lognat0704/qwen2-7b-instruct-trl-sft-ChartQA
Image-Text-to-Text • Updated • 16
Nelson Tseng PRO
lognat0704
·
AI & ML interests
Engineer working on generative media - diffusion models, LoRA fine-tuning, and squeezing image/vision models down to run fast and cheap (NVFP4 & low-bit quantization). Also fine-tune vision-language models (Qwen2-VL on ChartQA). Building tools that put creative AI in the hands of creators.
Recent Activity
updated a model 5 days ago
lognat0704/qwen2-7b-instruct-trl-sft-ChartQA updated a dataset 5 days ago
lognat0704/lyradiff updated a model 5 days ago
lognat0704/diffusion-lorasOrganizations
updated a
model 5 days ago
updated a
dataset 5 days ago
updated a
model 5 days ago
published a
model about 2 months ago
updated a
model 4 months ago
updated a
dataset 6 months ago
published a
dataset 6 months ago
published a
model 6 months ago
updated a
model about 1 year ago
published a
model about 1 year ago
published a
dataset about 1 year ago
reacted to DmitryRyumin's post with ❤️🔥 about 2 years ago
Post
2553
🚀🕺🌟 New Research Alert - CVPR 2024 (Avatars Collection)! 🌟💃🚀
📄 Title: 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting 🔝
📝 Description: 3DGS-Avatar is a novel method for creating animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS). By using a non-rigid deformation network and as-isometric-as-possible regularizations, the method achieves comparable or better performance than SOTA methods while being 400x faster in training and 250x faster in inference, allowing real-time rendering at 50+ FPS.
👥 Authors: Zhiyin Qian, Shaofei Wang, Marko Mihajlovic, Andreas Geiger, Siyu Tang
📅 Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA 🇺🇸
🔗 Paper: 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (2312.09228)
🌐 Github Page: https://neuralbodies.github.io/3DGS-Avatar/
📁 Repository: https://github.com/mikeqzy/3dgs-avatar-release
📺 Video: https://www.youtube.com/watch?v=FJ29U9OkmmU
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36
🔍 Keywords: #3DGSAvatar #3DAvatar #3DGaussianSplatting #AnimatableAvatars #MonocularVideo #RealTimeRendering #FastTraining #EfficientInference #CVPR2024 #DeepLearning #Innovation
📄 Title: 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting 🔝
📝 Description: 3DGS-Avatar is a novel method for creating animatable human avatars from monocular videos using 3D Gaussian Splatting (3DGS). By using a non-rigid deformation network and as-isometric-as-possible regularizations, the method achieves comparable or better performance than SOTA methods while being 400x faster in training and 250x faster in inference, allowing real-time rendering at 50+ FPS.
👥 Authors: Zhiyin Qian, Shaofei Wang, Marko Mihajlovic, Andreas Geiger, Siyu Tang
📅 Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA 🇺🇸
🔗 Paper: 3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting (2312.09228)
🌐 Github Page: https://neuralbodies.github.io/3DGS-Avatar/
📁 Repository: https://github.com/mikeqzy/3dgs-avatar-release
📺 Video: https://www.youtube.com/watch?v=FJ29U9OkmmU
📚 More Papers: more cutting-edge research presented at other conferences in the DmitryRyumin/NewEraAI-Papers curated by @DmitryRyumin
🚀 Added to the Avatars Collection: DmitryRyumin/avatars-65df37cdf81fec13d4dbac36
🔍 Keywords: #3DGSAvatar #3DAvatar #3DGaussianSplatting #AnimatableAvatars #MonocularVideo #RealTimeRendering #FastTraining #EfficientInference #CVPR2024 #DeepLearning #Innovation
updated 2
models over 2 years ago
liked a
model over 3 years ago
