papers

Publications (23)

cs.CV2024

Multi-Track Timeline Control for Text-Driven 3D Human Motion Generation

Mathis Petrovich, Or Litany, Umar Iqbal +4

Recent advances in generative modeling have led to promising progress on synthesizing 3D human motion from text, with methods that can generate character animations from short prom…

cs.CV2019

Multiview Aggregation for Learning Category-Specific Shape Reconstruction

Srinath Sridhar, Davis Rempe, Julien Valentin +2

We investigate the problem of learning category-specific 3D shape reconstruction from a variable number of RGB views of previously unobserved object instances. Most approaches for…

cs.CV2023

NIFTY: Neural Object Interaction Fields for Guided Human Motion Synthesis

Nilesh Kulkarni, Davis Rempe, Kyle Genova +4

We address the problem of generating realistic 3D motions of humans interacting with objects in a scene. Our key idea is to create a neural interaction field attached to a specific…

cs.RO2026

MotionBricks: Scalable Real-Time Motions with Modular Latent Generative Model and Smart Primitives

Tingwu Wang, Olivier Dionne, Michael De Ruyter +13

Despite transformative advances in generative motion synthesis, real-time interactive motion control remains dominated by traditional techniques. In this work, we identify two key…

cs.CV2020

Contact and Human Dynamics from Monocular Video

Davis Rempe, Leonidas J. Guibas, Aaron Hertzmann +3

Existing deep models predict 2D and 3D kinematic poses from video that are approximately accurate, but contain visible errors that violate physical constraints, such as feet penetr…

cs.GR2026

ARDY: Autoregressive Diffusion with Hybrid Representation for Interactive Human Motion Generation

Kaifeng Zhao, Mathis Petrovich, Haotian Zhang +3

Generating realistic 3D human motions in real-time within interactive applications is key for animation, simulation, and humanoid robotics. While recent offline motion generation a…

cs.CV2022

Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior

Davis Rempe, Jonah Philion, Leonidas J. Guibas +2

Evaluating and improving planning for autonomous vehicles requires scalable generation of long-tail traffic scenarios. To be useful, these scenarios must be realistic and challengi…

cs.GR2025

GENMO: A GENeralist Model for Human MOtion

Jiefeng Li, Jinkun Cao, Haotian Zhang +4

Human motion modeling traditionally separates motion generation and estimation into distinct tasks with specialized models. Motion generation models focus on creating diverse, real…

cs.CV2024

CurveCloudNet: Processing Point Clouds with 1D Structure

Colton Stearns, Davis Rempe, Jiateng Liu +5

Modern depth sensors such as LiDAR operate by sweeping laser-beams across the scene, resulting in a point cloud with notable 1D curve-like structures. In this work, we introduce a…

cs.CV2021

HuMoR: 3D Human Motion Model for Robust Pose Estimation

Davis Rempe, Tolga Birdal, Aaron Hertzmann +3

We introduce HuMoR: a 3D Human Motion Model for Robust Estimation of temporal pose and shape. Though substantial progress has been made in estimating 3D human motion and shape from…

cs.CV2023

COPILOT: Human-Environment Collision Prediction and Localization from Egocentric Videos

Boxiao Pan, Bokui Shen, Davis Rempe +4

The ability to forecast human-environment collisions from egocentric observations is vital to enable collision avoidance in applications such as VR, AR, and wearable assistive robo…

cs.GR2026

HIL: Hybrid Imitation Learning of Diverse Parkour Skills from Videos

Jiashun Wang, Yifeng Jiang, Haotian Zhang +4

Data-driven methods leveraging deep reinforcement learning have become the dominant paradigm for developing controllers that enable physically simulated characters to produce natur…

cs.CV2022

SpOT: Spatiotemporal Modeling for 3D Object Tracking

Colton Stearns, Davis Rempe, Jie Li +5

3D multi-object tracking aims to uniquely and consistently identify all mobile entities through time. Despite the rich spatiotemporal information available in this setting, current…

cs.CV2019

Learning Generalizable Physical Dynamics of 3D Rigid Objects

Davis Rempe, Srinath Sridhar, He Wang +1

Humans have a remarkable ability to predict the effect of physical interactions on the dynamics of objects. Endowing machines with this ability would allow important applications i…

cs.RO2023

Language-Guided Traffic Simulation via Scene-Level Diffusion

Ziyuan Zhong, Davis Rempe, Yuxiao Chen +5

Realistic and controllable traffic simulation is a core capability that is necessary to accelerate autonomous vehicle (AV) development. However, current approaches for controlling…

cs.CV2023

Trace and Pace: Controllable Pedestrian Animation via Guided Trajectory Diffusion

Davis Rempe, Zhengyi Luo, Xue Bin Peng +5

We introduce a method for generating realistic pedestrian trajectories and full-body animations that can be controlled to meet user-defined goals. We draw on recent advances in gui…

cs.CV2024

Generating Human Interaction Motions in Scenes with Text Control

Hongwei Yi, Justus Thies, Michael J. Black +2

We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Previous text-to-motion methods focus on characters in isolation w…

cs.LG2021

A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries

Ali Kashefi, Davis Rempe, Leonidas J. Guibas

We present a novel deep learning framework for flow field predictions in irregular domains when the solution is a function of the geometry of either the domain or objects inside th…

cs.CV2026

Kimodo: Scaling Controllable Human Motion Generation

Davis Rempe, Mathis Petrovich, Ye Yuan +21

High-quality human motion data is becoming increasingly important for applications in robotics, simulation, and entertainment. Recent generative models offer a potential data sourc…

cs.RO2022

Guided Conditional Diffusion for Controllable Traffic Simulation

Ziyuan Zhong, Davis Rempe, Danfei Xu +5

Controllable and realistic traffic simulation is critical for developing and verifying autonomous vehicles. Typical heuristic-based traffic models offer flexible control to make ve…

cs.CV2020

CaSPR: Learning Canonical Spatiotemporal Point Cloud Representations

Davis Rempe, Tolga Birdal, Yongheng Zhao +3

We propose CaSPR, a method to learn object-centric Canonical Spatiotemporal Point Cloud Representations of dynamically moving or evolving objects. Our goal is to enable information…

cs.CV2024

COIN: Control-Inpainting Diffusion Prior for Human and Camera Motion Estimation

Jiefeng Li, Ye Yuan, Davis Rempe +5

Estimating global human motion from moving cameras is challenging due to the entanglement of human and camera motions. To mitigate the ambiguity, existing methods leverage learned…

cs.CV2020

Predicting the Physical Dynamics of Unseen 3D Objects

Davis Rempe, Srinath Sridhar, He Wang +1

Machines that can predict the effect of physical interactions on the dynamics of previously unseen object instances are important for creating better robots and interactive virtual…