Search Results for author: Rajiv Soundararajan

Found 10 papers, 7 papers with code

Test Time Adaptation for Blind Image Quality Assessment

2 code implementations ICCV 2023 Subhadeep Roy, Shankhanil Mitra, Soma Biswas, Rajiv Soundararajan

In this work, we introduce two novel quality-relevant auxiliary tasks at the batch and sample levels to enable TTA for blind IQA.

Blind Image Quality Assessment Test

ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields

1 code implementation28 Apr 2023 Nagabhushan Somraj, Rajiv Soundararajan

We reformulate the NeRF to also directly output the visibility of a 3D point from a given viewpoint to reduce the training time with the visibility constraint.

Depth Estimation

Semi-supervised Learning of Perceptual Video Quality by Generating Consistent Pairwise Pseudo-Ranks

no code implementations30 Nov 2022 Shankhanil Mitra, Saiyam Jogani, Rajiv Soundararajan

Designing learning-based no-reference (NR) video quality assessment (VQA) algorithms for camera-captured videos is cumbersome due to the requirement of a large number of human annotations of quality.

Video Quality Assessment Visual Question Answering (VQA)

Low Light Video Enhancement by Learning on Static Videos with Cross-Frame Attention

1 code implementation9 Oct 2022 Shivam Chhirolya, Sameer Malik, Rajiv Soundararajan

The design of deep learning methods for low light video enhancement remains a challenging problem owing to the difficulty in capturing low light and ground truth video pairs.

Video Enhancement

Multiview Contrastive Learning for Completely Blind Video Quality Assessment of User Generated Content

1 code implementation13 Jul 2022 Shankhanil Mitra, Rajiv Soundararajan

Completely blind video quality assessment (VQA) refers to a class of quality assessment methods that do not use any reference videos, human opinion scores or training videos from the target database to learn a quality model.

Contrastive Learning Optical Flow Estimation +2

Quality Assessment of Low Light Restored Images: A Subjective Study and an Unsupervised Model

no code implementations4 Feb 2022 Vignesh Kannan, Sameer Malik, Rajiv Soundararajan

Challenges in capturing aligned low light and well-lit image pairs and collecting a large number of human opinion scores of quality for training, warrant the design of unsupervised (or opinion unaware) no-reference (NR) QA methods.

Benchmarking Contrastive Learning

Revealing Disocclusions in Temporal View Synthesis through Infilling Vector Prediction

1 code implementation17 Oct 2021 Vijayalakshmi Kanchana, Nagabhushan Somraj, Suraj Yadwad, Rajiv Soundararajan

We consider the problem of temporal view synthesis, where the goal is to predict a future video frame from the past frames using knowledge of the depth and relative camera motion.

Temporal View Synthesis

Understanding the Perceived Quality of Video Predictions

1 code implementation1 May 2020 Nagabhushan Somraj, Manoj Surya Kashi, S. P. Arun, Rajiv Soundararajan

We show that our feature design leads to state of the art quality prediction in accordance with human judgments on our IISc PVQA Database.

Representation Learning Video Prediction

Cannot find the paper you are looking for? You can Submit a new open access paper.