The power of feedback.

By focusing on users' abilities rather than disabilities, designers can create interactive systems better matched to those abilities.

https://dl.acm.org/doi/pdf/10.1145/3148051

Ability-based design

This paper develops a unified framework for image-to-image translation based on conditional diffusion models and evaluates this framework on four challenging image-to-image translation tasks, namely colorization, inpainting, uncropping, and JPEG restoration. Our simple implementation of image-to-image diffusion models outperforms strong GAN and regression baselines on all tasks, without task-specific hyper-parameter tuning, architecture customization, or any auxiliary loss or sophisticated new techniques needed. We uncover the impact of an L2 vs. L1 loss in the denoising diffusion objective on sample diversity, and demonstrate the importance of self-attention in the neural architecture through empirical studies. Importantly, we advocate a unified evaluation protocol based on ImageNet, with human evaluation and sample quality scores (FID, Inception Score, Classification Accuracy of a pre-trained ResNet-50, and Perceptual Distance against original images). We expect this standardized evaluation protocol to play a role in advancing image-to-image translation research. Finally, we show that a generalist, multi-task diffusion model performs as well or better than task-specific specialist counterparts. Check out https://diffusion-palette.github.io/ for an overview of the results and code. 

/pdf/palette-image-to-image-diffusion-models-3ur4o5ew.pdf

Palette: Image-to-Image Diffusion Models

Results of image stitching can be perceptually divided into single-perspective and multiple-perspective. Compared to the multiple-perspective result, the single-perspective result excels in perspective consistency but suffers from projective distortion. In this paper, we propose two single-perspective warps for natural image stitching. The first one is a parametric warp, which is an incremental combination of the dual-feature-based as-projective-as-possible warp and the quasi-homography warp. The second one is a mesh-based warp, which is determined by optimizing a total energy function that simultaneously emphasizes different characteristics of the single-perspective warp, including alignment, distortion and saliency. A comprehensive evaluation demonstrates that the proposed warp outperforms some state-of-the-art warps in urban scenes, including APAP, AutoStitch, SPHP and GSP.

Single-Perspective Warps in Natural Image Stitching

Image/video stitching is a technology for solving the field of view (FOV) limitation of images/ videos. It stitches multiple overlapping images/videos to generate a wide-FOV image/video, and has been used in various fields such as sports broadcasting, video surveillance, street view, and entertainment. This survey reviews image/video stitching algorithms, with a particular focus on those developed in recent years. Image stitching first calculates the corresponding relationships between multiple overlapping images, deforms and aligns the matched images, and then blends the aligned images to generate a wide-FOV image. A seamless method is always adopted to eliminate such potential flaws as ghosting and blurring caused by parallax or objects moving across the overlapping regions. Video stitching is the further extension of image stitching. It usually stitches selected frames of original videos to generate a stitching template by performing image stitching algorithms, and the subsequent frames can then be stitched according to the template. Video stitching is more complicated with moving objects or violent camera movement, because these factors introduce jitter, shakiness, ghosting, and blurring. Foreground detection technique is usually combined into stitching to eliminate ghosting and blurring, while video stabilization algorithms are adopted to solve the jitter and shakiness. This paper further discusses panoramic stitching as a special-extension of image / video stitching. Panoramic stitching is currently the most widely used application in stitching. This survey reviews the latest image/video stitching methods, and introduces the fundamental principles/advantages/weaknesses of image/video stitching algorithms. Image/video stitching faces long-term challenges such as wide baseline, large parallax, and low-texture problem in the overlapping region. New technologies may present new opportunities to address these issues, such as deep learning-based semantic correspondence, and 3D image stitching. Finally, this survey discusses the challenges of image/video stitching and proposes potential solutions.

/pdf/a-survey-on-image-and-video-stitching-50cnocmjcu.pdf

A survey on image and video stitching

Synthetic datasets play a critical role in pre-training CNN models for optical flow, but they are painstaking to generate and hard to adapt to new applications. To automate the process, we present AutoFlow, a simple and effective method to render training data for optical flow that optimizes the performance of a model on a target dataset. AutoFlow takes a layered approach to render synthetic data, where the motion, shape, and appearance of each layer are controlled by learnable hyperparameters. Experimental results show that AutoFlow achieves state-of-the-art accuracy in pre-training both PWC-Net and RAFT. Our code and data are available at autoflow-google.github.io.

