Kaushik Mitra

Neham Jain, Gopi Matta, Kaushik Mitra

Recovery of true color from underwater images is an ill-posed problem. This is because the wide-band attenuation coefficients for the RGB color channels depend on object range, reflectance, etc. which are difficult to model. Also, there is backscattering due to suspended particles in water. Thus, most existing deep-learning based color restoration methods, which are trained on synthetic underwater datasets, do not perform well on real underwater data. This can be attributed to the fact that synthetic data cannot accurately represent real conditions. To address this issue, we use an image to image translation network to bridge the gap between the synthetic and real domains by translating images from synthetic underwater domain to real underwater domain. Using this multimodal domain adaptation technique, we create a dataset that can capture a diverse array of underwater conditions. We then train a simple but effective CNN based network on our domain adapted dataset to perform color restoration. Code and pre-trained models can be accessed at https://github.com/nehamjain10/TRUDGCR

Yi Ding, Aijia Gao, Thibaud Ryden et al. · mit

Datacenter operators ensure fair and regular server maintenance by using automated processes to schedule maintenance jobs to complete within a strict time budget. Automating this scheduling problem is challenging because maintenance job duration varies based on both job type and hardware. While it is tempting to use prior machine learning techniques for predicting job duration, we find that the structure of the maintenance job scheduling problem creates a unique challenge. In particular, we show that prior machine learning methods that produce the lowest error predictions do not produce the best scheduling outcomes due to asymmetric costs. Specifically, underpredicting maintenance job duration has results in more servers being taken offline and longer server downtime than overpredicting maintenance job duration. The system cost of underprediction is much larger than that of overprediction. We present Acela, a machine learning system for predicting maintenance job duration, which uses quantile regression to bias duration predictions toward overprediction. We integrate Acela into a maintenance job scheduler and evaluate it on datasets from large-scale, production datacenters. Compared to machine learning based predictors from prior work, Acela reduces the number of servers that are taken offline by 1.87-4.28X, and reduces the server offline time by 1.40-2.80X.

Atreyee Saha, Salman S Khan, Sagar Sehrawat et al.

Fourier Ptychographic Microscopy (FPM) is an imaging procedure that overcomes the traditional limit on Space-Bandwidth Product (SBP) of conventional microscopes through computational means. It utilizes multiple images captured using a low numerical aperture (NA) objective and enables high-resolution phase imaging through frequency domain stitching. Existing FPM reconstruction methods can be broadly categorized into two approaches: iterative optimization based methods, which are based on the physics of the forward imaging model, and data-driven methods which commonly employ a feed-forward deep learning framework. We propose a hybrid model-driven residual network that combines the knowledge of the forward imaging system with a deep data-driven network. Our proposed architecture, LWGNet, unrolls traditional Wirtinger flow optimization algorithm into a novel neural network design that enhances the gradient images through complex convolutional blocks. Unlike other conventional unrolling techniques, LWGNet uses fewer stages while performing at par or even better than existing traditional and deep learning techniques, particularly, for low-cost and low dynamic range CMOS sensors. This improvement in performance for low-bit depth and low-cost sensors has the potential to bring down the cost of FPM imaging setup significantly. Finally, we show consistently improved performance on our collected real data.

Vinayak Gupta, Rongali Simhachala Venkata Girish, Mukund Varma T et al.

Neural rendering methods can achieve near-photorealistic image synthesis of scenes from posed input images. However, when the images are imperfect, e.g., captured in very low-light conditions, state-of-the-art methods fail to reconstruct high-quality 3D scenes. Recent approaches have tried to address this limitation by modeling various degradation processes in the image formation model; however, this limits them to specific image degradations. In this paper, we propose a generalizable neural rendering method that can perform high-fidelity novel view synthesis under several degradations. Our method, GAURA, is learning-based and does not require any test-time scene-specific optimization. It is trained on a synthetic dataset that includes several degradation types. GAURA outperforms state-of-the-art methods on several benchmarks for low-light enhancement, dehazing, deraining, and on-par for motion deblurring. Further, our model can be efficiently fine-tuned to any new incoming degradation using minimal data. We thus demonstrate adaptation results on two unseen degradations, desnowing and removing defocus blur. Code and video results are available at vinayak-vg.github.io/GAURA.

Kitty Varghese, Sudarshan Rajagopalan, Mohit Lamba et al.

Saliency detection methods are central to several real-world applications such as robot navigation and satellite imagery. However, the performance of existing methods deteriorate under low-light conditions because training datasets mostly comprise of well-lit images. One possible solution is to collect a new dataset for low-light conditions. This involves pixel-level annotations, which is not only tedious and time-consuming but also infeasible if a huge training corpus is required. We propose a technique that performs classical band-pass filtering in the Fourier space to transform well-lit images to low-light images and use them as a proxy for real low-light images. Unlike popular deep learning approaches which require learning thousands of parameters and enormous amounts of training data, the proposed transformation is fast and simple and easy to extend to other tasks such as low-light depth estimation. Our experiments show that the state-of-the-art saliency detection and depth estimation networks trained on our proxy low-light images perform significantly better on real low-light images than networks trained using existing strategies.

