ReBotNet: Fast Real-time Video Enhancement

Most video restoration networks are slow, have high computational load, and can't be used for real-time video enhancement. In this work, we design an efficient and fast framework to perform real-time video enhancement for practical use-cases like live video calls and video streams. Our proposed method, called Recurrent Bottleneck Mixer Network (ReBotNet), employs a dual-branch framework. The first branch learns spatio-temporal features by tokenizing the input frames along the spatial and temporal dimensions using a ConvNext-based encoder and processing these abstract tokens using a bottleneck mixer. To further improve temporal consistency, the second branch employs a mixer directly on tokens extracted from individual frames. A common decoder then merges the features form the two branches to predict the enhanced frame. In addition, we propose a recurrent training approach where the last frame's prediction is leveraged to efficiently enhance the current frame while improving temporal consistency. To evaluate our method, we curate two new datasets that emulate real-world video call and streaming scenarios, and show extensive results on multiple datasets where ReBotNet outperforms existing approaches with lower computations, reduced memory requirements, and faster inference time.

A View Independent Classification Framework for Yoga Postures

Yoga is a globally acclaimed and widely recommended practice for a healthy living. Maintaining correct posture while performing a Yogasana is of utmost importance. In this work, we employ transfer learning from Human Pose Estimation models for extracting 136 key-points spread all over the body to train a Random Forest classifier which is used for estimation of the Yogasanas. The results are evaluated on an in-house collected extensive yoga video database of 51 subjects recorded from 4 different camera angles. We propose a 3 step scheme for evaluating the generalizability of a Yoga classifier by testing it on 1) unseen frames, 2) unseen subjects, and 3) unseen camera angles. We argue that for most of the applications, validation accuracies on unseen subjects and unseen camera angles would be most important. We empirically analyze over three public datasets, the advantage of transfer learning and the possibilities of target leakage. We further demonstrate that the classification accuracies critically depend on the cross validation method employed and can often be misleading. To promote further research, we have made key-points dataset and code publicly available.

Defocus Map Estimation and Deblurring from a Single Dual-Pixel Image

We present a method that takes as input a single dual-pixel image, and simultaneously estimates the image's defocus map -- the amount of defocus blur at each pixel -- and recovers an all-in-focus image. Our method is inspired from recent works that leverage the dual-pixel sensors available in many consumer cameras to assist with autofocus, and use them for recovery of defocus maps or all-in-focus images. These prior works have solved the two recovery problems independently of each other, and often require large labeled datasets for supervised training. By contrast, we show that it is beneficial to treat these two closely-connected problems simultaneously. To this end, we set up an optimization problem that, by carefully modeling the optics of dual-pixel images, jointly solves both problems. We use data captured with a consumer smartphone camera to demonstrate that, after a one-time calibration step, our approach improves upon prior works for both defocus map estimation and blur removal, despite being entirely unsupervised.

Zoom-to-Inpaint: Image Inpainting with High Frequency Details

Although deep learning has enabled a huge leap forward in image inpainting, current methods are often unable to synthesize realistic high-frequency details. In this paper, we propose applying super resolution to coarsely reconstructed outputs, refining them at high resolution, and then downscaling the output to the original resolution. By introducing high-resolution images to the refinement network, our framework is able to reconstruct finer details that are usually smoothed out due to spectral bias - the tendency of neural networks to reconstruct low frequencies better than high frequencies. To assist training the refinement network on large upscaled holes, we propose a progressive learning technique in which the size of the missing regions increases as training progresses. Our zoom-in, refine and zoom-out strategy, combined with high-resolution supervision and progressive learning, constitutes a framework-agnostic approach for enhancing high-frequency details that can be applied to other inpainting methods. We provide qualitative and quantitative evaluations along with an ablation analysis to show the effectiveness of our approach, which outperforms state-of-the-art inpainting methods.

