Avinash Paliwal

I am a PhD Candidate in the Computer Science and Engineering department at Texas A&M University, advised by Dr. Nima Kalantari in the Aggie Graphics Group. My primary research interests are in 3D Computer Vision and Computational Photography. My current research work is focused on fast and photorealistic novel view synthesis from sparse images.

I was a Research Scientist Intern at Meta Reality Labs in 2023, a Research Intern at Leia Inc. in 2021 and SDE intern at Amazon in 2019.

I am actively looking for a Research position in industry starting Spring 2025.

Email / CV / Google Scholar / GitHub / LinkedIn

Research

	RI3D: Few-Shot Gaussian Splatting With Repair and Inpainting Diffusion Priors Avinash Paliwal, Xilong Zhou, Wei Ye, Jinhui Xiong, Rakesh Ranjan, Nima Kalantari arXiv, 2025 project page / arXiv / code / bibtex Create 3D scenes from extremely sparse images using finetuned diffusion models.
	PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion Avinash Paliwal, Xilong Zhou, Andrii Tsarov, Nima Kalantari arXiv, 2024 project page / arXiv / code / bibtex Create 360° 3D scenes from a single image.
	CoherentGS: Sparse Novel View Synthesis with Coherent 3D Gaussians Avinash Paliwal, Wei Ye, Jinhui Xiong, Dmytro Kotovenko, Rakesh Ranjan, Vikas Chandra, Nima Kalantari European Conference on Computer Vision (ECCV), 2024 project page / arXiv / conference / code / bibtex Coherent 3D Gaussians using an implicit decoder.
	WaSt-3D: Wasserstein-2 Distance for Scene-to-Scene Stylization on 3D Gaussians Dmytro Kotovenko, Olga Grebenkova, Nikolaos Sarafianos, Avinash Paliwal, Pingchuan Ma, Omid Poursaeed, Sreyas Mohan, Yuchen Fan, Yilei Li, Rakesh Ranjan, Bjorn Ommer European Conference on Computer Vision (ECCV), 2024 project page / arXiv / conference / code / bibtex 3D scene stylization with 3D Gaussians.
	ReShader: View-Dependent Highlights for Single Image View-Synthesis Avinash Paliwal, Brandon Nguyen, Andrii Tsarov, Nima Kalantari SIGGRAPH Asia (TOG), 2023 project page / arXiv / journal / video / code / bibtex Photorealistic view dependent effects.
	Implicit View-Time Interpolation of Stereo Videos using Multi-Plane Disparities and Non-Uniform Coordinates Avinash Paliwal, Andrii Tsarov, Nima Kalantari IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2023 project page / arXiv / conference / video / code / bibtex Real-time space time interpolation from stereo videos.
	Frame Interpolation for Dynamic Scenes with Implicit Flow Encoding Pedro Figueirêdo, Avinash Paliwal, Nima Kalantari IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2023 project page / arXiv / conference / video / code / bibtex Smooth interpolation between two near duplicate photos.
	Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask Avinash Paliwal, Libing Zeng, Nima Kalantari IEEE International Conference on Computational Photography (ICCP), 2021 project page / arXiv / conference / video / code / bibtex Temporally consistent adversarial raw video denoising.
	Deep Slow Motion Video Reconstruction with Hybrid Imaging System Avinash Paliwal, Nima Kalantari IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2020 project page / arXiv / journal / video / code / bibtex Generating Full HD (1080p) slow motion videos using dual cameras.

Teaching

	CSCE 441: Computer Graphics, Fall 2020 Graduate Teaching Assistant
	CSCE 489/689: Computational Photography, Spring 2020 Graduate Teaching Assistant

The original website!