Abstract: A method for multiple object tracking includes receiving, with a computing device, a point cloud dataset, detecting one or more objects in the point cloud dataset, each of the detected one or more objects defined by points of the point cloud dataset and a bounding box, querying one or more historical tracklets for historical tracklet states corresponding to each of the one or more detected objects, implementing a 4D encoding backbone comprising two branches: a first branch configured to compute per-point features for each of the one or more objects and the corresponding historical tracklet states, and a second branch configured to obtain 4D point features, concatenating the per-point features and the 4D point features, and predicting, with a decoder receiving the concatenated per-point features, current tracklet states for each of the one or more objects.

Abstract: Systems and methods are disclosed that perform global human and camera motion estimation using a motion diffusion model that is attached to a control branch. For instance, using a controlled motion denoiser that comprises the motion diffusion model and the control branch, global human motions and the corresponding camera motions from “in-the-wild” videos may be estimated. Initially, SLAM may be used to initialize the camera motion and a pose estimation model may be used to estimate the local human motion. Combining the two, embodiments of the present disclosure initialize the global human motion. Then, during optimization and using a COIN system that includes the controlled motion denoiser and/or using a COIN algorithm, embodiments of the present disclosure enforce the global human and camera motion to satisfy a two-dimensional (2D) projection on videos and the motion distribution from the motion diffusion model.

Abstract: A motion diffusion model may be pre-trained on motion data, and a scene-aware component (e.g., one or more layers of a neural network) may be connected and used to extract and inject a representation of scene information into the pre-trained motion diffusion model. For example, to predict orientations of joint waypoints along a path through a particular 3D scene, a scene-aware input channel that accepts a representation of the 3D structure of the scene may be added to a pre-trained motion diffusion model. To predict orientations of joint waypoints along a path that interacts with a 3D object in the 3D scene, a scene-aware input channel that accepts a representation of the 3D object and/or a surface thereof may be added to a pre-trained motion diffusion model. As such, the resulting scene-aware motion diffusion model(s) may be tuned on motion-scene data and used to generate human motion.

Abstract: In various examples, a timeline of text prompt(s) specifying any number of (e.g., sequential and/or simultaneous) actions may be specified or generated, and the timeline may be used to drive a diffusion model to generate compositional human motion that implements the arrangement of action(s) specified by the timeline. For example, at each denoising step, a pre-trained motion diffusion model may be used to denoise a motion segment corresponding to each text prompt independently of the others, and the resulting denoised motion segments may be temporally stitched, and/or spatially stitched based on body part labels associated with each text prompt. As such, the techniques described herein may be used to synthesize realistic motion that accurately reflects the semantics and timing of the text prompt(s) specified in the timeline.

Abstract: A method for multiple object tracking includes receiving, with a computing device, a point cloud dataset, detecting one or more objects in the point cloud dataset, each of the detected one or more objects defined by points of the point cloud dataset and a bounding box, querying one or more historical tracklets for historical tracklet states corresponding to each of the one or more detected objects, implementing a 4D encoding backbone comprising two branches: a first branch configured to compute per-point features for each of the one or more objects and the corresponding historical tracklet states, and a second branch configured to obtain 4D point features, concatenating the per-point features and the 4D point features, and predicting, with a decoder receiving the concatenated per-point features, current tracklet states for each of the one or more objects.

Abstract: In some embodiments, a model training system obtains a set of animation models. For each of the animation models, the model training system renders the animation model to generate a sequence of video frames containing a character using a set of rendering parameters and extracts joint points of the character from each frame of the sequence of video frames. The model training system further determines, for each frame of the sequence of video frames, whether a subset of the joint points are in contact with a ground plane in a three-dimensional space and generates contact labels for the subset of the joint points. The model training system trains a contact estimation model using training data containing the joint points extracted from the sequences of video frames and the generated contact labels. The contact estimation model can be used to refine a motion model for a character.

Abstract: In some embodiments, a model training system obtains a set of animation models. For each of the animation models, the model training system renders the animation model to generate a sequence of video frames containing a character using a set of rendering parameters and extracts joint points of the character from each frame of the sequence of video frames. The model training system further determines, for each frame of the sequence of video frames, whether a subset of the joint points are in contact with a ground plane in a three-dimensional space and generates contact labels for the subset of the joint points. The model training system trains a contact estimation model using training data containing the joint points extracted from the sequences of video frames and the generated contact labels. The contact estimation model can be used to refine a motion model for a character.

Abstract: In some embodiments, a motion model refinement system receives an input video depicting a human character and an initial motion model describing motions of individual joint points of the human character in a three-dimensional space. The motion model refinement system identifies foot joint points of the human character that are in contact with a ground plane using a trained contact estimation model. The motion model refinement system determines the ground plane based on the foot joint points and the initial motion model and constructs an optimization problem for refining the initial motion model. The optimization problem minimizes the difference between the refined motion model and the initial motion model under a set of plausibility constraints including constraints on the contact foot joint points and a time-dependent inertia tensor-based constraint. The motion model refinement system obtains the refined motion model by solving the optimization problem.

Abstract: In some embodiments, a motion model refinement system receives an input video depicting a human character and an initial motion model describing motions of individual joint points of the human character in a three-dimensional space. The motion model refinement system identifies foot joint points of the human character that are in contact with a ground plane using a trained contact estimation model. The motion model refinement system determines the ground plane based on the foot joint points and the initial motion model and constructs an optimization problem for refining the initial motion model. The optimization problem minimizes the difference between the refined motion model and the initial motion model under a set of plausibility constraints including constraints on the contact foot joint points and a time-dependent inertia tensor-based constraint. The motion model refinement system obtains the refined motion model by solving the optimization problem.