Single-Image Lens Flare Removal

Lens flare is a common artifact in photographs occurring when the camera is pointed at a strong light source. It is caused by either multiple reflections within the lens or scattering due to scratches or dust on the lens, and may appear in a wide variety of patterns: halos, streaks, color bleeding, haze, etc. The diversity in its appearance makes flare removal extremely challenging. Existing software methods make strong assumptions about the artifacts' geometry or brightness, and thus only handle a small subset of flares. We take a principled approach to explicitly model the optical causes of flare, which leads to a novel semi-synthetic pipeline for generating flare-corrupted images from both empirical and wave-optics-simulated lens flares. Using the semi-synthetic data generated by this pipeline, we build a neural network to remove lens flare. Experiments show that our model generalizes well to real lens flares captured by different devices, and outperforms start-of-the-art methods by 3dB in PSNR.

Learned Dual-View Reflection Removal

Traditional reflection removal algorithms either use a single image as input, which suffers from intrinsic ambiguities, or use multiple images from a moving camera, which is inconvenient for users. We instead propose a learning-based dereflection algorithm that uses stereo images as input. This is an effective trade-off between the two extremes: the parallax between two views provides cues to remove reflections, and two views are easy to capture due to the adoption of stereo cameras in smartphones. Our model consists of a learning-based reflection-invariant flow model for dual-view registration, and a learned synthesis model for combining aligned image pairs. Because no dataset for dual-view reflection removal exists, we render a synthetic dataset of dual-views with and without reflections for use in training. Our evaluation on an additional real-world dataset of stereo pairs shows that our algorithm outperforms existing single-image and multi-image dereflection approaches.

Learning to Autofocus

Autofocus is an important task for digital cameras, yet current approaches often exhibit poor performance. We propose a learning-based approach to this problem, and provide a realistic dataset of sufficient size for effective learning. Our dataset is labeled with per-pixel depths obtained from multi-view stereo, following "Learning single camera depth estimation using dual-pixels". Using this dataset, we apply modern deep classification models and an ordinal regression loss to obtain an efficient learning-based autofocus technique. We demonstrate that our approach provides a significant improvement compared with previous learned and non-learned methods: our model reduces the mean absolute error by a factor of 3.6 over the best comparable baseline algorithm. Our dataset and code are publicly available.

Du$^2$Net: Learning Depth Estimation from Dual-Cameras and Dual-Pixels

Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges. We present a novel approach based on neural networks for depth estimation that combines stereo from dual cameras with stereo from a dual-pixel sensor, which is increasingly common on consumer cameras. Our network uses a novel architecture to fuse these two sources of information and can overcome the above-mentioned limitations of pure binocular stereo matching. Our method provides a dense depth map with sharp edges, which is crucial for computational photography applications like synthetic shallow-depth-of-field or 3D Photos. Additionally, we avoid the inherent ambiguity due to the aperture problem in stereo cameras by designing the stereo baseline to be orthogonal to the dual-pixel baseline. We present experiments and comparisons with state-of-the-art approaches to show that our method offers a substantial improvement over previous works.

Learning Single Camera Depth Estimation using Dual-Pixels

Deep learning techniques have enabled rapid progress in monocular depth estimation, but their quality is limited by the ill-posed nature of the problem and the scarcity of high quality datasets. We estimate depth from a single camera by leveraging the dual-pixel auto-focus hardware that is increasingly common on modern camera sensors. Classic stereo algorithms and prior learning-based depth estimation techniques under-perform when applied on this dual-pixel data, the former due to too-strong assumptions about RGB image matching, and the latter due to a lack of understanding of the optics of dual-pixel image formation. To allow learning based methods to work well on dual-pixel imagery, we identify an inherent ambiguity in the depth estimated from dual-pixel cues, and develop an approach to estimate depth up to this ambiguity. Using our approach, existing monocular depth estimation techniques can be effectively applied to dual-pixel data, and much smaller models can be constructed that still infer high quality depth. To demonstrate this, we capture a large dataset of in-the-wild 5-viewpoint RGB images paired with corresponding dual-pixel data, and show how view supervision with this data can be used to learn depth up to the unknown ambiguities. On our new task, our model is 30% more accurate than any prior work on learning-based monocular or stereoscopic depth estimation.