317 citations · 585 across the 22 of their papers we have counts for
23 papers
4DNeX: Feed-Forward 4D Generative Modeling Made Easy
Zhaoxi Chen, Tianqi Liu, Long Zhuo +6
We present 4DNeX, the first feed-forward framework for generating 4D (i.e., dynamic 3D) scene representations from a single image. In contrast to existing methods that rely on comp…
Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
Hanxue Liang, Jiawei Ren, Ashkan Mirzaei +8
Recent advancements in static feed-forward scene reconstruction have demonstrated significant progress in high-quality novel view synthesis. However, these models often struggle wi…
L4GM: Large 4D Gaussian Reconstruction Model
Jiawei Ren, Kevin Xie, Ashkan Mirzaei +8
We present L4GM, the first 4D Large Reconstruction Model that produces animated objects from a single-view video input -- in a single feed-forward pass that takes only a second. Ke…
Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving
Shaoyuan Xie, Lingdong Kong, Wenwei Zhang +4
Recent advancements in bird's eye view (BEV) representations have shown remarkable promise for in-vehicle 3D perception. However, while these methods have achieved impressive resul…
Multi-Modal Data-Efficient 3D Scene Understanding for Autonomous Driving
Lingdong Kong, Xiang Xu, Jiawei Ren +5
Efficient data utilization is crucial for advancing 3D scene understanding in autonomous driving, where reliance on heavily human-annotated LiDAR point clouds challenges fully supe…
InsActor: Instruction-driven Physics-based Characters
Jiawei Ren, Mingyuan Zhang, Cunjun Yu +3
Generating animation of physics-based characters with intuitive control has long been a desirable task with numerous applications. However, generating physically simulated animatio…
FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing
Mingyuan Zhang, Huirong Li, Zhongang Cai +3
Text-driven motion generation has achieved substantial progress with the emergence of diffusion models. However, existing methods still struggle to generate complex motion sequence…
DreamGaussian4D: Generative 4D Gaussian Splatting
Jiawei Ren, Liang Pan, Jiaxiang Tang +4
4D content generation has achieved remarkable progress recently. However, existing methods suffer from long optimization times, a lack of motion controllability, and a low quality…
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
Jiaxiang Tang, Jiawei Ren, Hang Zhou +2
Recent advances in 3D content creation mostly leverage optimization-based 3D generation via score distillation sampling (SDS). Though promising results have been exhibited, these m…
DiffMimic: Efficient Motion Mimicking with Differentiable Physics
Jiawei Ren, Cunjun Yu, Siwei Chen +3
Motion mimicking is a foundational task in physics-based character animation. However, most existing motion mimicking methods are built upon reinforcement learning (RL) and suffer…
RoboBEV: Towards Robust Bird's Eye View Perception under Corruptions
Shaoyuan Xie, Lingdong Kong, Wenwei Zhang +4
The recent advances in camera-based bird's eye view (BEV) representation exhibit great potential for in-vehicle 3D perception. Despite the substantial progress achieved on standard…
Robo3D: Towards Robust and Reliable 3D Perception against Corruptions
Lingdong Kong, Youquan Liu, Xin Li +6
The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications. Existing large-scale 3D perception data…
OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation
Tong Wu, Jiarui Zhang, Xiao Fu +9
Recent advances in modeling 3D objects mostly rely on synthetic datasets due to the lack of large-scale realscanned 3D databases. To facilitate the development of 3D perception, re…
LaserMix for Semi-Supervised LiDAR Semantic Segmentation
Lingdong Kong, Jiawei Ren, Liang Pan +1
Densely annotating LiDAR point clouds is costly, which restrains the scalability of fully-supervised learning methods. In this work, we study the underexplored semi-supervised lear…
Sparse Mixture-of-Experts are Domain Generalizable Learners
Bo Li, Yifei Shen, Jingkang Yang +5
Human visual perception can easily generalize to out-of-distributed visual data, which is far beyond the capability of modern machine learning models. Domain generalization (DG) ai…
Balanced MSE for Imbalanced Visual Regression
Jiawei Ren, Mingyuan Zhang, Cunjun Yu +1
Data imbalance exists ubiquitously in real-world visual regressions, e.g., age estimation and pose estimation, hurting the model's generalizability and fairness. Thus, imbalanced r…
Benchmarking and Analyzing Point Cloud Classification under Corruptions
Jiawei Ren, Liang Pan, Ziwei Liu
3D perception, especially point cloud classification, has achieved substantial progress. However, in real-world deployment, point cloud corruptions are inevitable due to the scene…
Playing for 3D Human Recovery
Zhongang Cai, Mingyuan Zhang, Jiawei Ren +7
Image- and video-based 3D human recovery (i.e., pose and shape estimation) have achieved substantial progress. However, due to the prohibitive cost of motion capture, existing data…
HAVANA: Hierarchical and Variation-Normalized Autoencoder for Person Re-identification
Jiawei Ren, Xiao Ma, Chen Xu +2
Person Re-Identification (Re-ID) is of great importance to the many video surveillance systems. Learning discriminative features for Re-ID remains a challenge due to the large vari…
Balanced Activation for Long-tailed Visual Recognition
Jiawei Ren, Cunjun Yu, Zhongang Cai +1
Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distribu…
Leveraging Localization for Multi-camera Association
Zhongang Cai, Cunjun Yu, Junzhe Zhang +2
We present McAssoc, a deep learning approach to the as-sociation of detection bounding boxes in different views ofa multi-camera system. The vast majority of the academiahas been d…
Balanced Meta-Softmax for Long-Tailed Visual Recognition
Jiawei Ren, Cunjun Yu, Shunan Sheng +4
Deep classifiers have achieved great success in visual recognition. However, real-world data is long-tailed by nature, leading to the mismatch between training and testing distribu…
Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
Cunjun Yu, Xiao Ma, Jiawei Ren +2
Understanding crowd motion dynamics is critical to real-world applications, e.g., surveillance systems and autonomous driving. This is challenging because it requires effectively m…