/pdf/autoflow-learning-a-better-training-set-for-optical-flow-18qks2n732.pdf

AutoFlow: Learning a Better Training Set for Optical Flow

Data is the driving force of machine learning, with the amount and quality of training data often being more important for the performance of a system than architecture and training details. But collecting, processing and annotating real data at scale is difficult, expensive, and frequently raises additional privacy, fairness and legal concerns. Synthetic data is a powerful tool with the potential to address these shortcomings: 1) it is cheap 2) supports rich ground-truth annotations 3) offers full control over data and 4) can circumvent or mitigate problems regarding bias, privacy and licensing. Unfortunately, software tools for effective data generation are less mature than those for architecture design and training, which leads to fragmented generation efforts. To address these problems we introduce Kubric, an open-source Python framework that interfaces with PyBullet and Blender to generate photo-realistic scenes, with rich annotations, and seamlessly scales to large jobs distributed over thousands of machines, and generating TBs of data. We demonstrate the effectiveness of Kubric by presenting a series of 13 different generated datasets for tasks ranging from studying 3D NeRF models to optical flow estimation. We release Kubric, the used assets, all of the generation code, as well as the rendered datasets for reuse and modification.

Kubric: A scalable dataset generator

Panorama creation is one of the most widely deployed techniques in computer vision. In addition to industry applications such as Google Street View, it is also used by millions of consumers in smartphones and other cameras. Traditionally, the problem is decomposed into three phases: registration, which picks a single transformation of each source image to align it to the other inputs, seam finding, which selects a source image for each pixel in the final result, and blending, which fixes minor visual artifacts [1, 2]. Here, we observe that the use of a single registration often leads to errors, especially in scenes with significant depth variation or object motion. We propose instead the use of multiple registrations, permitting regions of the image at different depths to be captured with greater accuracy. MRF inference techniques naturally extend to seam finding over multiple registrations, and we show here that their energy functions can be readily modified with new terms that discourage duplication and tearing, common problems that are exacerbated by the use of multiple registrations. Our techniques are closely related to layer-based stereo [3, 4], and move image stitching closer to explicit scene modeling. Experimental evidence demonstrates that our techniques often generate significantly better panoramas when there is substantial motion or parallax.

/pdf/robust-image-stitching-with-multiple-registrations-3vtvtomvox.pdf

Robust Image Stitching with Multiple Registrations

Important applications such as mobile computing require reducing the computational costs of neural network inference. Ideally, applications would specify their preferred tradeoff between accuracy and speed, and the network would optimize this end-to-end, using classification error to remove parts of the network. Increasing speed can be done either during training – e.g., pruning filters – or during inference – e.g., conditionally executing a subset of the layers. We propose a single end-to-end framework that can improve inference efficiency in both settings. We use a combination of batch activation loss and classification loss, and Gumbel reparameterization to learn network structure. We train end-to-end, and the same technique supports pruning as well as conditional computation. We obtain promising experimental results for ImageNet classification with ResNet (45–52% less computation).

Channel Selection Using Gumbel Softmax

We present a method for obtaining lab-quality measurements of pointing performance from unobtrusive observations of natural in situ interactions. Specifically, we have developed a set of user-independent classifiers for discriminating between deliberate, targeted mouse pointer movements and those movements that were affected by any extraneous factors. To develop and validate these classifiers, we developed logging software to unobtrusively record pointer trajectories as participants naturally interacted with their computers over the course of several weeks. Each participant also performed a set of pointing tasks in a formal study set-up. For each movement, we computed a set of measures capturing nuances of the trajectory and the speed, acceleration, and jerk profiles. Treating the observations from the formal study as positive examples of deliberate, targeted movements and the in situ observations as unlabeled data with an unknown mix of deliberate and distracted interactions, we used a recent advance in machine learning to develop the classifiers. Our results show that, on four distinct metrics, the data collected in-situ and filtered with our classifiers closely matches the results obtained from the formal experiment.

/pdf/accurate-measurements-of-pointing-performance-from-in-situ-4cgavif98g.pdf

Charles Herrmann

Papers

AutoFlow: Learning a Better Training Set for Optical Flow

Kubric: A scalable dataset generator

Robust Image Stitching with Multiple Registrations

Channel Selection Using Gumbel Softmax

Accurate measurements of pointing performance from in situ observations