yosun

San Francisco

Results 151 comments of


                                            yosun

code release?

great please put it on replicate or huggingface so we can easily play with it

Any way to get facial landmark detection?

i still recommend using dlib68 for facial landmarks

What is I wish to generate the mesh with multiple images ? - I have front view, left view, right view and back view of a chair - how can I create a mesh utilising all these images ?

Cam this model be modified to support Multiple ground truth consistent input from the user?

What is I wish to generate the mesh with multiple images ? - I have front view, left view, right view and back view of a chair - how can I create a mesh utilising all these images ?

do you know which coordinate system they are using? as a test: i tried inputting screenshots from 6 images from a 3D model in the 360%6 azimuth and also 20...

What is I wish to generate the mesh with multiple images ? - I have front view, left view, right view and back view of a chair - how can I create a mesh utilising all these images ?

Curious - can you share your generated results from that?

What is I wish to generate the mesh with multiple images ? - I have front view, left view, right view and back view of a chair - how can I create a mesh utilising all these images ?

![screenshot_0](https://github.com/TencentARC/InstantMesh/assets/909246/54fbf5e3-d700-4c3e-81b1-e97fbe52a0dd) ![screenshot_1](https://github.com/TencentARC/InstantMesh/assets/909246/89263035-386f-4fb4-bf26-d896f81531b4) ![screenshot_2](https://github.com/TencentARC/InstantMesh/assets/909246/e46a37c0-9b42-4f9f-855b-fcb2ed13f8fe) ![screenshot_3](https://github.com/TencentARC/InstantMesh/assets/909246/dadf8629-7420-40eb-aca2-28e6240a2dc4) ![screenshot_4](https://github.com/TencentARC/InstantMesh/assets/909246/ad82f404-bcda-438f-8c15-58fbebc1866c) ![screenshot_5](https://github.com/TencentARC/InstantMesh/assets/909246/05a502e9-f69f-4cd6-b197-215a47794eac)

What is I wish to generate the mesh with multiple images ? - I have front view, left view, right view and back view of a chair - how can I create a mesh utilising all these images ?

yes but the generated result do not look good! i tried your input and got this! [![Image from Gyazo](https://i.gyazo.com/9b84ff423be437356117c11c57644e41.gif)](https://gyazo.com/9b84ff423be437356117c11c57644e41)

What is I wish to generate the mesh with multiple images ? - I have front view, left view, right view and back view of a chair - how can I create a mesh utilising all these images ?

okay tried it in the order above - slightly better but still not great [![Image from Gyazo](https://i.gyazo.com/eac544d22fea3f0056ec281d421767f1.gif)](https://gyazo.com/eac544d22fea3f0056ec281d421767f1)

What is I wish to generate the mesh with multiple images ? - I have front view, left view, right view and back view of a chair - how can I create a mesh utilising all these images ?

