Diffusion models have shown incredible capabilities as generative models; indeed, they power the current state-of-the-art models on text-conditioned image generation such as Imagen and DALL-E 2. In this work we review, demystify, and unify the understanding of diffusion models across both variational and score-based perspectives. We first derive Variational Diffusion Models (VDM) as a special case of a Markovian Hierarchical Variational Autoencoder, where three key assumptions enable tractable computation and scalable optimization of the ELBO. We then prove that optimizing a VDM boils down to learning a neural network to predict one of three potential objectives: the original source input from any arbitrary noisification of it, the original source noise from any arbitrarily noisified input, or the score function of a noisified input at any arbitrary noise level. We then dive deeper into what it means to learn the score function, and connect the variational perspective of a diffusion model explicitly with the Score-based Generative Modeling perspective through Tweedie's Formula. Lastly, we cover how to learn a conditional distribution using diffusion models via guidance.
We present XMem, a video object segmentation architecture for long videos with unified feature memory stores inspired by the Atkinson-Shiffrin memory model. Prior work on video object segmentation typically only uses one type of feature memory. For videos longer than a minute, a single feature memory model tightly links memory consumption and accuracy. In contrast, following the Atkinson-Shiffrin model, we develop an architecture that incorporates multiple independent yet deeply-connected feature memory stores: a rapidly updated sensory memory, a high-resolution working memory, and a compact thus sustained long-term memory. Crucially, we develop a memory potentiation algorithm that routinely consolidates actively used working memory elements into the long-term memory, which avoids memory explosion and minimizes performance decay for long-term prediction. Combined with a new memory reading mechanism, XMem greatly exceeds state-of-the-art performance on long-video datasets while being on par with state-of-the-art methods (that do not work on long videos) on short-video datasets. Code is available at https://hkchengrex.github.io/XMem
Nonparametric based methods have recently shown promising results in reconstructing human bodies from monocular images while model-based methods can help correct these estimates and improve prediction. However, estimating model parameters from global image features may lead to noticeable misalignment between the estimated meshes and image evidence. To address this issue and leverage the best of both worlds, we propose a framework of three consecutive modules. A dense map prediction module explicitly establishes the dense UV correspondence between the image evidence and each part of the body model. The inverse kinematics module refines the key point prediction and generates a posed template mesh. Finally, a UV inpainting module relies on the corresponding feature, prediction and the posed template, and completes the predictions of occluded body shape. Our framework leverages the best of non-parametric and model-based methods and is also robust to partial occlusion. Experiments demonstrate that our framework outperforms existing 3D human estimation methods on multiple public benchmarks.
We consider a new problem of adapting a human mesh reconstruction model to out-of-domain streaming videos, where performance of existing SMPL-based models are significantly affected by the distribution shift represented by different camera parameters, bone lengths, backgrounds, and occlusions. We tackle this problem through online adaptation, gradually correcting the model bias during testing. There are two main challenges: First, the lack of 3D annotations increases the training difficulty and results in 3D ambiguities. Second, non-stationary data distribution makes it difficult to strike a balance between fitting regular frames and hard samples with severe occlusions or dramatic changes. To this end, we propose the Dynamic Bilevel Online Adaptation algorithm (DynaBOA). It first introduces the temporal constraints to compensate for the unavailable 3D annotations, and leverages a bilevel optimization procedure to address the conflicts between multi-objectives. DynaBOA provides additional 3D guidance by co-training with similar source examples retrieved efficiently despite the distribution shift. Furthermore, it can adaptively adjust the number of optimization steps on individual frames to fully fit hard samples and avoid overfitting regular frames. DynaBOA achieves state-of-the-art results on three out-of-domain human mesh reconstruction benchmarks.
