Gallery

[ARuiChen]

No description provided.

[ARuiChen]

"Michelangelo style statue of dog reading news on a cellphone"
performance: 15 minutes for geometry modeling and 13 minutes for appearance modeling on 8 3090 GPUs
resolution: 256

dog_appearance_stratege0.mp4

dog_geometry.mp4

[ARuiChen]

"A highly detailed sandcastle"
performance: 15 minutes for geometry modeling and 13 minutes for appearance modeling on 8 3090 GPUs
resolution: 256

sandcastle_geometry.mp4

sandcastle_appearacne_strategy0.mp4

sandcastle_appearance_strategy1.mp4

sandcastle_appearance_strategy2.mp4

[ARuiChen]

"a baby bunny sitting on top of a stack of pancakes".
performance: 15 minutes for geometry modeling and 13 minutes for appearance modeling on 8 3090 GPUs
resolution: 256

See Google Drive to visualize the training process.

baby_bunny_geometry.mp4

bunny_appearance_strategy0.mp4

[akturtle]

Hi, could you also provide model results for downloading (obj file, or other format)?

[ARuiChen]

Hi, @akturtle ! No problem. But there may only be geometric parts, as UV padding for appearance requires some additional time using blender.

[colorful-liyu]

Hi, @akturtle ! No problem. But there may only be geometric parts, as UV padding for appearance requires some additional time using blender.

Thanks for your great work. I cannot reproduce the same results for I have only 4 GPUs and I met the Jesus multi-head problems. Could you release the generated ckpts for the gallery such as the trained weight of mlptexture?

[ARuiChen]

@colorful-liyu Which config file did you use and what text did you use? I have been preparing for my final exam recently, so some requirements will only be realized after I finish the exam.

[colorful-liyu]

@colorful-liyu Which config file did you use and what text did you use? I have been preparing for my final exam recently, so some requirements will only be realized after I finish the exam.

Specifically, the geometry generation results of bama_head and oldman always have multi-face or three ears, while the generated elephant has separate ivory. And the dog reading newspapers may have more than four legs. The appearance generation looks nice. So any release about .obj files especially ckpts will be helpful.

[zhangai6666]

Hi @ARuiChen,

Great work! Could you please help answer a quick question? What's the average speedup you see in 8GPU vs 1GPU? Thank you so much!

[ARuiChen]

"A high heel made of gold".
performance: 7 minutes for geometry modeling and 5 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256
zero_shot generation

heel_appearance.mp4

[ARuiChen]

"A DSLR photo of hamburger".
performance: 7 minutes for geometry modeling and 12 minutes for appearance modeling on 1 A100 GPU
DMTet resolution: 256
zero_shot generation

hamburger_appearance.mp4

[ARuiChen]

@colorful-liyu When you meet multiple faces, removing the annotation here and rotating the initialized shape with some angles can greatly alleviate janus-problem. But it is important to note that adding negative text in some cases may cause poor deformation ability.

[ARuiChen]

"a full body photo of a girl wearing a mecha"
performance: 11 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256
user-guided generation
See Google Drive to visualize the training process.

girl_geometry.mp4

girl_appearance.mp4

cyber_girl_appeappearance.mp4

[ARuiChen]

"a head of Stormtrooper"
"Einstein's head with high detail hair"

performance: (very stable) 5 minutes for geometry modeling on 8 A100 GPUs (4 GPUs should also work)

stormtrooper_geometry.mp4

einstein_geometry.mp4

[ARuiChen]

"a head of I am Groot"
"a portrait of Napoleon Bonaparte"
"a head of Naruto Uzumaki"
"a portrait of Doctor Strange"
"a portrait of Batman"
"a head of Terracotta Army"
"a portrait of Salvador Dali"

performance: (very stable) 5 minutes for geometry modeling on 8 A100 GPUs (4 GPUs should also work)

