Georgia Gkioxari's banner

Georgia Gkioxari

@georgiagkioxari • 12,129 subscribers

Assistant professor in Computing + Mathematical Sciences @Caltech 🏛️ ∙ Computer vision enthusiast 🤖 ∙ SAM 3D, PyTorch3D ∙ Ex: FAIR, Google 👩🏻‍💻∙ From 🇬🇷

Shorts

3Dfy anything from a single image! Very thrilled to announce SAM 3D. From an input image, select any object you want, 3Dfy it! Blog: Demo:

3Dfy anything from a single image! Very thrilled to announce SAM 3D. From an input image, select any object you want, 3Dfy it! Blog: Demo:

166,050 просмотров

Videos

Anya Rossi

sweetdream.ai

SweetDream.ai•Sponsored•Livecam

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Exclusive private shows

1.2k viewers online

Private Show

Join now for exclusive access

Free preview available • Premium content

3D editing is hard: you need to ground an image + instruction and generate a faithful 3D shape in one forward pass -- no test-time optimization. So, we steer pretrained image-to-3D representations to do text-guided 3D edits; no massive 3D edit-pair dataset needed. Key trap: the “no-edit” solution is a nasty local minimum. We fix it with preference optimization, pushing the model to actually edit. Steer3D is the second work that adapts alignment ideas from LLMs to the 3D modality. SAM 3D also used DPO to improve its 3D generations.

3D editing is hard: you need to ground an image + instruction and generate a faithful 3D shape in one forward pass -- no test-time optimization. So, we steer pretrained image-to-3D representations to do text-guided 3D edits; no massive 3D edit-pair dataset needed. Key trap: the “no-edit” solution is a nasty local minimum. We fix it with preference optimization, pushing the model to actually edit. Steer3D is the second work that adapts alignment ideas from LLMs to the 3D modality. SAM 3D also used DPO to improve its 3D generations.

Georgia Gkioxari

115,844 просмотров • 5 месяцев назад

💫It's fascinating that a single feed-forward pass through an LLM can replace a complex rendering pipeline, like Blender! Just feed it 3D shapes, xyz positions, and poses as tokens, and it spits out the image token-by-token. The dual, aka scene reconstruction, is also possible! 👇

💫It's fascinating that a single feed-forward pass through an LLM can replace a complex rendering pipeline, like Blender! Just feed it 3D shapes, xyz positions, and poses as tokens, and it spits out the image token-by-token. The dual, aka scene reconstruction, is also possible! 👇

Georgia Gkioxari

44,553 просмотров • 1 год назад

Aleksander Holynski Sir! This is for you 🫡

Aleksander Holynski Sir! This is for you 🫡

Georgia Gkioxari

15,013 просмотров • 6 месяцев назад

Больше нет контента для загрузки