3D human shape and pose estimation is the essential task for human motion analysis, which is widely used in many 3D applications. However, existing methods cannot simultaneously capture the relations at multiple levels, including spatial-temporal level and human joint level. Therefore they fail to make accurate predictions in some hard scenarios when there is cluttered background, occlusion, or extreme pose. To this end, we propose Multi-level Attention Encoder-Decoder Network (MAED), including a Spatial-Temporal Encoder (STE) and a Kinematic Topology Decoder (KTD) to model multi-level attentions in a unified framework. STE consists of a series of cascaded blocks based on Multi-Head Self-Attention, and each block uses two parallel branches to learn spatial and temporal attention respectively. Meanwhile, KTD aims at modeling the joint level attention. It regards pose estimation as a top-down hierarchical process similar to SMPL kinematic tree. With the training set of 3DPW, MAED outperforms previous state-of-the-art methods by 6.2, 7.2, and 2.4 mm of PA-MPJPE on the three widely used benchmarks 3DPW, MPI-INF-3DHP, and Human3.6M respectively. Our code is available at https://github.com/ziniuwan/maed.
Despite the recent progress, 3D multi-person pose estimation from monocular videos is still challenging due to the commonly encountered problem of missing information caused by occlusion, partially out-of-frame target persons, and inaccurate person detection. To tackle this problem, we propose a novel framework integrating graph convolutional networks (GCNs) and temporal convolutional networks (TCNs) to robustly estimate camera-centric multi-person 3D poses that do not require camera parameters. In particular, we introduce a human-joint GCN, which, unlike the existing GCN, is based on a directed graph that employs the 2D pose estimator's confidence scores to improve the pose estimation results. We also introduce a human-bone GCN, which models the bone connections and provides more information beyond human joints. The two GCNs work together to estimate the spatial frame-wise 3D poses and can make use of both visible joint and bone information in the target frame to estimate the occluded or missing human-part information. To further refine the 3D pose estimation, we use our temporal convolutional networks (TCNs) to enforce the temporal and human-dynamics constraints. We use a joint-TCN to estimate person-centric 3D poses across frames, and propose a velocity-TCN to estimate the speed of 3D joints to ensure the consistency of the 3D pose estimation in consecutive frames. Finally, to estimate the 3D human poses for multiple persons, we propose a root-TCN that estimates camera-centric 3D poses without requiring camera parameters. Quantitative and qualitative evaluations demonstrate the effectiveness of the proposed method.
We present a new method, called MEsh TRansfOrmer (METRO), to reconstruct 3D human pose and mesh vertices from a single image. Our method uses a transformer encoder to jointly model vertex-vertex and vertex-joint interactions, and outputs 3D joint coordinates and mesh vertices simultaneously. Compared to existing techniques that regress pose and shape parameters, METRO does not rely on any parametric mesh models like SMPL, thus it can be easily extended to other objects such as hands. We further relax the mesh topology and allow the transformer self-attention mechanism to freely attend between any two vertices, making it possible to learn non-local relationships among mesh vertices and joints. With the proposed masked vertex modeling, our method is more robust and effective in handling challenging situations like partial occlusions. METRO generates new state-of-the-art results for human mesh reconstruction on the public Human3.6M and 3DPW datasets. Moreover, we demonstrate the generalizability of METRO to 3D hand reconstruction in the wild, outperforming existing state-of-the-art methods on FreiHAND dataset. Code and pre-trained models are available at https://github.com/microsoft/MeshTransformer.
Heatmap representations have formed the basis of human pose estimation systems for many years, and their extension to 3D has been a fruitful line of recent research. This includes 2.5D volumetric heatmaps, whose X and Y axes correspond to image space and Z to metric depth around the subject. To obtain metric-scale predictions, 2.5D methods need a separate post-processing step to resolve scale ambiguity. Further, they cannot localize body joints outside the image boundaries, leading to incomplete estimates for truncated images. To address these limitations, we propose metric-scale truncation-robust (MeTRo) volumetric heatmaps, whose dimensions are all defined in metric 3D space, instead of being aligned with image space. This reinterpretation of heatmap dimensions allows us to directly estimate complete, metric-scale poses without test-time knowledge of distance or relying on anthropometric heuristics, such as bone lengths. To further demonstrate the utility our representation, we present a differentiable combination of our 3D metric-scale heatmaps with 2D image-space ones to estimate absolute 3D pose (our MeTRAbs architecture). We find that supervision via absolute pose loss is crucial for accurate non-root-relative localization. Using a ResNet-50 backbone without further learned layers, we obtain state-of-the-art results on Human3.6M, MPI-INF-3DHP and MuPoTS-3D. Our code will be made publicly available to facilitate further research.
