5 papers
Precise: SDE-Consistent Stochastic Sampling for RL Post-Training of Flow-Matching Models
Jade Zou, Tao Huang, Weijie Kong +7
Reinforcement learning (RL) has become an effective way to improve prompt alignment and perceptual quality in diffusion and flow-matching generators. A critical step for applying o…
Real-Time Neural Hair G-Buffer Anti-Aliasing
Chenghao Wu, Yuefan Shen, Tao Huang +3
We propose a lightweight real-time method for reconstructing strand-based hair G-Buffers from severely undersampled rasterized inputs. Our pipeline first applies neural spatial rec…
Real-time Neural Six-way Lightmaps
Wei Li, Hanxiao Sun, Tao Huang +4
Participating media are a pervasive and intriguing visual effect in virtual environments. Unfortunately, rendering such phenomena in real-time is notoriously difficult due to the c…
Efficient Scene Appearance Aggregation for Level-of-Detail Rendering
Yang Zhou, Tao Huang, Ravi Ramamoorthi +2
Creating an appearance-preserving level-of-detail (LoD) representation for arbitrary 3D scenes is a challenging problem. The appearance of a scene is an intricate combination of bo…
Real-time Level-of-Detail Strand-based Hair Rendering
Tao Huang, Yang Zhou, Daqi Lin +3
Strand-based hair rendering has become increasingly popular in production for its realistic appearance. However, the prevailing level-of-detail solution employing hair cards for di…