Kangxue Yin
Research Subjects
Research Interests
Kangxue Yin has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Evangelos Kalogerakis
University of Massachusetts Amherst
1 shared publicationGopal Sharma
University of Massachusetts Amherst
1 shared publication- Karsten Kreis
NVIDIA
1 shared publication - Nicholas Sharp
NVIDIA
1 shared publication Or Litany
NVIDIA
1 shared publicationSanja Fidler
NVIDIA
1 shared publication
Latest Publications
- Open Access
TexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models
We present TexFusion (Texture Diffusion), a new method to synthesize textures for given 3D geometries, using large-scale text-guided image diffusion models. In contrast to recent works that leverage 2D text-to-image diffusion models to distill 3D objects using a slow and fragile optimization process, TexFusion introduces a new 3D-consistent generation technique specifically designed for texture synthesis that employs regular diffusion model sampling on different 2D rendered views. Specifically, we leverage latent diffusion models, apply the diffusion model's denoiser on a set of 2D renders of the 3D object, and aggregate the different denoising predictions on a shared latent texture map. Final output RGB textures are produced by optimizing an intermediate neural color field on the decodings of 2D renders of the latent texture. We thoroughly validate TexFusion and show that we can efficiently generate diverse, high quality and globally coherent textures. We achieve state-of-the-art text-guided texture synthesis performance using only image diffusion models, while avoiding the pitfalls of previous distillation-based methods. The text-conditioning offers detailed control and we also do not rely on any ground truth 3D textures for training. This makes our method versatile and applicable to a broad range of geometry and texture types. We hope that TexFusion will advance AI-based texturing of 3D assets for applications in virtual reality, game design, simulation, and more.
Open AccessTexFusion: Synthesizing 3D Textures with Text-Guided Image Diffusion Models
We present TexFusion (Texture Diffusion), a new method to synthesize textures for given 3D geometries, using large-scale text-guided image diffusion models. In contrast to recent works that leverage 2D text-to-image diffusion models to distill 3D objects using a slow and fragile optimization process, TexFusion introduces a new 3D-consistent generation technique specifically designed for texture synthesis that employs regular diffusion model sampling on different 2D rendered views. Specifically, we leverage latent diffusion models, apply the diffusion model's denoiser on a set of 2D renders of the 3D object, and aggregate the different denoising predictions on a shared latent texture map. Final output RGB textures are produced by optimizing an intermediate neural color field on the decodings of 2D renders of the latent texture. We thoroughly validate TexFusion and show that we can efficiently generate diverse, high quality and globally coherent textures. We achieve state-of-the-art text-guided texture synthesis performance using only image diffusion models, while avoiding the pitfalls of previous distillation-based methods. The text-conditioning offers detailed control and we also do not rely on any ground truth 3D textures for training. This makes our method versatile and applicable to a broad range of geometry and texture types. We hope that TexFusion will advance AI-based texturing of 3D assets for applications in virtual reality, game design, simulation, and more.
- 11 November 2022
- Published by Springer Nature
- p. 550-567
MvDeCor: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation
- 11 November 2022
- Published by Springer Nature
- p. 550-567
MvDeCor: Multi-view Dense Correspondence Learning for Fine-Grained 3D Segmentation