We propose to estimate 3D human pose from multi-view images and a few IMUs attached at person's limbs. It operates by firstly detecting 2D poses from the two signals, and then lifting them to the 3D space. We present a geometric approach to reinforce the visual features of each pair of joints based on the IMUs. This notably improves 2D pose estimation accuracy especially when one joint is occluded. We call this approach Orientation Regularized Network (ORN). Then we lift the multi-view 2D poses to the 3D space by an Orientation Regularized Pictorial Structure Model (ORPSM) which jointly minimizes the projection error between the 3D and 2D poses, along with the discrepancy between the 3D pose and IMU orientations. The simple two-step approach reduces the error of the state-of-the-art by a large margin on a public dataset. Our code will be released at https://github.com/CHUNYUWANG/imu-human-pose-pytorch.
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE , https://github.com/mks0601/3DMPPE_POSENET_RELEASE.
Learning to capture long-range relations is fundamental to image/video recognition. Existing CNN models generally rely on increasing depth to model such relations which is highly inefficient. In this work, we propose the "double attention block", a novel component that aggregates and propagates informative global features from the entire spatio-temporal space of input images/videos, enabling subsequent convolution layers to access features from the entire space efficiently. The component is designed with a double attention mechanism in two steps, where the first step gathers features from the entire space into a compact set through second-order attention pooling and the second step adaptively selects and distributes features to each location via another attention. The proposed double attention block is easy to adopt and can be plugged into existing deep neural networks conveniently. We conduct extensive ablation studies and experiments on both image and video recognition tasks for evaluating its performance. On the image recognition task, a ResNet-50 equipped with our double attention blocks outperforms a much larger ResNet-152 architecture on ImageNet-1k dataset with over 40% less the number of parameters and less FLOPs. On the action recognition task, our proposed model achieves the state-of-the-art results on the Kinetics and UCF-101 datasets with significantly higher efficiency than recent works.
Recently, very deep convolutional neural networks (CNNs) have shown outstanding performance in object recognition and have also been the first choice for dense classification problems such as semantic segmentation. However, repeated subsampling operations like pooling or convolution striding in deep CNNs lead to a significant decrease in the initial image resolution. Here, we present RefineNet, a generic multi-path refinement network that explicitly exploits all the information available along the down-sampling process to enable high-resolution prediction using long-range residual connections. In this way, the deeper layers that capture high-level semantic features can be directly refined using fine-grained features from earlier convolutions. The individual components of RefineNet employ residual connections following the identity mapping mindset, which allows for effective end-to-end training. Further, we introduce chained residual pooling, which captures rich background context in an efficient manner. We carry out comprehensive experiments and set new state-of-the-art results on seven public datasets. In particular, we achieve an intersection-over-union score of 83.4 on the challenging PASCAL VOC 2012 dataset, which is the best reported result to date.
In this paper, we propose a pose grammar to tackle the problem of 3D human pose estimation. Our model directly takes 2D pose as input and learns a generalized 2D-3D mapping function. The proposed model consists of a base network which efficiently captures pose-aligned features and a hierarchy of Bi-directional RNNs (BRNN) on the top to explicitly incorporate a set of knowledge regarding human body configuration (i.e., kinematics, symmetry, motor coordination). The proposed model thus enforces high-level constraints over human poses. In learning, we develop a pose sample simulator to augment training samples in virtual camera views, which further improves our model generalizability. We validate our method on public 3D human pose benchmarks and propose a new evaluation protocol working on cross-view setting to verify the generalization capability of different methods. We empirically observe that most state-of-the-art methods encounter difficulty under such setting while our method can well handle such challenges.