D-Rex applies a LoRA-fine-tuned video diffusion model as an image-space post-process to add consistent relighting to any expressive full-body avatar pipeline while preserving motion and facial detail.
In: International Conference on 3D Vision (3DV)
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
CONDITIONAL 2representative citing papers
Both BiBO and LBO crystals deliver 32 W of 515 nm output from 57 W at 1030 nm with 56% conversion efficiency in a high-average-power picosecond setup, with direct performance comparisons.
citing papers explorer
-
D-Rex : Diffusion Rendering for Relightable Expressive Avatars
D-Rex applies a LoRA-fine-tuned video diffusion model as an image-space post-process to add consistent relighting to any expressive full-body avatar pipeline while preserving motion and facial detail.
-
Comparative study of second harmonic generation at 1030 nm in BiBO and LBO crystals using a 100 W-class picosecond laser
Both BiBO and LBO crystals deliver 32 W of 515 nm output from 57 W at 1030 nm with 56% conversion efficiency in a high-average-power picosecond setup, with direct performance comparisons.