13 citations · 18 across the 16 of their papers we have counts for
16 papers
Instant NuRec: Feed-Forward 3D Gaussian Reconstruction for Driving Scene Simulation
NVIDIA, :, Jiahui Huang +14
3D simulation platforms are critical for autonomous driving because they enable end-to-end policy evaluation, thereby reducing development costs and improving safety. In recent yea…
World from Motion: Generative Dynamic Gaussian Reconstruction from Monocular Video
Liyuan Zhu, Shengyu Huang, Amrita Mazumdar +6
We present World from Motion, a method for generating freely renderable dynamic 3D Gaussian representations from monocular videos. Our approach conditions a video model on dense, p…
Depth Completion as Parameter-Efficient Test-Time Adaptation
Bingxin Ke, Qunjie Zhou, Jiahui Huang +5
We introduce CAPA, a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion, using sparse geometric cues. Unli…
RadarGen: Automotive Radar Point Cloud Generation from Cameras
Tomer Borreda, Fangqiang Ding, Sanja Fidler +2
We present RadarGen, a diffusion model for synthesizing realistic automotive radar point clouds from multi-view camera imagery. RadarGen adapts efficient image-latent diffusion to…
SimULi: Real-Time LiDAR and Camera Simulation with Unscented Transforms
Haithem Turki, Qi Wu, Xin Kang +5
Rigorous testing of autonomous robots, such as self-driving vehicles, is essential to ensure their safety in real-world deployments. This requires building high-fidelity simulators…
Rectified Point Flow: Generic Point Cloud Pose Estimation
Tao Sun, Liyuan Zhu, Shengyu Huang +2
We introduce Rectified Point Flow, a unified parameterization that formulates pairwise point cloud registration and multi-part shape assembly as a single conditional generative pro…
Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis
Bingxin Ke, Kevin Qu, Tianfu Wang +5
The success of deep learning in computer vision over the past decade has hinged on large labeled datasets and strong pretrained models. In data-scarce settings, the quality of thes…
ReStyle3D: Scene-Level Appearance Transfer with Semantic Correspondences
Liyuan Zhu, Shengqu Cai, Shengyu Huang +3
We introduce ReStyle3D, a novel framework for scene-level appearance transfer from a single style image to a real-world scene represented by multiple views. The method combines exp…
Video Depth without Video Models
Bingxin Ke, Dominik Narnhofer, Shengyu Huang +5
Video depth estimation lifts monocular video clips to 3D by inferring dense depth at every frame. Recent advances in single-image depth estimation, brought about by the rise of lar…
LoopSplat: Loop Closure by Registering 3D Gaussian Splats
Liyuan Zhu, Yue Li, Erik Sandström +3
Simultaneous Localization and Mapping (SLAM) based on 3D Gaussian Splats (3DGS) has recently shown promise towards more accurate, dense 3D scene maps. However, existing 3DGS-based…
Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environments
Liyuan Zhu, Shengyu Huang, Konrad Schindler +1
Research into dynamic 3D scene understanding has primarily focused on short-term change tracking from dense observations, while little attention has been paid to long-term changes…
Dynamic LiDAR Re-simulation using Compositional Neural Fields
Hanfeng Wu, Xingxing Zuo, Stefan Leutenegger +3
We introduce DyNFL, a novel neural field-based approach for high-fidelity re-simulation of LiDAR scans in dynamic driving scenes. DyNFL processes LiDAR measurements from dynamic en…
DGInStyle: Domain-Generalizable Semantic Segmentation with Image Diffusion Models and Stylized Semantic Control
Yuru Jia, Lukas Hoyer, Shengyu Huang +4
Large, pretrained latent diffusion models (LDMs) have demonstrated an extraordinary ability to generate creative content, specialize to user data through few-shot fine-tuning, and…
Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation
Bingxin Ke, Anton Obukhov, Shengyu Huang +3
Monocular depth estimation is a fundamental computer vision task. Recovering 3D depth from a single image is geometrically ill-posed and requires scene understanding, so it is not…
Nothing Stands Still: A Spatiotemporal Benchmark on 3D Point Cloud Registration Under Large Geometric and Temporal Change
Tao Sun, Yan Hao, Shengyu Huang +4
Building 3D geometric maps of man-made spaces is a well-established and active field that is fundamental to computer vision and robotics. However, considering the evolving nature o…
Skin the sheep not only once: Reusing Various Depth Datasets to Drive the Learning of Optical Flow
Sheng-Chi Huang, Wei-Chen Chiu
Optical flow estimation is crucial for various applications in vision and robotics. As the difficulty of collecting ground truth optical flow in real-world scenarios, most of the e…