Groot_geometry.mp4

Napoleon_geometry.mp4

Naruto_geometry.mp4

Doctor_Strange.mp4

Batman.mp4

Army_geometry.mp4

Dali_geometry.mp4

[ARuiChen]

Use the dog_geometry_user_guided.json file.
"Michelangelo style statue of dog reading news on a cellphone"
A strange phenomenon for your reference: when I set "add_directional_text= false", the user-guided generation can grow a phone from the dog's hand; On the contrary, when I set "add_directional_text= true", the phone actually won't grow out.

dog_geometry_false.mp4

dog_geometry_true.mp4

[ARuiChen]

"a lionfish"
performance: 11 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 128

fish_geometry_1.mp4

fish_appearance_strategy0.mp4

fish_appearance_strategy1.mp4

fish_appearance_strategy2.mp4

[ARuiChen]

"A squirrel-octopus hybrid"
performance: (very stable) 8 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

squirrel_geometry.mp4

squirrel_appearance_strategy2.mp4

[ARuiChen]

"An astronaut is riding a horse".
performance: 12 minutes for geometry modeling and 10 minutes for appearance modeling on 8 A100 GPUs
resolution: 256

See Google Drive to visualize the training process.

astronaut_geometry.mp4

astronaut_geometry1.mp4

astronaut_appearance.mp4

[ARuiChen]

"A silver candelabra sitting on a red velvet tablecloth, only one candle is lit".
performance: 10 minutes for geometry modeling and 9 minutes for appearance modeling on 8 A100 GPUs
resolution: 256

See Google Drive to visualize the training process.

candle_geometry.mp4

candle_appearance_train.mp4

candle_appearance_relight.mp4

[ARuiChen]

"A ripe strawberry".
performance: 7 minutes for geometry modeling and 10 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

See Google Drive to visualize the training process.

strawberry_geometry.mp4

strawberry_appearance_strategy2_2.mp4

strawberry_appearance_strategy_2_1.mp4

[VLadImirluren]

@ARuiChen Hello ! Thanks for so many great demos. But these configs are not seen in config golder,when they will be released? Thanks!

[VLadImirluren]

@ARuiChen I have seen a lot of greate demos in paper, such as A 3D model of an adorable cottage with a thatched roof. Can you release the configs of the demos shown in paper? thanks!

[ARuiChen]

@VLadImirluren The results in the paper were generated using unorganized code, so the configuration I previously used may not be applicable. It's easy to replicate all the results using organized code, but I don't have time to complete it, and now I only have some fragmented time to run new results.
BTW， the configs about strawberry and candle have been committed.

[ARuiChen]

"a detailed human heart".
performance: 7 minutes for geometry modeling and 10 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

heart_geometry.mp4

heart_appearance_stratrgy2_1.mp4

[ARuiChen]

"A typewriter"
"a model of a house in Tudor style"
"Rabbit head"

typewriter_geometry.mp4

house_geometry.mp4

house_appearance.mp4

rabbit_geometry.mp4

[ARuiChen]

"A wooden deer standing on two separate wooden skateboards".
performance: 7 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

deer_geoemtry.mp4

deer_appearance.mp4

deer_geometry_process.mp4

[ARuiChen]

"A frog".
performance: 7 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

frog_geometry.mp4

frog_appearance_strategy2.mp4

[ARuiChen]

"A highly detailed standing pegasus with two wings".
performance: 7 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

pegasus_geometry.mp4

pegasus_appearance.mp4

pegasus_process.mp4

[VLadImirluren]

@ARuiChen Hello, is it possible to share the config while uploading the video? Your technique is very superb, I often cannot reproduce many cases, there is a lot of noise and distortion, I would like to learn from you how to call out more realistic effects (such as smoother and more realistic in geometry, less noise in color).
best wishthanks

[ARuiChen]

@VLadImirluren . Of course, except for some that I don't want to release yet, I will release most of the corresponding configurations in the future. But I am currently busy with something and I will finish it tomorrow evening.

