9 citations · 33 across the 11 of their papers we have counts for
12 papers
DGGT: Feedforward 4D Reconstruction of Dynamic Driving Scenes using Unposed Images
Xiaoxue Chen, Ziyi Xiong, Yuantao Chen +11
Autonomous driving needs fast, scalable 4D reconstruction and re-simulation for training and evaluation, yet most methods for dynamic driving scenes still rely on per-scene optimiz…
InvRGB+L: Inverse Rendering of Complex Scenes with Unified Color and LiDAR Reflectance Modeling
Xiaoxue Chen, Bhargav Chandaka, Chih-Hao Lin +4
We present InvRGB+L, a novel inverse rendering model that reconstructs large, relightable, and dynamic scenes from a single RGB+LiDAR sequence. Conventional inverse graphics method…
RGM: Reconstructing High-fidelity 3D Car Assets with Relightable 3D-GS Generative Model from a Single Image
Xiaoxue Chen, Jv Zheng, Hao Huang +8
The generation of high-quality 3D car assets is essential for various applications, including video games, autonomous driving, and virtual reality. Current 3D generation methods ut…
NeRRF: 3D Reconstruction and View Synthesis for Transparent and Specular Objects with Neural Refractive-Reflective Fields
Xiaoxue Chen, Junchen Liu, Hao Zhao +2
Neural radiance fields (NeRF) have revolutionized the field of image-based view synthesis. However, NeRF uses straight rays and fails to deal with complicated light path changes ca…
DPF: Learning Dense Prediction Fields with Weak Supervision
Xiaoxue Chen, Yuhang Zheng, Yupeng Zheng +4
Nowadays, many visual scene understanding problems are addressed by dense prediction networks. But pixel-wise dense annotations are very expensive (e.g., for scene parsing) or impo…
VIMI: Vehicle-Infrastructure Multi-view Intermediate Fusion for Camera-based 3D Object Detection
Zhe Wang, Siqi Fan, Xiaoliang Huo +5
In autonomous driving, Vehicle-Infrastructure Cooperative 3D Object Detection (VIC3D) makes use of multi-view cameras from both vehicles and traffic infrastructure, providing a glo…
LODE: Locally Conditioned Eikonal Implicit Scene Completion from Sparse LiDAR
Pengfei Li, Ruowen Zhao, Yongliang Shi +4
Scene completion refers to obtaining dense scene representation from an incomplete perception of complex 3D scenes. This helps robots detect multi-scale obstacles and analyse objec…
TOIST: Task Oriented Instance Segmentation Transformer with Noun-Pronoun Distillation
Pengfei Li, Beiwen Tian, Yongliang Shi +4
Current referring expression comprehension algorithms can effectively detect or segment objects indicated by nouns, but how to understand verb reference is still under-explored. As…
When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning
Jianxiong Li, Xianyuan Zhan, Haoran Xu +3
In offline reinforcement learning (RL), one detrimental issue to policy learning is the error accumulation of deep Q function in out-of-distribution (OOD) areas. Unfortunately, exi…
Semi-supervised Implicit Scene Completion from Sparse LiDAR
Pengfei Li, Yongliang Shi, Tianyu Liu +3
Recent advances show that semi-supervised implicit representation learning can be achieved through physical constraints like Eikonal equations. However, this scheme has not yet bee…
Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing
Xiaoxue Chen, Tianyu Liu, Hao Zhao +2
Multi-task indoor scene understanding is widely considered as an intriguing formulation, as the affinity of different tasks may lead to improved performance. In this paper, we tack…
PQ-Transformer: Jointly Parsing 3D Objects and Layouts from Point Clouds
Xiaoxue Chen, Hao Zhao, Guyue Zhou +1
3D scene understanding from point clouds plays a vital role for various robotic applications. Unfortunately, current state-of-the-art methods use separate neural networks for diffe…