Shreyas Singh, Aryan Garg, Kaushik Mitra

The recent advent of 3D Gaussian Splatting (3DGS) has revolutionized the 3D scene reconstruction space enabling high-fidelity novel view synthesis in real-time. However, with the exception of RawNeRF, all prior 3DGS and NeRF-based methods rely on 8-bit tone-mapped Low Dynamic Range (LDR) images for scene reconstruction. Such methods struggle to achieve accurate reconstructions in scenes that require a higher dynamic range. Examples include scenes captured in nighttime or poorly lit indoor spaces having a low signal-to-noise ratio, as well as daylight scenes with shadow regions exhibiting extreme contrast. Our proposed method HDRSplat tailors 3DGS to train directly on 14-bit linear raw images in near darkness which preserves the scenes' full dynamic range and content. Our key contributions are two-fold: Firstly, we propose a linear HDR space-suited loss that effectively extracts scene information from noisy dark regions and nearly saturated bright regions simultaneously, while also handling view-dependent colors without increasing the degree of spherical harmonics. Secondly, through careful rasterization tuning, we implicitly overcome the heavy reliance and sensitivity of 3DGS on point cloud initialization. This is critical for accurate reconstruction in regions of low texture, high depth of field, and low illumination. HDRSplat is the fastest method to date that does 14-bit (HDR) 3D scene reconstruction in $\le$15 minutes/scene ($\sim$30x faster than prior state-of-the-art RawNeRF). It also boasts the fastest inference speed at $\ge$120fps. We further demonstrate the applicability of our HDR scene reconstruction by showcasing various applications like synthetic defocus, dense depth map extraction, and post-capture control of exposure, tone-mapping and view-point.

Raman Jha, Adithya Lenka, Mani Ramanagopal et al.

In nighttime conditions, high noise levels and bright illumination sources degrade image quality, making low-light image enhancement challenging. Thermal images provide complementary information, offering richer textures and structural details. We propose RT-X Net, a cross-attention network that fuses RGB and thermal images for nighttime image enhancement. We leverage self-attention networks for feature extraction and a cross-attention mechanism for fusion to effectively integrate information from both modalities. To support research in this domain, we introduce the Visible-Thermal Image Enhancement Evaluation (V-TIEE) dataset, comprising 50 co-located visible and thermal images captured under diverse nighttime conditions. Extensive evaluations on the publicly available LLVIP dataset and our V-TIEE dataset demonstrate that RT-X Net outperforms state-of-the-art methods in low-light image enhancement. The code and the V-TIEE can be found here https://github.com/jhakrraman/rt-xnet.

Aryan Garg, Raghav Mallampali, Akshat Joshi et al.

Dual pixels contain disparity cues arising from the defocus blur. This disparity information is useful for many vision tasks ranging from autonomous driving to 3D creative realism. However, directly estimating disparity from dual pixels is less accurate. This work hypothesizes that distilling high-precision dark stereo knowledge, implicitly or explicitly, to efficient dual-pixel student networks enables faithful reconstructions. This dark knowledge distillation should also alleviate stereo-synchronization setup and calibration costs while dramatically increasing parameter and inference time efficiency. We collect the first and largest 3-view dual-pixel video dataset, dpMV, to validate our explicit dark knowledge distillation hypothesis. We show that these methods outperform purely monocular solutions, especially in challenging foreground-background separation regions using faithful guidance from dual pixels. Finally, we demonstrate an unconventional use case unlocked by dpMV and implicit dark knowledge distillation from an ensemble of teachers for Light Field (LF) video reconstruction. Our LF video reconstruction method is the fastest and most temporally consistent to date. It remains competitive in reconstruction fidelity while offering many other essential properties like high parameter efficiency, implicit disocclusion handling, zero-shot cross-dataset transfer, geometrically consistent inference on higher spatial-angular resolutions, and adaptive baseline control. All source code is available at the anonymous repository https://github.com/Aryan-Garg.

Bhargav Ghanekar, Salman Siddique Khan, Pranav Sharma et al.

Passive, compact, single-shot 3D sensing is useful in many application areas such as microscopy, medical imaging, surgical navigation, and autonomous driving where form factor, time, and power constraints can exist. Obtaining RGB-D scene information over a short imaging distance, in an ultra-compact form factor, and in a passive, snapshot manner is challenging. Dual-pixel (DP) sensors are a potential solution to achieve the same. DP sensors collect light rays from two different halves of the lens in two interleaved pixel arrays, thus capturing two slightly different views of the scene, like a stereo camera system. However, imaging with a DP sensor implies that the defocus blur size is directly proportional to the disparity seen between the views. This creates a trade-off between disparity estimation vs. deblurring accuracy. To improve this trade-off effect, we propose CADS (Coded Aperture Dual-Pixel Sensing), in which we use a coded aperture in the imaging lens along with a DP sensor. In our approach, we jointly learn an optimal coded pattern and the reconstruction algorithm in an end-to-end optimization setting. Our resulting CADS imaging system demonstrates improvement of >1.5dB PSNR in all-in-focus (AIF) estimates and 5-6% in depth estimation quality over naive DP sensing for a wide range of aperture settings. Furthermore, we build the proposed CADS prototypes for DSLR photography settings and in an endoscope and a dermoscope form factor. Our novel coded dual-pixel sensing approach demonstrates accurate RGB-D reconstruction results in simulations and real-world experiments in a passive, snapshot, and compact manner.

Vinayak Gupta, Manoj S, Mukund Varma T et al.

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.

Yuekun Dai, Dafeng Zhang, Xiaoming Li et al.

