xxlong0 / Wonder3D

Single Image to 3D using Cross-Domain Diffusion for 3D Generation
https://www.xxlong.site/Wonder3D/
GNU Affero General Public License v3.0
4.7k stars 373 forks source link

Why camera poses incline #140

Closed Jinzhe-Zhang closed 7 months ago

Jinzhe-Zhang commented 7 months ago

Hi, Thanks for the wonderful job!

I noticed that the camera poses in mvdiffusion/data/fixed_poses/nine_views (not exactly 0°,45°,90°,180°,270°,315°) is different from camera poses in instant-nsr-pl/datasets/fixed_poses (exactly 0°,45°,90°,180°,270°,315°). And the pictures inferenced from test_mvdiffusion_seq.py are a little inclined.

I also noticed the "self.camera_embedding" in mvdiffusion/pipelines/pipeline_mvdiffusion_image.py line 136 corresbonds to the views in mvdiffusion. It's also inclined.(for example, self.camera_embedding[2,2] should be half of pi(1.57) instead of 1.6934)

So how do the views in mvdiffusion folder come about?

Jinzhe-Zhang commented 7 months ago

为啥位姿是斜的呀,推理出来的图片也是有点斜的

flamehaze1115 commented 7 months ago

我刚更新了readme 加了个图示 你可以看下

Jinzhe-Zhang commented 7 months ago

I've changed the pose to multiples of 45°, and I get the correct results when training stage1 in the overfitting of a single object (6 views normals and rgbs).