> ![screenshot_0](https://private-user-images.githubusercontent.com/909246/335486371-54fbf5e3-d700-4c3e-81b1-e97fbe52a0dd.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTcxNDE1MTAsIm5iZiI6MTcxNzE0MTIxMCwicGF0aCI6Ii85MDkyNDYvMzM1NDg2MzcxLTU0ZmJmNWUzLWQ3MDAtNGMzZS04MWIxLWU5N2ZiZTUyYTBkZC5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNTMxJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDUzMVQwNzQwMTBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1mNDM5NmZhMGNiZTUwNGFkOGUyZDM2OTFmNDQ2MzViYTA5N2ZhMWZkZjQ4YTFlMWYyNWE2ZDZmY2ZjNTAyNjllJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.G99SyDR6M4voEVjJiLcV2bzGtnD7OMADtrc8XrUokag) ![screenshot_1](https://private-user-images.githubusercontent.com/909246/335486376-89263035-386f-4fb4-bf26-d896f81531b4.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTcxNDE1MTAsIm5iZiI6MTcxNzE0MTIxMCwicGF0aCI6Ii85MDkyNDYvMzM1NDg2Mzc2LTg5MjYzMDM1LTM4NmYtNGZiNC1iZjI2LWQ4OTZmODE1MzFiNC5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNTMxJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDUzMVQwNzQwMTBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT0wNGM1YWQ5ZWVjM2RmNjhmZjk3MjM0YjI1MWMyMzkzYzg3ZTI4YjE4MDU3NGFjMzQyNGNiZWUyNjdkMzY2MjQ0JlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.86mKBeofwJ7mhGJj_YBJf6XVz1ViFTolYZCcI-YBpQk) ![screenshot_2](https://private-user-images.githubusercontent.com/909246/335486379-e46a37c0-9b42-4f9f-855b-fcb2ed13f8fe.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTcxNDE1MTAsIm5iZiI6MTcxNzE0MTIxMCwicGF0aCI6Ii85MDkyNDYvMzM1NDg2Mzc5LWU0NmEzN2MwLTliNDItNGY5Zi04NTViLWZjYjJlZDEzZjhmZS5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNTMxJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDUzMVQwNzQwMTBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1iOWFlYjEzZmU4YzEwMGUyMmM0ZTVlYzAwMjlhNDZkMjJkZTE1Y2MzMzMzMmUzYmE1MTE2MThiNmM4NmU2NDQ5JlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.-mnXI0eCTPQvqItNDlNRP4zY2XsDyR9yE-0RAyAs2wI) ![screenshot_3](https://private-user-images.githubusercontent.com/909246/335486382-dadf8629-7420-40eb-aca2-28e6240a2dc4.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTcxNDE1MTAsIm5iZiI6MTcxNzE0MTIxMCwicGF0aCI6Ii85MDkyNDYvMzM1NDg2MzgyLWRhZGY4NjI5LTc0MjAtNDBlYi1hY2EyLTI4ZTYyNDBhMmRjNC5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNTMxJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDUzMVQwNzQwMTBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT01MTk2MDdlZmEwMmY0ODJjN2RlZTIyYmIxYjMwMDRiZGIwMWNhODkyMGU5ZDQ2ODVmZGNiZDJmYTg0NzU5YzM5JlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.zjEuN7vsE58svqab7LwWj-23DAmrf8Am7MQA6qHBUbQ) ![screenshot_4](https://private-user-images.githubusercontent.com/909246/335486386-ad82f404-bcda-438f-8c15-58fbebc1866c.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTcxNDE1MTAsIm5iZiI6MTcxNzE0MTIxMCwicGF0aCI6Ii85MDkyNDYvMzM1NDg2Mzg2LWFkODJmNDA0LWJjZGEtNDM4Zi04YzE1LTU4ZmJlYmMxODY2Yy5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNTMxJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDUzMVQwNzQwMTBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT05OTY5ODQ2ZmYyZWZmZTVjZTAwNTg5NDMwNWU4MTgxMWJlMDFlMWQ2MmRjNDVlZmZmNDIzYmZmNjhhNzBlOTdhJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.H4bZSZmMDRy0ZZNUWTSK7s2OEBr_g75a_i4BMJCNuns) ![screenshot_5](https://private-user-images.githubusercontent.com/909246/335486387-05a502e9-f69f-4cd6-b197-215a47794eac.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTcxNDE1MTAsIm5iZiI6MTcxNzE0MTIxMCwicGF0aCI6Ii85MDkyNDYvMzM1NDg2Mzg3LTA1YTUwMmU5LWY2OWYtNGNkNi1iMTk3LTIxNWE0Nzc5NGVhYy5wbmc_WC1BbXotQWxnb3JpdGhtPUFXUzQtSE1BQy1TSEEyNTYmWC1BbXotQ3JlZGVudGlhbD1BS0lBVkNPRFlMU0E1M1BRSzRaQSUyRjIwMjQwNTMxJTJGdXMtZWFzdC0xJTJGczMlMkZhd3M0X3JlcXVlc3QmWC1BbXotRGF0ZT0yMDI0MDUzMVQwNzQwMTBaJlgtQW16LUV4cGlyZXM9MzAwJlgtQW16LVNpZ25hdHVyZT1iMTcxYTMxZmVmYTYxNjUyYzIyZDRmZjc1MjY1OTY4YTE0MzdkNTIwYjc1ZWJkNTIxMDU2ZDI4MjE3YzFjOTIxJlgtQW16LVNpZ25lZEhlYWRlcnM9aG9zdCZhY3Rvcl9pZD0wJmtleV9pZD0wJnJlcG9faWQ9MCJ9.qVFXhLrETNHzH3ty7MqnHR5pjdqX21-e0oYQQ7wRDQ0) [![Image from Gyazo](https://i.gyazo.com/8614599d51a86a1dd0f901234cd8e83a.gif)](https://gyazo.com/8614599d51a86a1dd0f901234cd8e83a)

What is I wish to generate the mesh with multiple images ? - I have front view, left view, right view and back view of a chair - how can I create a mesh utilising all these images ?

![screenshot_0](https://github.com/TencentARC/InstantMesh/assets/909246/f150a8b3-fc51-4bca-8abb-93bfc310ec20) ![screenshot_1](https://github.com/TencentARC/InstantMesh/assets/909246/f3d721a7-9fb5-4da1-8262-420099e77086) ![screenshot_2](https://github.com/TencentARC/InstantMesh/assets/909246/69fba235-7dbe-4eba-b622-56e54cd7a373) ![screenshot_3](https://github.com/TencentARC/InstantMesh/assets/909246/69d86198-1fe5-42b3-8b45-9a06d7036e9a) ![screenshot_4](https://github.com/TencentARC/InstantMesh/assets/909246/1d272cf9-c2c3-4748-b56b-aefd33aa20ff) ![screenshot_5](https://github.com/TencentARC/InstantMesh/assets/909246/57950ba8-5797-4759-8720-d3e6bcfce7a0) hmm still kind of a mess [![Image from Gyazo](https://i.gyazo.com/6ae4599f9aaa5cf77e2fadb522f2f359.gif)](https://gyazo.com/6ae4599f9aaa5cf77e2fadb522f2f359)