skip to main content

This content will become publicly available on October 11, 2022

Title: Predicting Camera Viewpoint Improves Cross-dataset Generalization for 3D Human Pose Estimation
Monocular estimation of 3d human pose has attracted in- creased attention with the availability of large ground-truth motion capture datasets. However, the diversity of training data available is limited and it is not clear to what extent methods generalize outside the specific datasets they are trained on. In this work we carry out a systematic study of the diversity and biases present in specific datasets and its e↵ect on cross-dataset generalization across a compendium of 5 pose datasets. We specifically focus on systematic di↵erences in the distri- bution of camera viewpoints relative to a body-centered coordinate frame. Based on this observation, we propose an auxiliary task of predicting the camera viewpoint in addition to pose. We find that models trained to jointly predict viewpoint and pose systematically show significantly improved cross-dataset generalization.
; ;
Award ID(s):
Publication Date:
Journal Name:
IEEE International Conference on Computer Vision workshops
Sponsoring Org:
National Science Foundation
More Like this
  1. Automatic speech emotion recognition provides computers with critical context to enable user understanding. While methods trained and tested within the same dataset have been shown successful, they often fail when applied to unseen datasets. To address this, recent work has focused on adversarial methods to find more generalized representations of emotional speech. However, many of these methods have issues converging, and only involve datasets collected in laboratory conditions. In this paper, we introduce Adversarial Discriminative Domain Generalization (ADDoG), which follows an easier to train “meet in the middle“ approach. The model iteratively moves representations learned for each dataset closer tomore »one another, improving cross-dataset generalization. We also introduce Multiclass ADDoG, or MADDoG, which is able to extend the proposed method to more than two datasets, simultaneously. Our results show consistent convergence for the introduced methods, with significantly improved results when not using labels from the target dataset. We also show how, in most cases, ADDoG and MADDoG can be used to improve upon baseline state-of-the-art methods when target dataset labels are added and in-the-wild data are considered. Even though our experiments focus on cross-corpus speech emotion, these methods could be used to remove unwanted factors of variation in other settings.« less
  2. Recent volumetric 3D reconstruction methods can produce very accurate results, with plausible geometry even for unobserved surfaces. However, they face an undesirable trade-off when it comes to multi-view fusion. They can fuse all available view information by global averaging, thus losing fine detail, or they can heuristically cluster views for local fusion, thus restricting their ability to consider all views jointly. Our key insight is that greater detail can be retained without restricting view diversity by learning a view-fusion function conditioned on camera pose and image content. We propose to learn this multi-view fusion using a transformer. To this end,more »we introduce VoRTX, 1 an end-to-end volumetric 3D reconstruction network using transformers for wide-baseline, multi-view feature fusion. Our model is occlusion-aware, leveraging the transformer architecture to predict an initial, projective scene geometry estimate. This estimate is used to avoid back-projecting image features through surfaces into occluded regions. We train our model on ScanNet and show that it produces better reconstructions than state-of-the-art methods. We also demonstrate generalization without any fine-tuning, outperforming the same state-of-the-art methods on two other datasets, TUM-RGBD and ICL-NUIM.« less
  3. Monocular depth predictors are typically trained on large-scale training sets which are naturally biased w.r.t the distribution of camera poses. As a result, trained predic- tors fail to make reliable depth predictions for testing exam- ples captured under uncommon camera poses. To address this issue, we propose two novel techniques that exploit the camera pose during training and prediction. First, we in- troduce a simple perspective-aware data augmentation that synthesizes new training examples with more diverse views by perturbing the existing ones in a geometrically consis- tent manner. Second, we propose a conditional model that exploits the per-image camera posemore »as prior knowledge by encoding it as a part of the input. We show that jointly ap- plying the two methods improves depth prediction on im- ages captured under uncommon and even never-before-seen camera poses. We show that our methods improve perfor- mance when applied to a range of different predictor ar- chitectures. Lastly, we show that explicitly encoding the camera pose distribution improves the generalization per- formance of a synthetically trained depth predictor when evaluated on real images.« less
  4. Deep learning approaches currently achieve the state-of-the-art results on camera-based vital signs measurement. One of the main challenges with using neural models for these applications is the lack of sufficiently large and diverse datasets. Limited data increases the chances of overfitting models to the available data which in turn can harm generalization. In this paper, we show that the generalizability of imaging photoplethysmography models can be improved by augmenting the training set with "magnified" videos. These augmentations are specifically designed to reveal useful features for recovering the photoplethysmogram. We show that using augmentations of this form is more effective atmore »improving model robustness than other commonly used data augmentation approaches. We show better within-dataset and especially cross-dataset performance with our proposed data augmentation approach on three publicly available datasets.« less
  5. Interest in physical therapy and individual exercises such as yoga/dance has increased alongside the well-being trend, and people globally enjoy such exercises at home/office via video streaming platforms. However, such exercises are hard to follow without expert guidance. Even if experts can help, it is almost impossible to give personalized feedback to every trainee remotely. Thus, automated pose correction systems are required more than ever, and we introduce a new captioning dataset named FixMyPose to address this need. We collect natural language descriptions of correcting a “current” pose to look like a “target” pose. To support a multilingual setup, wemore »collect descriptions in both English and Hindi. The collected descriptions have interesting linguistic properties such as egocentric relations to the environment objects, analogous references, etc., requiring an understanding of spatial relations and commonsense knowledge about postures. Further, to avoid ML biases, we maintain a balance across characters with diverse demographics, who perform a variety of movements in several interior environments (e.g., homes, offices). From our FixMyPose dataset, we introduce two tasks: the pose-correctional-captioning task and its reverse, the target-pose-retrieval task. During the correctional-captioning task, models must generate the descriptions of how to move from the current to the target pose image, whereas in the retrieval task, models should select the correct target pose given the initial pose and the correctional description. We present strong cross-attention baseline models (uni/multimodal, RL, multilingual) and also show that our baselines are competitive with other models when evaluated on other image-difference datasets. We also propose new task-specific metrics (object-match, body-part-match, direction-match) and conduct human evaluation for more reliable evaluation, and we demonstrate a large human-model performance gap suggesting room for promising future work. Finally, to verify the sim-to-real transfer of our FixMyPose dataset, we collect a set of real images and show promising performance on these images. Data and code are available:« less