The increasing demand for computational photography and imaging on mobile platforms has led to the widespread development and integration of advanced image sensors with novel algorithms in camera systems. However, the scarcity of high-quality data for research and the rare opportunity for in-depth exchange of views from industry and academia constrain the development of mobile intelligent photography and imaging (MIPI). Building on the achievements of the previous MIPI Workshops held at ECCV 2022 and CVPR 2023, we introduce our third MIPI challenge including three tracks focusing on novel image sensors and imaging algorithms. In this paper, we summarize and review the Nighttime Flare Removal track on MIPI 2024. In total, 170 participants were successfully registered, and 14 teams submitted results in the final testing phase. The developed solutions in this challenge achieved state-of-the-art performance on Nighttime Flare Removal. More details of this challenge and the link to the dataset can be found at https://mipi-challenge.org/MIPI2024/.

Purvam Jain, Althaf M. Nazar, Salman S. Khan et al.

Existing eye trackers use cameras based on thick compound optical elements, necessitating the cameras to be placed at focusing distance from the eyes. This results in the overall bulk of wearable eye trackers, especially for augmented and virtual reality (AR/VR) headsets. We overcome this limitation by building a compact flat eye gaze tracker using mask-based lensless cameras. These cameras, in combination with co-designed lightweight deep neural network algorithm, can be placed in extreme close proximity to the eye, within the eyeglasses frame, resulting in ultra-flat and lightweight eye gaze tracker system. We collect a large dataset of near-eye lensless camera measurements along with their calibrated gaze directions for training the gaze tracking network. Through real and simulation experiments, we show that the proposed gaze tracking system performs on par with conventional lens-based trackers while maintaining a significantly flatter and more compact form-factor. Moreover, our gaze regressor boasts real-time (>125 fps) performance for gaze tracking.

Tharun Anand, Aryan Garg, Kaushik Mitra

Facial video editing has become increasingly important for content creators, enabling the manipulation of facial expressions and attributes. However, existing models encounter challenges such as poor editing quality, high computational costs and difficulties in preserving facial identity across diverse edits. Additionally, these models are often constrained to editing predefined facial attributes, limiting their flexibility to diverse editing prompts. To address these challenges, we propose a novel facial video editing framework that leverages the rich latent space of pre-trained text-to-image (T2I) diffusion models and fine-tune them specifically for facial video editing tasks. Our approach introduces a targeted fine-tuning scheme that enables high quality, localized, text-driven edits while ensuring identity preservation across video frames. Additionally, by using pre-trained T2I models during inference, our approach significantly reduces editing time by 80%, while maintaining temporal consistency throughout the video sequence. We evaluate the effectiveness of our approach through extensive testing across a wide range of challenging scenarios, including varying head poses, complex action sequences, and diverse facial expressions. Our method consistently outperforms existing techniques, demonstrating superior performance across a broad set of metrics and benchmarks.

Rakesh Raj Madavan, Akshat Kaimal, Badhrinarayanan K et al.

Lensless imaging offers a significant opportunity to develop ultra-compact cameras by removing the conventional bulky lens system. However, without a focusing element, the sensor's output is no longer a direct image but a complex multiplexed scene representation. Traditional methods have attempted to address this challenge by employing learnable inversions and refinement models, but these methods are primarily designed for 2D reconstruction and do not generalize well to 3D reconstruction. We introduce GANESH, a novel framework designed to enable simultaneous refinement and novel view synthesis from multi-view lensless images. Unlike existing methods that require scene-specific training, our approach supports on-the-fly inference without retraining on each scene. Moreover, our framework allows us to tune our model to specific scenes, enhancing the rendering and refinement quality. To facilitate research in this area, we also present the first multi-view lensless dataset, LenslessScenes. Extensive experiments demonstrate that our method outperforms current approaches in reconstruction accuracy and refinement quality. Code and video results are available at https://rakesh-123-cryp.github.io/Rakesh.github.io/

Gopi Raju Matta, Trisha Reddypalli, Vemunuri Divya Madhuri et al.

We introduce GeMS, a framework for 3D Gaussian Splatting (3DGS) designed to handle severely motion-blurred images. State-of-the-art deblurring methods for extreme blur, such as ExBluRF, as well as Gaussian Splatting-based approaches like Deblur-GS, typically assume access to sharp images for camera pose estimation and point cloud generation, an unrealistic assumption. Methods relying on COLMAP initialization, such as BAD-Gaussians, also fail due to unreliable feature correspondences under severe blur. To address these challenges, we propose GeMS, a 3DGS framework that reconstructs scenes directly from extremely blurred images. GeMS integrates: (1) VGGSfM, a deep learning-based Structure-from-Motion pipeline that estimates poses and generates point clouds directly from blurred inputs; (2) 3DGS-MCMC, which enables robust scene initialization by treating Gaussians as samples from a probability distribution, eliminating heuristic densification and pruning; and (3) joint optimization of camera trajectories and Gaussian parameters for stable reconstruction. While this pipeline produces strong results, inaccuracies may remain when all inputs are severely blurred. To mitigate this, we propose GeMS-E, which integrates a progressive refinement step using events: (4) Event-based Double Integral (EDI) deblurring restores sharper images that are then fed into GeMS, improving pose estimation, point cloud generation, and overall reconstruction. Both GeMS and GeMS-E achieve state-of-the-art performance on synthetic and real-world datasets. To our knowledge, this is the first framework to address extreme motion blur within 3DGS directly from severely blurred inputs.

Sai Sri Teja, Sreevidya Chintalapati, Vinayak Gupta et al.

