KMKaushik Mitra

Kaushik Mitra

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Kaushik Mitra has a total of 89 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Dark Stereo Multi-Exposure Dataset (DSMD) for extreme low-light image restoration and depth estimation

    by Rongali Simhachala Venkata Girish, M.V.A. Suhas Kumar, Mohit Lamba, Devaganthan S.S., Adithya Lenka, Kaushik Mitra

  • Open Access

    Blur to Brilliance: Neuromorphic Data Guided Deblurring and HDR Novel View Synthesis

    by Sally Khaidem, Anirud Nandakumar, Mansi Sharma, Kaushik Mitra

    Event cameras are neuromorphic sensors that asynchronously capture intensity changes, making them highly effective for fast motion and challenging lighting conditions. While Neural Radiance Fields (NeRFs) have revolutionized 3D scene representation, they remain limited when operating on blurred, low dynamic range (LDR) inputs. In this work, we present a novel framework that fuses blurred RGB frames with an accompanying event stream to reconstruct sharp, high-dynamic range (HDR) novel views. Specifically, we exploit the high temporal resolution of events to guide luma sharpening and dynamic range expansion, generating intermediate HDR image sequences. We generate a stack of sharp LDR images at different exposures through tone mapping, which are then integrated into an enhanced NeRF pipeline. This enables our model to learn richer radiance fields that recover fine details and handle extreme lighting variations more effectively than existing methods. Extensive experiments on real and simulated benchmarks show that our approach is competitive with state-of-the-art HDR and LDR NeRF methods and often outperforms them. This demonstrates its potential as a robust solution for generating high-quality novel views in fast-motion scenarios and challenging lighting conditions.

  • Open Access

    A Hybrid Dataset and Depth-Guided Transformer for Nighttime Flare Removal

    by Advait Amit Kisar, Sumeet Shekhar, Gopi Raju Matta, Kaushik Mitra

  • Open Access

    U2NeRF: Unsupervised Underwater Image Restoration and Neural Radiance Fields

    by Vinayak Gupta, Manoj S, Mukund Varma T, Kaushik Mitra

    Underwater images suffer from colour shifts, low contrast, and haziness due to light absorption, refraction, scattering and restoring these images has warranted much attention. In this work, we present Unsupervised Underwater Neural Radiance Field U2NeRF, a transformer-based architecture that learns to render and restore novel views conditioned on multi-view geometry simultaneously. Due to the absence of supervision, we attempt to implicitly bake restoring capabilities onto the NeRF pipeline and disentangle the predicted color into several components - scene radiance, direct transmission map, backscatter transmission map, and global background light, and when combined reconstruct the underwater image in a self-supervised manner. In addition, we release an Underwater View Synthesis UVS dataset consisting of 12 underwater scenes, containing both synthetically-generated and real-world data. Our experiments demonstrate that when optimized on a single scene, U2NeRF outperforms several baselines by as much LPIPS 11%, UIQM 5%, UCIQE 4% (on average) and showcases improved rendering and restoration capabilities. Code will be made available upon acceptance.

  • Open Access

    R 2 SFD: Improving Single Image Reflection Removal using Semantic Feature Dictionary

    by Green Rosh, Pawan Prasad B H, Lokesh R. Boregowda, Kaushik Mitra

    Single image reflection removal is a severely ill-posed problem and it is very hard to separate the desirable transmission and undesirable reflection layers. Most of the existing single image reflection removal methods try to recover the transmission layer by exploiting cues that are extracted only from the given input image. However, there is abundant unutilized information in the form of millions of reflection free images available publicly. Even though this information is easily available, utilizing the same for effectively removing reflections is non-trivial. In this paper, we propose a novel method, termed R^2SFD, for improving single image reflection removal using a Semantic Feature Dictionary (SFD) constructed from a database of reflection-free images. The SFD is constructed using a novel Reflection Aware Feature Extractor (RAFENet) that extracts features invariant to the presence of reflections. The SFD and the input image are then passed to another novel network termed SFDNet. This network first extracts RAFENet features from the reflection-corrupted input image, searches for similar features in the SFD, and transfers the semantic content to generate the final output. To further improve reflection removal, we also introduce a Large Scale Reflection Removal (LSRR) dataset consisting of 2650 image pairs comprising of a variety of real world reflection scenarios. The proposed method achieves superior results both qualitatively and quantitatively compared to the state of the art single image reflection removal methods on real public datasets as well as our LSRR dataset. We will release the dataset at https://github.com/ee19d005/r2sfd.


  • Open Access

    Fast Single Image Reflection Removal Using Multi-Stage Scale Space Network

    by B. H. Pawan Prasad, Green Rosh, R. B. Lokesh, Kaushik Mitra

    Images captured in front of a glass obstruction often suffer from degradation due to the presence of reflections. These reflections can be classified as either high transmitted or low transmitted depending upon whether the captured image is dominated by either the background or the reflections respectively. Current approaches either aim to handle only high transmitted reflections or propose to train a unified neural network for addressing both kinds of reflections. However, using a single network to address different types of reflections is not very effective. Further, these methods are also computationally expensive and impractical to deploy on devices with limited resources such as smart-phones. To address these challenges, we present a multi-stage pipeline for single image reflection removal within a scale space framework to address low and high transmitted reflections separately. Specifically, we treat the removal of low transmitted reflections that typically obscure the desired background as an inpainting challenge, while we handle high transmitted reflections using conventional techniques. We use specialized networks for these types of reflections within a scale space architecture that is light weight and is capable of removing reflections from very high resolution images. Our method shows superior performance both qualitatively and quantitatively compared to state of the art methods and our smartphone implementation takes about ~ 5 seconds to generate a high resolution 12 MP image.


  • OpEnCam: Lensless Optical Encryption Camera

    by Salman S. Khan, Xiang Yu, Kaushik Mitra, Manmohan Chandraker, Francesco Pittaluga

    Lensless cameras multiplex the incoming light before it is recorded by the sensor. This ability to multiplex the incoming light has led to the development of ultra-thin, high-speed, and single-shot 3D imagers. Recently, there have been various attempts at demonstrating another useful aspect of lensless cameras - their ability to preserve the privacy of a scene by capturing encrypted measurements. However, existing lensless camera designs suffer numerous inherent privacy vulnerabilities. To demonstrate this, we develop the first comprehensive attack model for encryption cameras, and propose OPENCAM– a novel lensless optical encryption camera design that overcomes these vulnerabilities. OPENCAM encrypts the incoming light before capturing it using the modulating ability of optical masks. Recovery of the original scene from an OPENCAM measurement is possible only if one has access to the camera's encryption key, defined by the unique optical elements of each camera. Our OPENCAM design introduces two major improvements over existing lensless camera designs - (a) the use of two co-axially located optical masks, one stuck to the sensor and the other a few millimeters above the sensor and (b) the design of mask patterns, which are derived heuristically from signal processing ideas. We show, through experiments, that OPENCAM is robust against a range of attack types while still maintaining the imaging capabilities of existing lensless cameras. We validate the efficacy of OPENCAM using simulated and real data. Finally, we built and tested a prototype in the lab for proof-of-concept