profile

Mahesh Reddy

I am a Researcher at Qualcomm AI Research and working on 3D computer vision and generative AI. I completed my MSc in Computing Science from Simon Fraser University, where I was advised by Prof. Yağız Aksoy. Previously, I was a research intern at Borealis AI and received my MSc in Computer Science from the University of Manitoba, where I was advised by Prof. Yang Wang. Before that, I received my BE in Information Science from VTU, India.
         

Publications

profile
HexaGen3D: StableDiffusion is just one step away from Fast and Diverse Text-to-3D Generation
Antoine Mercier, Ramin Nakhli, Mahesh Reddy, Rajeev Yasarla, Hong Cai, Fatih Porikli, and Guillaume Berger
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2025
paper
profile
Scale-Invariant Monocular Depth Estimation via SSI Depth
S. Mahdi H. Miangoleh, Mahesh Reddy, and Yağız Aksoy
SIGGRAPH, 2024
webpage // paper // video // code
profile
EdgeRelight360: Text-Conditioned 360-Degree HDR Image Generation for Real-Time On-Device Video Portrait Relighting
Min-Hui Lin*, Mahesh Reddy*, Guillaume Berger, Michel Sarkis, Fatih Porikli, and Ning Bi
CVPR Workshop on Efficient and On-Device Generation (EDGE), 2024
paper // video
profile
Datamoshing with Optical Flow
Chris Careaga, Mahesh Reddy, and Yağız Aksoy
SIGGRAPH Asia Posters, 2023
webpage // paper // code
profile
Interactive Editing of Monocular Depth
Obumneme Stanley Dukor, S. Mahdi H. Miangoleh, Mahesh Reddy, Long Mai, and Yağız Aksoy
SIGGRAPH Posters, 2022
interactive editor // webpage // paper
profile
AdaCrowd: Unlabeled Scene Adaptation for Crowd Counting
Mahesh Reddy, Mrigank Rochan, Yiwei Lu and Yang Wang
IEEE Transactions on Multimedia (TMM), 2021
paper // code
profile
Sentence Guided Temporal Modulation for Dynamic Video Thumbnail Generation
Mrigank Rochan, Mahesh Reddy and Yang Wang
British Machine Vision Conference (BMVC), 2020
paper
profile
Adaptive Video Highlight Detection by Learning from User History
Mrigank Rochan, Mahesh Reddy, Linwei Ye and Yang Wang
European Conference on Computer Vision (ECCV), 2020
paper // code
profile
Few-Shot Scene-Adaptive Anomaly Detection
Yiwei Lu, Frank Yu, Mahesh Reddy and Yang Wang
European Conference on Computer Vision (ECCV), 2020 (Spotlight)
paper // code
profile
Few-Shot Scene Adaptive Crowd Counting Using Meta-Learning
Mahesh Reddy, Mohammad Hossain, Mrigank Rochan and Yang Wang
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2020
paper // code // poster
profile
Domain Adaptation in Crowd Counting
Mohammad Hossain, Mahesh Reddy, Kevin Cannons, Zhan Xu and Yang Wang
Conference on Robot and Computer Vision (CRV), 2020
paper
profile
One-Shot Scene-Specific Crowd Counting
Mohammad Hossain, Mahesh Reddy, Mehrdad Hosseinzadeh, Omit Chanda and Yang Wang
British Machine Vision Conference (BMVC), 2019
paper
profile
Future Frame Prediction Using Convolutional VRNN for Anomaly Detection
Yiwei Lu, Mahesh Reddy, Seyed shahabeddin Nabavi and Yang Wang
IEEE International Conference on Advanced Video and Signal-based Surveillance (AVSS), 2019
paper // code

Theses

Metric Monocular Reconstruction through Ordinal Depth
Mahesh Reddy
MSc Thesis, Simon Fraser University, 2022
profile
Scene Adaptive Crowd Counting
Mahesh Reddy
MSc Thesis, University of Manitoba, 2020