Benran Hu

I'm an MSCS student at CMU and am expected to graduate in December, 2024. I'm actively looking for PhD and full-time industry opportunities.

At CMU, I work with Prof. Ioannis Gkioulekas on uncertainty quantification in differentiable rendering. Previously, I interned at Snap Research with Ivan Skorokhodov on better video generation models. I received my B.Sc. in Computer Science from HKUST, where I was advised by Prof. Chi-Keung Tang, Prof. Yu-Wing Tai, and Prof. Pedro V. Sander.

Email  /  CV  /  Scholar  /  Github

Research

I'm interested in 3D vision, differentiable rendering, real-time rendering, generative AI, as well as other computer vision and graphics fields. My past research is mainly on empowering radiance fields and other 3D representations with the capability of scene understanding. I also work on uncertainty quantification in differentiable rendering, and accelerating rendering with temporal reprojection.

Fusing multi-view SAM segmentation masks as an object field improves the performance of zero-shot 3D segmentation in NeRF.

3D instance segmentation in NeRF by matching multi-view instance masks with sparse 3D masks produced by a 3D Mask R-CNN.

We introduce 3D object detection to NeRF by sampling feature grids from radiance fields and applying a 3D detector on them.

This is another website using Jon Barron's template.