9 citations · 47 across the 24 of their papers we have counts for
24 papers
Adaptive Surface Normal Constraint for Geometric Estimation from Monocular Images
Xiaoxiao Long, Yuhang Zheng, Yupeng Zheng +6
We introduce a novel approach to learn geometries such as depth and surface normal from images while incorporating geometric context. The difficulty of reliably capturing geometric…
Latency-aware Road Anomaly Segmentation in Videos: A Photorealistic Dataset and New Metrics
Beiwen Tian, Huan-ang Gao, Leiyao Cui +6
In the past several years, road anomaly segmentation is actively explored in the academia and drawing growing attention in the industry. The rationale behind is straightforward: if…
SlimmeRF: Slimmable Radiance Fields
Shiran Yuan, Hao Zhao
Neural Radiance Field (NeRF) and its variants have recently emerged as successful methods for novel view synthesis and 3D scene reconstruction. However, most current NeRF models ei…
ASSIST: Interactive Scene Nodes for Scalable and Realistic Indoor Simulation
Zhide Zhong, Jiakai Cao, Songen Gu +6
We present ASSIST, an object-wise neural radiance field as a panoptic representation for compositional and realistic simulation. Central to our approach is a novel scene node data…
PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection
Qiang Zhou, Weize Li, Lihan Jiang +4
Object anomaly detection is an important problem in the field of machine vision and has seen remarkable progress recently. However, two significant challenges hinder its research a…
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…
3D Implicit Transporter for Temporally Consistent Keypoint Discovery
Chengliang Zhong, Yuhang Zheng, Yupeng Zheng +9
Keypoint-based representation has proven advantageous in various visual and robotic tasks. However, the existing 2D and 3D methods for detecting keypoints mainly rely on geometric…
H2O+: An Improved Framework for Hybrid Offline-and-Online RL with Dynamics Gaps
Haoyi Niu, Tianying Ji, Bingqi Liu +7
Solving real-world complex tasks using reinforcement learning (RL) without high-fidelity simulation environments or large amounts of offline data can be quite challenging. Online R…
ECT: Fine-grained Edge Detection with Learned Cause Tokens
Shaocong Xu, Xiaoxue Chen, Yuhang Zheng +4
In this study, we tackle the challenging fine-grained edge detection task, which refers to predicting specific edges caused by reflectance, illumination, normal, and depth changes,…
Car-Studio: Learning Car Radiance Fields from Single-View and Endless In-the-wild Images
Tianyu Liu, Hao Zhao, Yang Yu +2
Compositional neural scene graph studies have shown that radiance fields can be an efficient tool in an editable autonomous driving simulator. However, previous studies learned wit…
STRAP: Structured Object Affordance Segmentation with Point Supervision
Leiyao Cui, Xiaoxue Chen, Hao Zhao +2
With significant annotation savings, point supervision has been proven effective for numerous 2D and 3D scene understanding problems. This success is primarily attributed to the st…
Delving into Shape-aware Zero-shot Semantic Segmentation
Xinyu Liu, Beiwen Tian, Zhen Wang +5
Thanks to the impressive progress of large-scale vision-language pretraining, recent recognition models can classify arbitrary objects in a zero-shot and open-set manner, with a su…
DQS3D: Densely-matched Quantization-aware Semi-supervised 3D Detection
Huan-ang Gao, Beiwen Tian, Pengfei Li +2
In this paper, we study the problem of semi-supervised 3D object detection, which is of great importance considering the high annotation cost for cluttered 3D indoor scenes. We res…
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…
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…
STEPS: Joint Self-supervised Nighttime Image Enhancement and Depth Estimation
Yupeng Zheng, Chengliang Zhong, Pengfei Li +8
Self-supervised depth estimation draws a lot of attention recently as it can promote the 3D sensing capabilities of self-driving vehicles. However, it intrinsically relies upon the…
ADAPT: Action-aware Driving Caption Transformer
Bu Jin, Xinyu Liu, Yupeng Zheng +6
End-to-end autonomous driving has great potential in the transportation industry. However, the lack of transparency and interpretability of the automatic decision-making process hi…
From Semi-supervised to Omni-supervised Room Layout Estimation Using Point Clouds
Huan-ang Gao, Beiwen Tian, Pengfei Li +5
Room layout estimation is a long-existing robotic vision task that benefits both environment sensing and motion planning. However, layout estimation using point clouds (PCs) still…
Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning
Wenkai Yang, Deli Chen, Hao Zhou +3
Federated Learning (FL) has become a popular distributed learning paradigm that involves multiple clients training a global model collaboratively in a data privacy-preserving manne…
Self-Aligning Depth-regularized Radiance Fields for Asynchronous RGB-D Sequences
Yuxin Huang, Andong Yang, Zirui Wu +6
It has been shown that learning radiance fields with depth rendering and depth supervision can effectively promote the quality and convergence of view synthesis. However, this para…
VIBUS: Data-efficient 3D Scene Parsing with VIewpoint Bottleneck and Uncertainty-Spectrum Modeling
Beiwen Tian, Liyi Luo, Hao Zhao +1
Recently, 3D scenes parsing with deep learning approaches has been a heating topic. However, current methods with fully-supervised models require manually annotated point-wise supe…
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…
Planning Assembly Sequence with Graph Transformer
Lin Ma, Jiangtao Gong, Hao Xu +4
Assembly sequence planning (ASP) is the essential process for modern manufacturing, proven to be NP-complete thus its effective and efficient solution has been a challenge for rese…
Understanding Embodied Reference with Touch-Line Transformer
Yang Li, Xiaoxue Chen, Hao Zhao +4
We study embodied reference understanding, the task of locating referents using embodied gestural signals and language references. Human studies have revealed that objects referred…