Brightdreamer: Generic 3d gaussian generative framework for fast text-to-3d synthesis

L Jiang, X Zheng, Y Lyu, J Zhou, L Wang - arxiv preprint arxiv:2403.11273, 2024 - arxiv.org
Text-to-3D synthesis has recently seen intriguing advances by combining the text-to-image
priors with 3D representation methods, eg, 3D Gaussian Splatting (3D GS), via Score …

Baking gaussian splatting into diffusion denoiser for fast and scalable single-stage image-to-3d generation

Y Cai, H Zhang, K Zhang, Y Liang, M Ren… - arxiv preprint arxiv …, 2024 - arxiv.org
Existing feed-forward image-to-3D methods mainly rely on 2D multi-view diffusion models
that cannot guarantee 3D consistency. These methods easily collapse when changing the …

LangSurf: Language-Embedded Surface Gaussians for 3D Scene Understanding

H Li, R Qin, Z Zou, D He, B Li, B Dai, D Zhang… - arxiv preprint arxiv …, 2024 - arxiv.org
Applying Gaussian Splatting to perception tasks for 3D scene understanding is becoming
increasingly popular. Most existing works primarily focus on rendering 2D feature maps from …