Advances in 3D reconstruction using neural rendering have enabled high-quality 3D capture. However, they often fail when the input imagery is corrupted by motion blur, due to fast motion of the camera or the objects in the scene. This work advances neural rendering techniques in such scenarios by using single-photon avalanche diode (SPAD) arrays, an emerging sensing technology capable of sensing images at extremely high speeds. However, the use of SPADs presents its own set of unique challenges in the form of binary images, that are driven by stochastic photon arrivals. To address this, we introduce PhotonSplat, a framework designed to reconstruct 3D scenes directly from SPAD binary images, effectively navigating the noise vs. blur trade-off. Our approach incorporates a novel 3D spatial filtering technique to reduce noise in the renderings. The framework also supports both no-reference using generative priors and reference-based colorization from a single blurry image, enabling downstream applications such as segmentation, object detection and appearance editing tasks. Additionally, we extend our method to incorporate dynamic scene representations, making it suitable for scenes with moving objects. We further contribute PhotonScenes, a real-world multi-view dataset captured with the SPAD sensors.

Gopi Raju Matta, Reddypalli Trisha, Kaushik Mitra

Novel view synthesis has been greatly enhanced by the development of radiance field methods. The introduction of 3D Gaussian Splatting (3DGS) has effectively addressed key challenges, such as long training times and slow rendering speeds, typically associated with Neural Radiance Fields (NeRF), while maintaining high-quality reconstructions. In this work (BeSplat), we demonstrate the recovery of sharp radiance field (Gaussian splats) from a single motion-blurred image and its corresponding event stream. Our method jointly learns the scene representation via Gaussian Splatting and recovers the camera motion through Bezier SE(3) formulation effectively, minimizing discrepancies between synthesized and real-world measurements of both blurry image and corresponding event stream. We evaluate our approach on both synthetic and real datasets, showcasing its ability to render view-consistent, sharp images from the learned radiance field and the estimated camera trajectory. To the best of our knowledge, ours is the first work to address this highly challenging ill-posed problem in a Gaussian Splatting framework with the effective incorporation of temporal information captured using the event stream.

Gopi Raju Matta, Rahul Siddartha, Rongali Simhachala Venkata Girish et al.

Flare, an optical phenomenon resulting from unwanted scattering and reflections within a lens system, presents a significant challenge in imaging. The diverse patterns of flares, such as halos, streaks, color bleeding, and haze, complicate the flare removal process. Existing traditional and learning-based methods have exhibited limited efficacy due to their reliance on single-image approaches, where flare removal is highly ill-posed. We address this by framing flare removal as a multi-view image problem, taking advantage of the view-dependent nature of flare artifacts. This approach leverages information from neighboring views to recover details obscured by flare in individual images. Our proposed framework, GN-FR (Generalizable Neural Radiance Fields for Flare Removal), can render flare-free views from a sparse set of input images affected by lens flare and generalizes across different scenes in an unsupervised manner. GN-FR incorporates several modules within the Generalizable NeRF Transformer (GNT) framework: Flare-occupancy Mask Generation (FMG), View Sampler (VS), and Point Sampler (PS). To overcome the impracticality of capturing both flare-corrupted and flare-free data, we introduce a masking loss function that utilizes mask information in an unsupervised setting. Additionally, we present a 3D multi-view flare dataset, comprising 17 real flare scenes with 782 images, 80 real flare patterns, and their corresponding annotated flare-occupancy masks. To our knowledge, this is the first work to address flare removal within a Neural Radiance Fields (NeRF) framework.

Mohit Lamba, Atul Balaji, Kaushik Mitra

The ability to capture good quality images in the dark and near-zero lux conditions has been a long-standing pursuit of the computer vision community. The seminal work by Chen et al. [5] has especially caused renewed interest in this area, resulting in methods that build on top of their work in a bid to improve the reconstruction. However, for practical utility and deployment of low-light enhancement algorithms on edge devices such as embedded systems, surveillance cameras, autonomous robots and smartphones, the solution must respect additional constraints such as limited GPU memory and processing power. With this in mind, we propose a deep neural network architecture that aims to strike a balance between the network latency, memory utilization, model parameters, and reconstruction quality. The key idea is to forbid computations in the High-Resolution (HR) space and limit them to a Low-Resolution (LR) space. However, doing the bulk of computations in the LR space causes artifacts in the restored image. We thus propose Pack and UnPack operations, which allow us to effectively transit between the HR and LR spaces without incurring much artifacts in the restored image. We show that we can enhance a full resolution, 2848 x 4256, extremely dark single-image in the ballpark of 3 seconds even on a CPU. We achieve this with 2 - 7x fewer model parameters, 2 - 3x lower memory utilization, 5 - 20x speed up and yet maintain a competitive image reconstruction quality compared to the state-of-the-art algorithms.

Prasan Shedligeri, Anupama S, Kaushik Mitra

Several coded exposure techniques have been proposed for acquiring high frame rate videos at low bandwidth. Most recently, a Coded-2-Bucket camera has been proposed that can acquire two compressed measurements in a single exposure, unlike previously proposed coded exposure techniques, which can acquire only a single measurement. Although two measurements are better than one for an effective video recovery, we are yet unaware of the clear advantage of two measurements, either quantitatively or qualitatively. Here, we propose a unified learning-based framework to make such a qualitative and quantitative comparison between those which capture only a single coded image (Flutter Shutter, Pixel-wise coded exposure) and those that capture two measurements per exposure (C2B). Our learning-based framework consists of a shift-variant convolutional layer followed by a fully convolutional deep neural network. Our proposed unified framework achieves the state of the art reconstructions in all three sensing techniques. Further analysis shows that when most scene points are static, the C2B sensor has a significant advantage over acquiring a single pixel-wise coded measurement. However, when most scene points undergo motion, the C2B sensor has only a marginal benefit over the single pixel-wise coded exposure measurement.

