A key assumption of top-down human pose estimation approaches is their expectation of having a single person/instance present in the input bounding box. This often leads to failures in crowded scenes with occlusions. We propose a novel solution to overcome the limitations of this fundamental assumption. Our Multi-Instance Pose Network (MIPNet) allows for predicting multiple 2D pose instances within a given bounding box. We introduce a Multi-Instance Modulation Block (MIMB) that can adaptively modulate channel-wise feature responses for each instance and is parameter efficient. We demonstrate the efficacy of our approach by evaluating on COCO, CrowdPose, and OCHuman datasets. Specifically, we achieve 70.0 AP on CrowdPose and 42.5 AP on OCHuman test sets, a significant improvement of 2.4 AP and 6.5 AP over the prior art, respectively. When using ground truth bounding boxes for inference, MIP-Net achieves an improvement of 0.7 AP on COCO, 0.9 AP on CrowdPose, and 9.1 AP on OCHuman validation sets compared to HRNet. Interestingly, when fewer, high confidence bounding boxes are used, HRNet’s performance degrades (by 5 AP) on OCHuman, whereas MIPNet maintains a relatively stable performance (drop of 1 AP) for the same inputs.

We propose a novel computer vision system for reconstructing 3D body shapes from 2D images with the goal of producing highly accurate anthropomorphic measurements from a pair of images. We adopt a supervised learning approach that maps silhouette images to 3D body shapes via a convolutional neural network (CNN). We propose three key improvements over previous approaches: (1) Large-scale realistic synthetic data generation, including more realistic variations in segmentation noise and camera viewpoints. (2) A multi-task learning (MTL) approach to predicting multiple outputs such as shape, 3D joint locations, pose angles, and body volume. (3) A new network architecture that additionally takes known body measurements (e.g., height) and per-pixel segmentation confidence as input. Ablation studies show the improvement in accuracy due to the various components of our system. Results demonstrate that our system produces state-of-the-art results on body circumference errors. We also analyze the repeatability of our system in the presence of realistic camera, background, and pose variations. Our system achieves a vertex standard deviation of ~3mm on the [36] CAESAR dataset.

We present an unsupervised learning approach to re- cover 3D human pose from 2D skeletal joints extracted from a single image. Our method does not require any multi- view image data, 3D skeletons, correspondences between 2D-3D points, or use previously learned 3D priors during training. A lifting network accepts 2D landmarks as inputs and generates a corresponding 3D skeleton estimate. Dur- ing training, the recovered 3D skeleton is reprojected on random camera viewpoints to generate new ‘synthetic’ 2D poses. By lifting the synthetic 2D poses back to 3D and re-projecting them in the original camera view, we can de- fine self-consistency loss both in 3D and in 2D. The training can thus be self supervised by exploiting the geometric self- consistency of the lift-reproject-lift process. We show that self-consistency alone is not sufficient to generate realistic skeletons, however adding a 2D pose discriminator enables the lifter to output valid 3D poses. Additionally, to learn from 2D poses ‘in the wild’, we train an unsupervised 2D domain adapter network to allow for an expansion of 2D data. This improves results and demonstrates the useful- ness of 2D pose data for unsupervised 3D lifting. Results on Human3.6M dataset for 3D human pose estimation demon- strate that our approach improves upon the previous un- supervised methods by 30% and outperforms many weakly supervised approaches that explicitly use 3D data.

We present a task-specific approach to synthetic data generation. Our framework employs a trainable synthesizer network that is optimized to produce meaningful training samples by assessing the strengths and weaknesses of a `target' classifier. The synthesizer and target networks are trained in an adversarial manner wherein each network is updated with a goal to outdo the other. Additionally, we ensure the synthesizer generates realistic data by pairing it with a discriminator trained on real-world images. Further, to make the target classifier invariant to blending artefacts, we introduce these artefacts to background regions of the training images so the target does not over-fit to them. We demonstrate the efficacy of our approach by applying it to different target networks including a classification network on AffNIST [46], and two object detection networks (SSD, Faster-RCNN) on different datasets. On the AffNIST benchmark, our approach is able to surpass the baseline results with just half the training examples. On the VOC person detection benchmark, we show improvements of up to 2.7% as a result of our data augmentation. Similarly on the GMU detection benchmark, we report a performance boost of 3.5% in mAP over the baseline method, outperforming the previous state of the art approaches by as much as 7.5% in individual categories.

Recent work has made significant progress in improving spatial resolution for pixelwise labeling with Fully Convolutional Network (FCN) framework by employing Dilated/Atrous convolution, utilizing multi-scale features and refining boundaries. In this paper, we explore the impact of global contextual information in semantic segmentation by introducing the Context Encoding Module, which captures the semantic context of scenes and selectively highlights class-dependent featuremaps. The proposed Context Encoding Module significantly improves semantic segmentation results with only marginal extra computation cost over FCN. Our approach has achieved new state-of-the-art results 51.7% mIoU on PASCAL-Context, 85.9% mIoU on PASCAL VOC 2012. Our single model achieves a final score of 0.5567 on ADE20K test set, which surpasses the winning entry of COCO-Place Challenge 2017. In addition, we also explore how the Context Encoding Module can improve the feature representation of relatively shallow networks for the image classification on CIFAR-10 dataset. Our 14 layer network has achieved an error rate of 3.45%, which is comparable with state-of-the-art approaches with over 10Ã- more layers. The source code for the complete system are publicly available1.