“VolumeMatic and the AI3D.foundation Benchmark Card for 3D Generative AI: Text to spatial computing volume app with generated content”
Conference:
Type(s):
Title:
- VolumeMatic and the AI3D.foundation Benchmark Card for 3D Generative AI: Text to spatial computing volume app with generated content
Developer(s):
Description:
What if you can chat to automagically create your own 3D interactive software for mixed reality? We present a visionOS app that lets anyone make their own 3D volume apps for Vision Pro! We introduce a volume-snapable chat interface with context-aware widgets to help users express better in NLP code.
References:
[1]
2023. csm. Retrieved May 17, 2024 from https://csm.ai
[2]
2023a. fal. Retrieved May 17, 2024 from https://fal.ai
[3]
2023b. fal LCM. Retrieved May 17, 2024 from https://fal.ai/models/fal-ai/lcm
[4]
2023. Github: LGM. Retrieved May 17, 2024 from https://github.com/3DTopia/LGM
[5]
2023. Github: LRM. Retrieved May 17, 2024 from https://github.com/3DTopia/OpenLRM
[6]
2023a. Github: TripoSR. Retrieved May 17, 2024 from https://github.com/VAST-AI-Research/TripoSR
[7]
2023. HuggingFace Spaces. Retrieved May 17, 2024 from https://huggingface.com
[8]
2023. Luma Labs. Retrieved May 17, 2024 from https://lumalabs.ai
[9]
2023. Meshy. Retrieved May 17, 2024 from https://meshy.ai
[10]
2023. Replicate. Retrieved May 17, 2024 from https://replicate.com
[11]
2023. SudoAI. Retrieved May 17, 2024 from https://sudo.ai
[12]
2023b. Tripo3D. Retrieved May 17, 2024 from https://tripo3d.ai
[13]
2024. Github: TencentArc/InstantMesh. Retrieved May 17, 2024 from https://github.com/TencentARC/InstantMesh
[14]
2024. huggingface space: TencentArc/InstantMesh on Zero. Retrieved May 17, 2024 from https://huggingface.co/spaces/TencentARC/InstantMesh
[15]
2024a. Replicate/bytedance/sdxl-lightning-4step on A100. Retrieved May 17, 2024 from https://replicate.com/bytedance/sdxl-lightning-4step
[16]
2024b. Replicate/camenduru/InstantMesh on A100. Retrieved May 17, 2024 from https://replicate.com/camenduru/instantmesh
[17]
Yosun Chang. 2020. DrawmaticAR. https://DrawmaticAR.com.
[18]
Yosun Chang. 2023a. Napkinmatic. In ACM SIGGRAPH 2023 Appy Hour (Los Angeles, CA, USA) (SIGGRAPH ?23). Association for Computing Machinery, New York, NY, USA, Article 4, 2 pages. https://doi.org/10.1145/3588427.3595357
[19]
Yosun Chang. 2023b. Napkinmatic 3D. In ACM SIGGRAPH 2023 Real-Time Live! (Los Angeles, CA, USA) (SIGGRAPH ?23). Association for Computing Machinery, New York, NY, USA, Article 6, 2 pages. https://doi.org/10.1145/3588430.3597253
[20]
Yosun Chang. 2024a. AI3D Benchmark Card: Stanford Bunny PBR (Permalink). Retrieved May 17, 2024 from https://ai3d.dev/benchmark/stanford_bunny_pbr/
[21]
Yosun Chang. 2024b. VolumeMatic Demo. Retrieved Feb 2, 2024 from https://x.com/Yosun/status/1759980927361360301
[22]
Discord Inc.[n. d.]. Discord. https://discord.com
[23]
Hackmans. 2022. Sketchfab: Stanford Bunny PBR. Retrieved May 17, 2024 from https://sketchfab.com/3d-models/stanford-bunny-pbr-42c9bdc4d27a418daa19b2d5ff690095
[24]
Stanford University Computer Graphics Laboratory. 1993. Stanford Bunny. Retrieved May 17, 2024 from https://graphics.stanford.edu/data/3Dscanrep/
[25]
Christopher A. aka CATID Taylor. 2024. Github: catid/InstantMesh on RTX4090. Retrieved May 17, 2024 from https://github.com/catid/InstantMesh
[26]
Gemini Team. 2024. Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context. arxiv:2403.05530 [cs.CL]