Salman S. Khan, Varun Sundar, Vivek Boominathan et al.

Lensless imaging has emerged as a potential solution towards realizing ultra-miniature cameras by eschewing the bulky lens in a traditional camera. Without a focusing lens, the lensless cameras rely on computational algorithms to recover the scenes from multiplexed measurements. However, the current iterative-optimization-based reconstruction algorithms produce noisier and perceptually poorer images. In this work, we propose a non-iterative deep learning based reconstruction approach that results in orders of magnitude improvement in image quality for lensless reconstructions. Our approach, called $\textit{FlatNet}$, lays down a framework for reconstructing high-quality photorealistic images from mask-based lensless cameras, where the camera's forward model formulation is known. FlatNet consists of two stages: (1) an inversion stage that maps the measurement into a space of intermediate reconstruction by learning parameters within the forward model formulation, and (2) a perceptual enhancement stage that improves the perceptual quality of this intermediate reconstruction. These stages are trained together in an end-to-end manner. We show high-quality reconstructions by performing extensive experiments on real and challenging scenes using two different types of lensless prototypes: one which uses a separable forward model and another, which uses a more general non-separable cropped-convolution model. Our end-to-end approach is fast, produces photorealistic reconstructions, and is easy to adopt for other mask-based lensless cameras.

S Anupama, Prasan Shedligeri, Abhishek Pal et al.

Learning-based methods have enabled the recovery of a video sequence from a single motion-blurred image or a single coded exposure image. Recovering video from a single motion-blurred image is a very ill-posed problem and the recovered video usually has many artifacts. In addition to this, the direction of motion is lost and it results in motion ambiguity. However, it has the advantage of fully preserving the information in the static parts of the scene. The traditional coded exposure framework is better-posed but it only samples a fraction of the space-time volume, which is at best 50% of the space-time volume. Here, we propose to use the complementary information present in the fully-exposed (blurred) image along with the coded exposure image to recover a high fidelity video without any motion ambiguity. Our framework consists of a shared encoder followed by an attention module to selectively combine the spatial information from the fully-exposed image with the temporal information from the coded image, which is then super-resolved to recover a non-ambiguous high-quality video. The input to our algorithm is a fully-exposed and coded image pair. Such an acquisition system already exists in the form of a Coded-two-bucket (C2B) camera. We demonstrate that our proposed deep learning approach using blurred-coded image pair produces much better results than those from just a blurred image or just a coded image.

Yuqian Zhou, Michael Kwan, Kyle Tolentino et al.

This paper is the report of the first Under-Display Camera (UDC) image restoration challenge in conjunction with the RLQ workshop at ECCV 2020. The challenge is based on a newly-collected database of Under-Display Camera. The challenge tracks correspond to two types of display: a 4k Transparent OLED (T-OLED) and a phone Pentile OLED (P-OLED). Along with about 150 teams registered the challenge, eight and nine teams submitted the results during the testing phase for each track. The results in the paper are state-of-the-art restoration performance of Under-Display Camera Restoration. Datasets and paper are available at https://yzhouas.github.io/projects/UDC/udc.html.

Varun Sundar, Sumanth Hegde, Divya Kothandaraman et al.

Under Display Cameras present a promising opportunity for phone manufacturers to achieve bezel-free displays by positioning the camera behind semi-transparent OLED screens. Unfortunately, such imaging systems suffer from severe image degradation due to light attenuation and diffraction effects. In this work, we present Deep Atrous Guided Filter (DAGF), a two-stage, end-to-end approach for image restoration in UDC systems. A Low-Resolution Network first restores image quality at low-resolution, which is subsequently used by the Guided Filter Network as a filtering input to produce a high-resolution output. Besides the initial downsampling, our low-resolution network uses multiple, parallel atrous convolutions to preserve spatial resolution and emulates multi-scale processing. Our approach's ability to directly train on megapixel images results in significant performance improvement. We additionally propose a simple simulation scheme to pre-train our model and boost performance. Our overall framework ranks 2nd and 5th in the RLQ-TOD'20 UDC Challenge for POLED and TOLED displays, respectively.

Sharath M Shankaranarayana, Keerthi Ram, Kaushik Mitra et al.

One of the important parameters for the assessment of glaucoma is optic nerve head (ONH) evaluation, which usually involves depth estimation and subsequent optic disc and cup boundary extraction. Depth is usually obtained explicitly from imaging modalities like optical coherence tomography (OCT) and is very challenging to estimate depth from a single RGB image. To this end, we propose a novel method using adversarial network to predict depth map from a single image. The proposed depth estimation technique is trained and evaluated using individual retinal images from INSPIRE-stereo dataset. We obtain a very high average correlation coefficient of 0.92 upon five fold cross validation outperforming the state of the art. We then use the depth estimation process as a proxy task for joint optic disc and cup segmentation.

Honey Gupta, Kaushik Mitra

Guided super-resolution (GSR) of thermal images using visible range images is challenging because of the difference in the spectral-range between the images. This in turn means that there is significant texture-mismatch between the images, which manifests as blur and ghosting artifacts in the super-resolved thermal image. To tackle this, we propose a novel algorithm for GSR based on pyramidal edge-maps extracted from the visible image. Our proposed network has two sub-networks. The first sub-network super-resolves the low-resolution thermal image while the second obtains edge-maps from the visible image at a growing perceptual scale and integrates them into the super-resolution sub-network with the help of attention-based fusion. Extraction and integration of multi-level edges allows the super-resolution network to process texture-to-object level information progressively, enabling more straightforward identification of overlapping edges between the input images. Extensive experiments show that our model outperforms the state-of-the-art GSR methods, both quantitatively and qualitatively.

