24 citations · 27 across the 25 of their papers we have counts for
23 papers · 1 filter
CtrlWAM: Controllable World Action Models with Aligned Intent and Foresight
Chensheng Peng, Wenhao Ding, Ran Tian +9
World action models (WAMs) jointly predict actions (intent) and visual future (foresight). Standard training adds noise to recorded actions and video simultaneously, but such train…
RoboSTAR: Next-Scale Autoregressive Sign Language Translation for Humanoid Robots
Yujia Zeng, Chensheng Peng, Yuxin Chen +3
Sign-language interpretation in public communication relies on qualified professional interpreters and can be difficult to scale, motivating robotic signing as a complementary acce…
Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends
Jiuming Liu, Chaojun Ni, Mengmeng Liu +7
With rapid development of large language models and diffusion-based content generation, world modeling has attracted increasing research attention, benefiting various downstream do…
Teaching Video Generators to Remember: Eliciting Dynamic Memory for Out-of-Sight State Evolution
Tianshuo Xu, Yichen Xie, Depu Meng +5
Video world models should maintain evolving states when evidence is unobserved, yet current generators often freeze hidden states upon interruption. This is not simply a capacity p…
Rethinking Image-to-3D Generation with Sparse Queries: Efficiency, Capacity, and Input-View Bias
Zhiyuan Xu, Jiuming Liu, Yuxin Chen +3
We present SparseGen, a novel framework for efficient image-to-3D generation, which exhibits low input-view bias while being significantly faster. Unlike traditional approaches tha…
SpectralSplat: Appearance-Disentangled Feed-Forward Gaussian Splatting for Driving Scenes
Quentin Herau, Tianshuo Xu, Depu Meng +5
Feed-forward 3D Gaussian Splatting methods have achieved impressive reconstruction quality for autonomous driving scenes, yet they entangle scene geometry with transient appearance…
URoPE: Universal Relative Position Embedding across Geometric Spaces
Yichen Xie, Depu Meng, Chensheng Peng +4
Relative position embedding has become a standard mechanism for encoding positional information in Transformers. However, existing formulations are typically limited to a fixed geo…
Learning to Drive is a Free Gift: Large-Scale Label-Free Autonomy Pretraining from Unposed In-The-Wild Videos
Matthew Strong, Wei-Jer Chang, Quentin Herau +4
Ego-centric driving videos available online provide an abundant source of visual data for autonomous driving, yet their lack of annotations makes it difficult to learn representati…
UniQueR: Unified Query-based Feedforward 3D Reconstruction
Chensheng Peng, Quentin Herau, Jiezhi Yang +6
We present UniQueR, a unified query-based feedforward framework for efficient and accurate 3D reconstruction from unposed images. Existing feedforward models such as DUSt3R, VGGT,…
RAYNOVA: Scale-Temporal Autoregressive World Modeling in Ray Space
Yichen Xie, Chensheng Peng, Mazen Abdelfattah +6
World foundation models aim to simulate the evolution of the real world with physically plausible behavior. Unlike prior methods that handle spatial and temporal correlations separ…
DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splatting
Chenpeng Su, Wenhua Wu, Chensheng Peng +3
Urban scene reconstruction is critical for autonomous driving, enabling structured 3D representations for data synthesis and closed-loop testing. Supervised approaches rely on cost…
S2GO: Streaming Sparse Gaussian Occupancy Prediction
Jinhyung Park, Yihan Hu, Chensheng Peng +3
Despite the demonstrated efficiency and performance of sparse query-based representations for perception, state-of-the-art 3D occupancy prediction methods still rely on voxel-based…
R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation
William Ljungbergh, Bernardo Taveira, Wenzhao Zheng +8
Validating autonomous driving (AD) systems requires diverse and safety-critical testing, making photorealistic virtual environments essential. Traditional simulation platforms, whi…
A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision
Chensheng Peng, Ido Sobol, Masayoshi Tomizuka +3
We present a novel framework for training 3D image-conditioned diffusion models using only 2D supervision. Recovering 3D structure from 2D images is inherently ill-posed due to the…
X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios
Yichen Xie, Chenfeng Xu, Chensheng Peng +6
Recent advancements have exploited diffusion models for the synthesis of either LiDAR point clouds or camera image data in driving scenarios. Despite their success in modeling sing…
DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes
Chensheng Peng, Chengwei Zhang, Yixiao Wang +6
We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex drivi…
CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians
Chongjian Ge, Chenfeng Xu, Yuanfeng Ji +6
Recent breakthroughs in text-guided image generation have significantly advanced the field of 3D generation. While generating a single high-quality 3D object is now feasible, gener…
Optimizing Diffusion Models for Joint Trajectory Prediction and Controllable Generation
Yixiao Wang, Chen Tang, Lingfeng Sun +8
Diffusion models are promising for joint trajectory prediction and controllable generation in autonomous driving, but they face challenges of inefficient inference steps and high c…
PNAS-MOT: Multi-Modal Object Tracking with Pareto Neural Architecture Search
Chensheng Peng, Zhaoyu Zeng, Jinling Gao +5
Multiple object tracking is a critical task in autonomous driving. Existing works primarily focus on the heuristic design of neural networks to obtain high accuracy. As tracking ac…
DVLO: Deep Visual-LiDAR Odometry with Local-to-Global Feature Fusion and Bi-Directional Structure Alignment
Jiuming Liu, Dong Zhuo, Zhiheng Feng +4
Information inside visual and LiDAR data is well complementary derived from the fine-grained texture of images and massive geometric information in point clouds. However, it remain…
Q-SLAM: Quadric Representations for Monocular SLAM
Chensheng Peng, Chenfeng Xu, Yue Wang +6
In this paper, we reimagine volumetric representations through the lens of quadrics. We posit that rigid scene components can be effectively decomposed into quadric surfaces. Lever…
DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds
Chensheng Peng, Guangming Wang, Xian Wan Lo +5
Point clouds are naturally sparse, while image pixels are dense. The inconsistency limits feature fusion from both modalities for point-wise scene flow estimation. Previous methods…
Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking
Guangming Wang, Chensheng Peng, Jinpeng Zhang +1
Multiple object tracking (MOT) is a significant task in achieving autonomous driving. Traditional works attempt to complete this task, either based on point clouds (PC) collected b…