Zheng Chen
Zheng Chen
I tried to run prolificdreamer in the default scene setting like this on one A100 card (with 40G VRAM): `python launch.py --config configs/prolificdreamer-scene.yaml --train --gpu 0 system.prompt_processor.prompt="Inside of a smart...
The code in `https://github.com/3DTopia/LGM/blob/main/core/provider_objaverse.py#L166`: ``` cam_pos = - cam_poses[:, :3, 3] # [V, 3] ``` I cannot understand why you added a negative sign here.
https://github.com/nihalsid/panoptic-lifting/blob/b8ad4f5941ed0158f365d2c19facc86fbae2061e/dataset/preprocessing/preprocess_hypersim.py#L420 I found the maximum depths of some scenes in Hypersim after multiplying 1000 are far larger than the maximum value of int16(32767). It is not adequate to use int16...
I run the following code: `python main.py data/bonsai/ --workspace trial_merf_360_bonsai --enable_cam_center --eval_cnt 1 --save_cnt 1 --downscale 4 #--fast_baking` And I finally get a weird result like this:  Do you...
Hi! This work is really impressive! I wonder when you will release the code of ConsistNet?
Hi! I do not understand why here you add a negative sign. https://github.com/liuyuan-pal/NeuRay/blob/939af16b5e27bcda4f011d1e43cb833c1508622a/network/render_ops.py#L37
Hi! I have 640x360 images. I wonder if I can use the model directly on these lower resolution images without resizing to 616x1064.
I have a long sequence with intrinsics which are different from those given. How can I revise the configuration file?