Pradyumna Chari, Anil Kumar Vadathya, Kaushik Mitra

Dual camera systems have assisted in the proliferation of various applications, such as optical zoom, low-light imaging and High Dynamic Range (HDR) imaging. In this work, we explore an optimal method for capturing the scene HDR and disparity map using dual camera setups. Hasinoff et al. (2010) have developed a noise optimal framework for HDR capture from a single camera. We generalize this to the dual camera set-up for estimating both HDR and disparity map. It may seem that dual camera systems can capture HDR in a shorter time. However, disparity estimation is a necessary step, which requires overlap among the images captured by the two cameras. This may lead to an increase in the capture time. To address this conflicting requirement, we propose a novel framework to find the optimal exposure and ISO sequence by minimizing the capture time under the constraints of an upper bound on the disparity error and a lower bound on the per-exposure SNR. We show that the resulting optimization problem is non-convex in general and propose an appropriate initialization technique. To obtain the HDR and disparity map from the optimal capture sequence, we propose a pipeline which alternates between estimating the camera ICRFs and the scene disparity map. We demonstrate that our optimal capture sequence leads to better results than other possible capture sequences. Our results are also close to those obtained by capturing the full stereo stack spanning the entire dynamic range. Finally, we present for the first time a stereo HDR dataset consisting of dense ISO and exposure stack captured from a smartphone dual camera. The dataset consists of 6 scenes, with an average of 142 exposure-ISO image sequence per scene.

Mohit Lamba, Kranthi Kumar, Kaushik Mitra

Light Field (LF) offers unique advantages such as post-capture refocusing and depth estimation, but low-light conditions limit these capabilities. To restore low-light LFs we should harness the geometric cues present in different LF views, which is not possible using single-frame low-light enhancement techniques. We, therefore, propose a deep neural network for Low-Light Light Field (L3F) restoration, which we refer to as L3Fnet. The proposed L3Fnet not only performs the necessary visual enhancement of each LF view but also preserves the epipolar geometry across views. We achieve this by adopting a two-stage architecture for L3Fnet. Stage-I looks at all the LF views to encode the LF geometry. This encoded information is then used in Stage-II to reconstruct each LF view. To facilitate learning-based techniques for low-light LF imaging, we collected a comprehensive LF dataset of various scenes. For each scene, we captured four LFs, one with near-optimal exposure and ISO settings and the others at different levels of low-light conditions varying from low to extreme low-light settings. The effectiveness of the proposed L3Fnet is supported by both visual and numerical comparisons on this dataset. To further analyze the performance of low-light reconstruction methods, we also propose an L3F-wild dataset that contains LF captured late at night with almost zero lux values. No ground truth is available in this dataset. To perform well on the L3F-wild dataset, any method must adapt to the light level of the captured scene. To do this we propose a novel pre-processing block that makes L3Fnet robust to various degrees of low-light conditions. Lastly, we show that L3Fnet can also be used for low-light enhancement of single-frame images, despite it being engineered for LF data. We do so by converting the single-frame DSLR image into a form suitable to L3Fnet, which we call as pseudo-LF.

Mohit Lamba, Kaushik Mitra

Images captured nowadays are of varying dimensions with smartphones and DSLR's allowing users to choose from a list of available image resolutions. It is therefore imperative for forensic algorithms such as resampling detection to scale well for images of varying dimensions. However, in our experiments, we observed that many state-of-the-art forensic algorithms are sensitive to image size and their performance quickly degenerates when operated on images of diverse dimensions despite re-training them using multiple image sizes. To handle this issue, we propose a novel pooling strategy called ITERATIVE POOLING. This pooling strategy can dynamically adjust input tensors in a discrete without much loss of information as in ROI Max-pooling. This pooling strategy can be used with any of the existing deep models and for demonstration purposes, we show its utility on Resnet-18 for the case of resampling detection a fundamental operation for any image sought of image manipulation. Compared to existing strategies and Max-pooling it gives up to 7-8% improvement on public datasets.

Honey Gupta, Kaushik Mitra

Depth estimation from a single underwater image is one of the most challenging problems and is highly ill-posed. Due to the absence of large generalized underwater depth datasets and the difficulty in obtaining ground truth depth-maps, supervised learning techniques such as direct depth regression cannot be used. In this paper, we propose an unsupervised method for depth estimation from a single underwater image taken `in the wild' by using haze as a cue for depth. Our approach is based on indirect depth-map estimation where we learn the mapping functions between unpaired RGB-D terrestrial images and arbitrary underwater images to estimate the required depth-map. We propose a method which is based on the principles of cycle-consistent learning and uses dense-block based auto-encoders as generator networks. We evaluate and compare our method both quantitatively and qualitatively on various underwater images with diverse attenuation and scattering conditions and show that our method produces state-of-the-art results for unsupervised depth estimation from a single underwater image.

Sharath M Shankaranarayana, Keerthi Ram, Kaushik Mitra et al.

Glaucoma is a serious ocular disorder for which the screening and diagnosis are carried out by the examination of the optic nerve head (ONH). The color fundus image (CFI) is the most common modality used for ocular screening. In CFI, the central r

Chaitanya Chinni, Abhishek Kulkarni, Dheeraj M. Pai et al.

