Search Results for author: Chensheng Peng

Found 11 papers, 5 papers with code

R3D2: Realistic 3D Asset Insertion via Diffusion for Autonomous Driving Simulation

no code implementations9 Jun 2025 William Ljungbergh, Bernardo Taveira, Wenzhao Zheng, Adam Tonderski, Chensheng Peng, Fredrik Kahl, Christoffer Petersson, Michael Felsberg, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan

This is achieved by training R3D2 on a novel dataset: 3DGS object assets are generated from in-the-wild AD data using an image-conditioned 3D generative model, and then synthetically placed into neural rendering-based virtual environments, allowing R3D2 to learn realistic integration.

3DGS Autonomous Driving +3

S2GO: Streaming Sparse Gaussian Occupancy Prediction

no code implementations5 Jun 2025 Jinhyung Park, Yihan Hu, Chensheng Peng, Wenzhao Zheng, Kris Kitani, Wei Zhan

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 or dense Gaussian-based 3D representations.

Denoising Prediction

A Lesson in Splats: Teacher-Guided Diffusion for 3D Gaussian Splats Generation with 2D Supervision

no code implementations1 Dec 2024 Chensheng Peng, Ido Sobol, Masayoshi Tomizuka, Kurt Keutzer, Chenfeng Xu, Or Litany

Additionally, our method is flexible, as it can learn from various 3D Gaussian Splat (3DGS) teachers with minimal adaptation; we demonstrate this by surpassing the performance of two different deterministic models as teachers, highlighting the potential generalizability of our framework.

3DGS Denoising

DeSiRe-GS: 4D Street Gaussians for Static-Dynamic Decomposition and Surface Reconstruction for Urban Driving Scenes

1 code implementation CVPR 2025 Chensheng Peng, Chengwei Zhang, Yixiao Wang, Chenfeng Xu, Yichen Xie, Wenzhao Zheng, Kurt Keutzer, Masayoshi Tomizuka, Wei Zhan

We present DeSiRe-GS, a self-supervised gaussian splatting representation, enabling effective static-dynamic decomposition and high-fidelity surface reconstruction in complex driving scenarios.

Autonomous Driving Surface Reconstruction

X-Drive: Cross-modality consistent multi-sensor data synthesis for driving scenarios

1 code implementation2 Nov 2024 Yichen Xie, Chenfeng Xu, Chensheng Peng, Shuqi Zhao, Nhat Ho, Alexander T. Pham, Mingyu Ding, Masayoshi Tomizuka, Wei Zhan

Recent advancements have exploited diffusion models for the synthesis of either LiDAR point clouds or camera image data in driving scenarios.

Denoising

CompGS: Unleashing 2D Compositionality for Compositional Text-to-3D via Dynamically Optimizing 3D Gaussians

no code implementations CVPR 2025 Chongjian Ge, Chenfeng Xu, Yuanfeng Ji, Chensheng Peng, Masayoshi Tomizuka, Ping Luo, Mingyu Ding, Varun Jampani, Wei Zhan

To achieve this goal, two core designs are proposed: (1) 3D Gaussians Initialization with 2D compositionality: We transfer the well-established 2D compositionality to initialize the Gaussian parameters on an entity-by-entity basis, ensuring both consistent 3D priors for each entity and reasonable interactions among multiple entities; (2) Dynamic Optimization: We propose a dynamic strategy to optimize 3D Gaussians using Score Distillation Sampling (SDS) loss.

3D Generation Scene Generation +1

DELFlow: Dense Efficient Learning of Scene Flow for Large-Scale Point Clouds

1 code implementation ICCV 2023 Chensheng Peng, Guangming Wang, Xian Wan Lo, Xinrui Wu, Chenfeng Xu, Masayoshi Tomizuka, Wei Zhan, Hesheng Wang

Previous methods rarely predict scene flow from the entire point clouds of the scene with one-time inference due to the memory inefficiency and heavy overhead from distance calculation and sorting involved in commonly used farthest point sampling, KNN, and ball query algorithms for local feature aggregation.

Scene Flow Estimation

Interactive Multi-scale Fusion of 2D and 3D Features for Multi-object Tracking

no code implementations30 Mar 2022 Guangming Wang, Chensheng Peng, Jinpeng Zhang, Hesheng Wang

Specifically, through multi-scale interactive query and fusion between pixel-level and point-level features, our method, can obtain more distinguishing features to improve the performance of multiple object tracking.

Autonomous Driving Multi-Object Tracking +1

Cannot find the paper you are looking for? You can Submit a new open access paper.