excels with 25 views but suffers with 2. Could...

Lizb6626

Generate target images from a single top-view reference image

1

Hi, thanks for your amazing work. I am conducting a research about using one single top-view image to generate the entire object. I've tried many model, including zero-123 XL and...

jayin92

Memory requirements

2

Hi, I'd like to know how much memory is required for EscherNet? An A100 or just RTX3090 with 24GB will be enough?

yejr0229

Result on Franka dataset

1

Dear authors, first of all, thank you for the amazing work. I am trying to use the model on the Frianka16, but it's not clear to me how to do...

Giuse1

Some questions about image encoder and reference images

1

Thanks for your nice work. I'm still confused by the choice of ConvNeXt2 as the image encoder in this project. It is mentioned that the reason for employing ConvNeXt2 is...

zhanghaoyu816

the genenrated target views become blurry during training

5

Hi @fradif96 We don't have new modules for cross/self-attention. It's the same attention layers but just reshape the latent features from ((b t) l d) -> (b (t l) d)...

fangchuan