Recent developments in the field of deep learning have motivated many researchers to apply these methods to problems in quantum information. Torlai and Melko first proposed a decoder for surface codes based on neural networks. Since then, many other researchers have applied neural networks to study a variety of problems in the context of decoding. An important development in this regard was due to Varsamopoulos et al. who proposed a two-step decoder using neural networks. Subsequent work of Maskara et al. used the same concept for decoding for various noise models. We propose a similar two-step neural decoder using inverse parity-check matrix for topological color codes. We show that it outperforms the state-of-the-art performance of non-neural decoders for independent Pauli errors noise model on a 2D hexagonal color code. Our final decoder is independent of the noise model and achieves a threshold of $10 \%$. Our result is comparable to the recent work on neural decoder for quantum error correction by Maskara et al.. It appears that our decoder has significant advantages with respect to training cost and complexity of the network for higher lengths when compared to that of Maskara et al.. Our proposed method can also be extended to arbitrary dimension and other stabilizer codes.

Anil Kumar Vadathya, Sharath Girish, Kaushik Mitra

Light field presents a rich way to represent the 3D world by capturing the spatio-angular dimensions of the visual signal. However, the popular way of capturing light field (LF) via a plenoptic camera presents spatio-angular resolution trade-off. Computational imaging techniques such as compressive light field and programmable coded aperture reconstruct full sensor resolution LF from coded projections obtained by multiplexing the incoming spatio-angular light field. Here, we present a unified learning framework that can reconstruct LF from a variety of multiplexing schemes with minimal number of coded images as input. We consider three light field capture schemes: heterodyne capture scheme with code placed near the sensor, coded aperture scheme with code at the camera aperture and finally the dual exposure scheme of capturing a focus-defocus pair where there is no explicit coding. Our algorithm consists of three stages 1) we recover the all-in-focus image from the coded image 2) we estimate the disparity maps for all the LF views from the coded image and the all-in-focus image, 3) we then render the LF by warping the all-in-focus image using disparity maps and refine it. For these three stages we propose three deep neural networks - ViewNet, DispairtyNet and RefineNet. Our reconstructions show that our learning algorithm achieves state-of-the-art results for all the three multiplexing schemes. Especially, our LF reconstructions from focus-defocus pair is comparable to other learning-based view synthesis approaches from multiple images. Thus, our work paves the way for capturing high-resolution LF (~ a megapixel) using conventional cameras such as DSLRs. Please check our supplementary materials $\href{https://docs.google.com/presentation/d/1Vr-F8ZskrSd63tvnLfJ2xmEXY6OBc1Rll3XeOAtc11I/}{online}$ to better appreciate the reconstructed light fields.

Prasan A Shedligeri, Kaushik Mitra

Event sensors output a stream of asynchronous brightness changes (called ``events'') at a very high temporal rate. Previous works on recovering the lost intensity information from the event sensor data have heavily relied on the event stream, which makes the reconstructed images non-photorealistic and also susceptible to noise in the event stream. We propose to reconstruct photorealistic intensity images from a hybrid sensor consisting of a low frame rate conventional camera, which has the scene texture information, along with the event sensor. To accomplish our task, we warp the low frame rate intensity images to temporally dense locations of the event data by estimating a spatially dense scene depth and temporally dense sensor ego-motion. The results obtained from our algorithm are more photorealistic compared to any of the previous state-of-the-art algorithms. We also demonstrate our algorithm's robustness to abrupt camera motion and noise in the event sensor data.

Lokesh Boominathan, Mayug Maniparambil, Honey Gupta et al.

Fourier Ptychography is a recently proposed imaging technique that yields high-resolution images by computationally transcending the diffraction blur of an optical system. At the crux of this method is the phase retrieval algorithm, which is used for computationally stitching together low-resolution images taken under varying illumination angles of a coherent light source. However, the traditional iterative phase retrieval technique relies heavily on the initialization and also need a good amount of overlap in the Fourier domain for the successively captured low-resolution images, thus increasing the acquisition time and data. We show that an auto-encoder based architecture can be adaptively trained for phase retrieval under both low overlap, where traditional techniques completely fail, and at higher levels of overlap. For the low overlap case we show that a supervised deep learning technique using an autoencoder generator is a good choice for solving the Fourier ptychography problem. And for the high overlap case, we show that optimizing the generator for reducing the forward model error is an appropriate choice. Using simulations for the challenging case of uncorrelated phase and amplitude, we show that our method outperforms many of the previously proposed Fourier ptychography phase retrieval techniques.

Stefanie Anna Baby, Bimal Vinod, Chaitanya Chinni et al.

Unlike conventional cameras which capture video at a fixed frame rate, Dynamic Vision Sensors (DVS) record only changes in pixel intensity values. The output of DVS is simply a stream of discrete ON/OFF events based on the polarity of change in its pixel values. DVS has many attractive features such as low power consumption, high temporal resolution, high dynamic range and fewer storage requirements. All these make DVS a very promising camera for potential applications in wearable platforms where power consumption is a major concern. In this paper, we explore the feasibility of using DVS for Human Activity Recognition (HAR). We propose to use the various slices (such as $x-y$, $x-t$, and $y-t$) of the DVS video as a feature map for HAR and denote them as Motion Maps. We show that fusing motion maps with Motion Boundary Histogram (MBH) give good performance on the benchmark DVS dataset as well as on a real DVS gesture dataset collected by us. Interestingly, the performance of DVS is comparable to that of conventional videos although DVS captures only sparse motion information.

Akshat Dave, Anil Kumar Vadathya, Ramana Subramanyam et al.

