It's about learning to get (surface) Normal!
Computer Vision | Computer Graphics | Deep Learning
My primary research interest is in extending the boundaries of photometric methods - Photometric Stereo, Shape from Polarization, and Photo-polarimetric Stereo to infer the physical 3D world through (neural) inverse rendering approaches. I am also interested in exploring creative art forms, human pose transfer, and graph representation learning.
Incremental Multi-Scene Modeling via Continual Neural Graphics Primitives
Prajwal Singh, Ashish Tiwari, Gautam Vashishta, and Shanmuganathan Raman
British Machine Vision Conference (BMVC) 2025, Sheffield, UK
paper | project page
RASP: Revisiting 3D Anamorphic Art for Shadow-Guided Packing of Irregular Objects
Soumyaratna Debnath*, Ashish Tiwari*, Kaustubh Sadekar, and Shanmuganathan Raman
* equal contribution
IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) 2025, Nashville, Tennessee
LIPIDS: Learning-based Illumination Planning In Discretized (Light) Space for Photometric Stereo (Oral)
Ashish Tiwari, Mihirkumar Sutariya, and Shanmuganathan Raman
Winter Conference on Applications of Computer Vision (WACV) 2025, Tucson, Arizona
MERLiN: Single-Shot Material Estimation and Relighting for Photometric Stereo [**New**]
Ashish Tiwari, Satoshi Ikehata, and Shanmuganathan Raman
European Conference on Computer Vision (ECCV) 2024, Milan, Italy, Sep 29 - Oct 4, 2024.
ScribGen: Generating Scribble Art Through Metaheuristics [**New**]
Soumyaratna Debnath, Ashish Tiwari, and Shanmuganathan Raman
SIGGRAPH Asia 2024, Tokyo, Japan
SS-SfP: Neural Inverse Rendering for Self-Supervised Shape from (Mixed) Polarization (Oral)
Ashish Tiwari and Shanmuganathan Raman
Pacific Graphics 2023, Daejeon, South Korea, October 10-13, 2023.
Hand Shadow Art: A Differentiable Rendering Perspective (Best Poster Award)
Aalok Gangopadhyay, Prajwal Singh, Ashish Tiwari and Shanmuganathan Raman
Pacific Graphics 2023, Daejeon, South Korea, October 10-13, 2023.
TreeGCN-ED: A Tree-Structured Graph-Based Autoencoder
Framework For Point Cloud Processing
Prajwal Singh, Ashish Tiwari, Kaustubh Sadekar, and Shanmuganathan Raman
Pacific Graphics 2023, Daejeon, South Korea, October 10-13, 2023.
DeepPS2: Revisiting Photometric Stereo Using Two Differently Illuminated Images
Ashish Tiwari and Shanmuganathan Raman
European Conference on Computer Vision (ECCV) 2022, Tel Aviv, Israel, October 25-27, 2022.
LERPS: Lighting Estimation and Relighting for Photometric Stereo
Ashish Tiwari and Shanmuganathan Raman
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2022, Singapore, May 22-27, 2022.
Shadow Art Revisited: A Differentiable Rendering Based Approach
Kaustubh Sadekar, Ashish Tiwari, and Shanmuganathan Raman
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), Waikoloa, HI, January 4-8, 2022.
Revisiting Heterophily in Graph Convolutional Networks By Learning Representations Across Topological and Feature Spaces
Ashish Tiwari, Sresth Tosniwal, and Shanmuganathan Raman
Exploring Deeper Graph Convolution for Semi-Supervised Node Classification
Ashish Tiwari, Richeek Das, and Shanmuganathan Raman
International Conference on Acoustics, Speech, and Signal Processing (ICASSP) 2022, Singapore, May 22-27, 2022.
Deep Appearance Consistent Human Pose Transfer
Ashish Tiwari, Zeeshan Khan, Aditya Vora, Manjuprakash Rama Rao, and Shanmuganathan Raman
International Conference on Pattern Recognition (ICPR) 2022, Montreal, Quebec, Canada, August 21-25, 2022.
LS-HDIB: A Large Scale Dataset for Handwritten Document Image Binarization
Kaustubh Sadekar, Ashish Tiwari, Prajwal Singh, and Shanmuganathan Raman
International Conference on Pattern Recognition (ICPR) 2022, Montreal, Quebec, Canada, August 21-25, 2022.