[VLadImirluren]

@VLadImirluren . Of course, except for some that I don't want to release yet, I will release most of the corresponding configurations in the future. But I am currently busy with something and I will finish it tomorrow evening.

sometimes, I can't reach the same as yours.I am confused that is the problem of different GPU? Can you share the GPU you use with us?(I see most of them are A100 * 8, how can I reach the same as yours on V100 , 3090 or 4090?)

[ARuiChen]

The GPU type only affects the generation speed and does not have a significant impact on the results. The most significant impact may be on the number of GPUs, as my algorithm was debugged under 8 GPUs， which is related to the sampling perspective in the dataset.py.
In addition, the random numbers generated in different machines may vary using the same seed, which may also be one of the influencing factors.
You can publish a separate issue about your generated results and corresponding configurations, and I will take some time to make suggestions on this.
Lastly, please ensure that your code is up to date.

[VLadImirluren]

The GPU type only affects the generation speed and does not have a significant impact on the results. The most significant impact may be on the number of GPUs, as my algorithm was debugged under 8 GPUs， which is related to the sampling perspective in the dataset.py. In addition, the random numbers generated in different machines may vary using the same seed, which may also be one of the influencing factors. You can publish a separate issue about your generated results and corresponding configurations, and I will take some time to make suggestions on this. Lastly, please ensure that your code is up to date.

thanks

[VLadImirluren]

@ARuiChen I went back and tested for a long time, but I still couldn't reproduce the appearance of the cottage. By adjusting the strategy, I made the geometry smoother, but there is still a lot of noise in the appearance. Could you please share the appearance settings of the cottage? Thanks

[ARuiChen]

Sure, wait a few minutes for me.

[VLadImirluren]

Sure, wait a few minutes for me.

Could you please show the geometry and appearance of "a model of a house in Tudor style" if it is convenient? . . thanks. . . . .

[ARuiChen]

Done. house_geometry.json and house_appearance.json. Please pull the latest code. Push another issue if you have any other questions. This is where the Gallery is located ^_^.

[VLadImirluren]

Done. house_geometry.json and house_appearance.json. Please pull the latest code. Push another issue if you have any other questions. This is where the Gallery is located ^_^.

thanks. I will

[ARuiChen]

“A man riding a bike”
Performance: 9 minutes for geometry modeling on 8 A100 GPUs
DMTet resolution: 256

bike_geometry.mp4

[ARuiChen]

squirrel_geometry1.json and squirrel_appearance1_strategy2.json
Adding negative prompts can improve the visual quality in appearance modeling!
text: “A squirrel”
negative text: "shadow, oversaturated color, strange color"
Performance: 7 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

If the negative prompt is not added, in some cases, you can see many shadows and strange colors:

w/ the negative prompt ( just used in appearance modeling):

squirrel_geometry1.mp4

squrrel_appearance_strategy2.mp4

[ARuiChen]

text: “michelangelo style statue of an astronaut carrying space jet backpacks and wearing spacesuits”
negative text: "shadow, oversaturated color, strange color"
Performance: 8 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

michelangelo_astronaut_geometry.mp4

michelangelo_astronaut_appearance_strategy1.mp4

michelangelo_astronaut_appearance_strategy2.mp4

[ARuiChen]

text: “A standing bulldog wearing a black pirate hat”
Performance: 8 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

bulldog_geometry.mp4

bulldog_appearance_strategy0.mp4

bulldog_appearance_strategy2.mp4

[ARuiChen]

text: “military Mech, long barrel”
Performance: 8 minutes for geometry modeling and 8 minutes for appearance modeling on 8 A100 GPUs
DMTet resolution: 256

military_geometry.mp4

military_appearance_strategy2.mp4

[yd-yin]

Hi, @akturtle ! No problem. But there may only be geometric parts, as UV padding for appearance requires some additional time using blender.

Hi! So how to download the geometry of the results, please?

[ARuiChen]

@yd-yin here