Computer vision systems that are deployed in safety-critical applications need to quantify their output uncertainty. We study regression from images to parameter values and here it is common to detect uncertainty by predicting probability distributions. In this context, we investigate the regression-by-classification paradigm which can represent multimodal distributions, without a prior assumption on the number of modes. Through experiments on a specifically designed synthetic dataset, we demonstrate that traditional loss functions lead to poor probability distribution estimates and severe overconfidence, in the absence of full ground truth distributions. In order to alleviate these issues, we propose hinge-Wasserstein – a simple improvement of the Wasserstein loss that reduces the penalty for weak secondary modes during training. This enables prediction of complex distributions with multiple modes, and allows training on datasets where full ground truth distributions are not available. In extensive experiments, we show that the proposed loss leads to substantially better uncertainty estimation on two challenging computer vision tasks: horizon line detection and stereo disparity estimation.

This paper deals with 3D reconstruction of seabirds which recently came into focus of environmental scientists as valuable bio-indicators for environmental change. Such 3D information is beneficial for analyzing the bird's behavior and physiological shape, for example by tracking motion, shape, and appearance changes. From a computer vision perspective birds are especially challenging due to their rapid and oftentimes non-rigid motions. We propose an approach to reconstruct the 3D pose and shape from monocular videos of a specific breed of seabird - the common murre. Our approach comprises a full pipeline of detection, tracking, segmentation, and temporally consistent 3D reconstruction. Additionally, we propose a temporal loss that extends current single-image 3D bird pose estimators to the temporal domain. Moreover, we provide a real-world dataset of 10000 frames of video observations on average capture nine birds simultaneously, comprising a large variety of motions and interactions, including a smaller test set with bird-specific keypoint labels. Using our temporal optimization, we achieve state-of-the-art performance for the challenging sequences in our dataset. 

For most applications, 2D keypoint detection works well and offers a simple and fast tool to analyse human movements. However, there remain many situations where even the best state-of-the-art algorithms reach their limits and fail to detect human keypoints correctly. Such situations may occur especially when individual body parts are occluded, twisted, or when the whole person is flipped. Especially when analysing injuries in alpine ski racing, such twisted and rotated body positions occur frequently. To improve the detection of keypoints for this application, we developed a novel method that refines keypoint estimates by rotating the input videos. We select the best rotation for every frame with a graph-based global solver. Thereby, we improve keypoint detection of an arbitrary pose estimation algorithm, in particular for 'hard' keypoints. In the current proof-of-concept study, we show that our approach outperforms standard keypoint detection results in all categories and in all metrics, in injury-related out-of-balance and fall situations by a large margin as well as previous methods, in performance and robustness. The Injury Ski II dataset was made publicly available, aiming to facilitate the investigation of sports accidents based on computer vision in the future.

A long-standing goal in the field of sensory substitution is enabling sound perception for deaf and hard of hearing (DHH) people by visualizing audio content. Different from existing models that translate to hand sign language, between speech and text, or text and images, we target immediate and low-level audio to video translation that applies to generic environment sounds as well as human speech. Since such a substitution is artificial, with-out labels for supervised learning, our core contribution is to build a mapping from audio to video that learns from unpaired examples via high-level constraints. For speech, we additionally disentangle content from style, such as gender and dialect. Qualitative and quantitative results, including a human study, demonstrate that our unpaired translation approach maintains important audio features in the generated video and that videos of faces and numbers are well suited for visualizing high-dimensional audio features that can be parsed by humans to match and distinguish between sounds and words. Project website: https://chunjinsong.github.io/audioviewer

Traditionally, monocular 3D human pose estimation employs a machine learning model to predict the most likely 3D pose for a given input image. However, a single image can be highly ambiguous and induces multiple plausible solutions for the 2D-3D lifting step, which results in overly confident 3D pose predictors. To this end, we propose DiffPose, a conditional diffusion model that predicts multiple hypotheses for a given input image. Compared to similar approaches, our diffusion model is straightforward and avoids intensive hyperparameter tuning, complex network structures, mode collapse, and unstable training. Moreover, we tackle the problem of over-simplification of the intermediate representation of the common two-step approaches which first estimate a distribution of 2D joint locations via joint-wise heatmaps and consecutively use their maximum argument for the 3D pose estimation step. Since such a simplification of the heatmaps removes valid information about possibly correct, though labeled unlikely, joint locations, we propose to represent the heatmaps as a set of 2D joint candidate samples. To extract information about the original distribution from these samples, we introduce our embedding transformer which conditions the diffusion model. Experimentally, we show that DiffPose improves upon the state of the art for multi-hypothesis pose estimation by 3-5% for simple poses and outperforms it by a large margin for highly ambiguous poses.

Generative adversarial networks (GANs) can now generate photorealistic images. However, how to best control the image content remains an open challenge. We introduce LatentKeypointGAN, a two-stage GAN internally conditioned on a set of keypoints and associated appearance embeddings providing control of the position and style of the generated objects and their respective parts. A major difficulty that we address is disentangling the image into spatial and appearance factors with little domain knowledge and supervision signals. We demonstrate in a user study and quantitative experiments that LatentKeypointGAN provides an interpretable latent space that can be used to re-arrange the generated images by re-positioning, adding, removing, and exchanging keypoint embeddings, such as generating portraits by combining the eyes, and mouth from different images. Notably, our method does not require labels as it is self-supervised and thereby applies to diverse application domains, such as editing portraits, indoor rooms, and full-body human poses. In addition, the explicit generation of keypoints and matching images enables a new, GAN-based method for unsupervised keypoint detection.