Check out Gaussian-enhanced Surfels (GESs) from Zhejiang University!
A novel bi-scale radiance field representation combining 2D opaque surfels (coarse geometry) with 3D Gaussians (fine details).
Fast, sorting-free rendering with high fidelity and view consistency.
AnySyn3D is a non-commercial, non-profit research group focused on 3D AIGC research and cutting-edge technologies.
Joined February 2024
- 🔥🔥🔥Don't miss it! GECO proposes a 3D distillation pipeline and trains a feedforward 3D generative model that inferences only in 0.4s. It also outperforms reconstruction models by better handling the back view! #AIGC #3D #3DVision #DiffusionModel #Deeplearning #ReconstructionExcited to share our new work GECO, a 3D distillation pipeline to train a feedforward 3D generative model that operates in only 0.4s. (1/n)
- 🚀 Check out our Era3D! Efficient single-to-multiple view generation for high-res images!🚀 Era3D: A new AI model that creates high-res 🗿3D images from multiple viewpoints using just one input image!🌄 - Generates high-quality images up to 512×512 pixels🎯 - Uses efficient row-wise attention to reduce computation⚡ - 12x more efficient than sota methods💪
- Check it out! 🚀DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos.Thanks for the tweet. We improve 3D Gaussain splatting for dash cam videos that contain serious reflections and obstructions. With Dash cam videos, it's possible to leverage massive driving data. Visit our page at linhanwang.github.io/dcgaussian/ Codes will be soon.
- ✨The rapid progress in 3D generation is impressive, but generated meshes often lack structure. We integrate *parts* into the reconstruction process, enhancing segmentation, structural distinction, and shape editing! Project Page: liuar0512.github.io/part123_offici… #SIGGRAPH2024 #AIGC