Signal reconstruction is a challenging aspect of computational imaging as it often involves solving ill-posed inverse problems. Recently, deep feed-forward neural networks have led to state-of-the-art results in solving various inverse imaging problems. However, being task specific, these networks have to be learned for each inverse problem. On the other hand, a more flexible approach would be to learn a deep generative model once and then use it as a signal prior for solving various inverse problems. We show that among the various state of the art deep generative models, autoregressive models are especially suitable for our purpose for the following reasons. First, they explicitly model the pixel level dependencies and hence are capable of reconstructing low-level details such as texture patterns and edges better. Second, they provide an explicit expression for the image prior which can then be used for MAP based inference along with the forward model. Third, they can model long range dependencies in images which make them ideal for handling global multiplexing as encountered in various compressive imaging systems. We demonstrate the efficacy of our proposed approach in solving three computational imaging problems: Single Pixel Camera (SPC), LiSens and FlatCam. For both real and simulated cases, we obtain better reconstructions than the state-of-the-art methods in terms of perceptual and quantitative metrics.

Anil Kumar Vadathya, Saikiran Cholleti, Gautham Ramajayam et al.

Light field imaging is a rich way of representing the 3D world around us. However, due to limited sensor resolution capturing light field data inherently poses spatio-angular resolution trade-off. In this paper, we propose a deep learning based solution to tackle the resolution trade-off. Specifically, we reconstruct full sensor resolution light field from a single coded image. We propose to do this in three stages 1) reconstruction of center view from the coded image 2) estimating disparity map from the coded image and center view 3) warping center view using the disparity to generate light field. We propose three neural networks for these stages. Our disparity estimation network is trained in an unsupervised manner alleviating the need for ground truth disparity. Our results demonstrate better recovery of parallax from the coded image. Also, we get better results than dictionary learning based approaches both qualitatively and quatitatively.

Prasan A Shedligeri, Sreyas Mohan, Kaushik Mitra

Inserting a patterned occluder at the aperture of a camera lens has been shown to improve the recovery of depth map and all-focus image compared to a fully open aperture. However, design of the aperture pattern plays a very critical role. Previous approaches for designing aperture codes make simple assumptions on image distributions to obtain metrics for evaluating aperture codes. However, real images may not follow those assumptions and hence the designed code may not be optimal for them. To address this drawback we propose a data driven approach for learning the optimal aperture pattern to recover depth map from a single coded image. We propose a two stage architecture where, in the first stage we simulate coded aperture images from a training dataset of all-focus images and depth maps and in the second stage we recover the depth map using a deep neural network. We demonstrate that our learned aperture code performs better than previously designed codes even on code design metrics proposed by previous approaches.

Akshat Dave, Anil Kumar Vadathya, Kaushik Mitra

Reconstruction of signals from compressively sensed measurements is an ill-posed problem. In this paper, we leverage the recurrent generative model, RIDE, as an image prior for compressive image reconstruction. Recurrent networks can model long-range dependencies in images and hence are suitable to handle global multiplexing in reconstruction from compressive imaging. We perform MAP inference with RIDE using back-propagation to the inputs and projected gradient method. We propose an entropy thresholding based approach for preserving texture in images well. Our approach shows superior reconstructions compared to recent global reconstruction approaches like D-AMP and TVAL3 on both simulated and real data.

Ryuichi Tadano, Adithya Kumar Pediredla, Kaushik Mitra et al.

Transient imaging or light-in-flight techniques capture the propagation of an ultra-short pulse of light through a scene, which in effect captures the optical impulse response of the scene. Recently, it has been shown that we can capture transient images using commercially available Time-of-Flight (ToF) systems such as Photonic Mixer Devices (PMD). In this paper, we propose `spatial phase-sweep', a technique that exploits the speed of light to increase the temporal resolution beyond the 100 picosecond limit imposed by current electronics. Spatial phase-sweep uses a linear array of light sources with spatial separation of about 3 mm between them, thereby resulting in a time shift of about 10 picoseconds, which translates into 100 Gfps of transient imaging in theory. We demonstrate a prototype and transient imaging results using spatial phase-sweep.

Kaushik Mitra, Oliver Cossairt, Ashok Veeraraghavan

Over the last decade, a number of Computational Imaging (CI) systems have been proposed for tasks such as motion deblurring, defocus deblurring and multispectral imaging. These techniques increase the amount of light reaching the sensor via multiplexing and then undo the deleterious effects of multiplexing by appropriate reconstruction algorithms. Given the widespread appeal and the considerable enthusiasm generated by these techniques, a detailed performance analysis of the benefits conferred by this approach is important. Unfortunately, a detailed analysis of CI has proven to be a challenging problem because performance depends equally on three components: (1) the optical multiplexing, (2) the noise characteristics of the sensor, and (3) the reconstruction algorithm. A few recent papers have performed analysis taking multiplexing and noise characteristics into account. However, analysis of CI systems under state-of-the-art reconstruction algorithms, most of which exploit signal prior models, has proven to be unwieldy. In this paper, we present a comprehensive analysis framework incorporating all three components. In order to perform this analysis, we model the signal priors using a Gaussian Mixture Model (GMM). A GMM prior confers two unique characteristics. Firstly, GMM satisfies the universal approximation property which says that any prior density function can be approximated to any fidelity using a GMM with appropriate number of mixtures. Secondly, a GMM prior lends itself to analytical tractability allowing us to derive simple expressions for the `minimum mean square error' (MMSE), which we use as a metric to characterize the performance of CI systems. We use our framework to analyze several previously proposed CI techniques, giving conclusive answer to the question: `How much performance gain is due to use of a signal prior and how much is due to multiplexing?