12 citations · 17 across the 8 of their papers we have counts for
8 papers
A Diffusion Model Translator for Efficient Image-to-Image Translation
Mengfei Xia, Yu Zhou, Ran Yi +2
Applying diffusion models to image-to-image translation (I2I) has recently received increasing attention due to its practical applications. Previous attempts inject information fro…
Rectified Diffusion Guidance for Conditional Generation
Mengfei Xia, Nan Xue, Yujun Shen +3
Classifier-Free Guidance (CFG), which combines the conditional and unconditional score functions with two coefficients summing to one, serves as a practical technique for diffusion…
PVP-Recon: Progressive View Planning via Warping Consistency for Sparse-View Surface Reconstruction
Sheng Ye, Yuze He, Matthieu Lin +8
Neural implicit representations have revolutionized dense multi-view surface reconstruction, yet their performance significantly diminishes with sparse input views. A few pioneerin…
Automatic Tooth Arrangement with Joint Features of Point and Mesh Representations via Diffusion Probabilistic Models
Changsong Lei, Mengfei Xia, Shaofeng Wang +4
Tooth arrangement is a crucial step in orthodontics treatment, in which aligning teeth could improve overall well-being, enhance facial aesthetics, and boost self-confidence. To im…
SMaRt: Improving GANs with Score Matching Regularity
Mengfei Xia, Yujun Shen, Ceyuan Yang +3
Generative adversarial networks (GANs) usually struggle in learning from highly diverse data, whose underlying manifold is complex. In this work, we revisit the mathematical founda…
Towards More Accurate Diffusion Model Acceleration with A Timestep Tuner
Mengfei Xia, Yujun Shen, Changsong Lei +5
A diffusion model, which is formulated to produce an image using thousands of denoising steps, usually suffers from a slow inference speed. Existing acceleration algorithms simplif…
TBench: Benchmarking Current Progress in Text-to-3D Generation
Yuze He, Yushi Bai, Matthieu Lin +6
Recent methods in text-to-3D leverage powerful pretrained diffusion models to optimize NeRF. Notably, these methods are able to produce high-quality 3D scenes without training on 3…
MMPI: a Flexible Radiance Field Representation by Multiple Multi-plane Images Blending
Yuze He, Peng Wang, Yubin Hu +4
This paper presents a flexible representation of neural radiance fields based on multi-plane images (MPI), for high-quality view synthesis of complex scenes. MPI with Normalized De…