Presentation

<
PixTex: Consistent 3D Texturing via Pixel-Space Multi-View Diffusion
SessionGenerative 3D (2)
DescriptionWe propose PixTex, the first pixel-space multi-view diffusion framework for texture generation. By bypassing latent compression and utilizing a coarse-to-fine strategy, it ensures lossless geometric guidance and superior pixel-level multi-view consistency, achieving state-of-the-art, high-fidelity, and seamless results.
Authors
Yuqing Zhang
State Key Lab of CAD&CG, Zhejiang
Yan-Pei Cao
VAST
Hao Xu
State Key Lab of CAD&CG, Zhejiang University
Yiqian Wu
State Key Lab of CAD&CG, Zhejiang University
Sirui Lin
State Key Lab of CAD&CG, Zhejiang University
Yuqing Wang
State Key Lab of CAD&CG, Zhejiang University
Ding Liang
VAST
Yuan-Chen Guo
VAST
Xiaogang Jin
Zhejiang University
State Key Laboratory of CAD&CG, Zhejiang University
Event Type
Technical Paper
TimeTuesday, 21 July 20269:40am - 9:50am PDT
LocationRoom 403 B
Digital Library PDF
Session Time & Location
Sunday, 19 July 20266:00pm - 8:45pm PDTHall K
Tuesday, 21 July 20269:00am - 10:30am PDTRoom 403 B
Keywords
Artificial Intelligence/Machine Learning
Registration Categories
Full Conference Supporter
Full Conference
Next PresentationNext PresentationGenerative 3D Gaussians with Learned Density Control
Similar Presentations
Controllable Texture Tiling via Diffusion Transformers with Transformed Rotary Embeddings
Generative 3D Gaussians with Learned Density Control
GeoQuery: Geometry-Query Diffusion for Sparse-View Reconstruction