198 citations · 379 across the 22 of their papers we have counts for
22 papers
ArchSIBench: Benchmarking the Architectural Spatial Intelligence of Vision-Language Models
Qirui Shen, Wenda Wang, Jiachen Lu +5
Architectural spatial intelligence, the ability to recognize and infer architectural space, is fundamental to tasks such as robot navigation, embodied interaction, and 3D scene und…
Sketch2MinSurf: Vision-Language Guided Generation of Editable Minimal Surfaces from Hand-Drawn Sketches
Wenda Wang, Anqi Liu, Junqi Yang +4
Converting hand-drawn sketches into structured 3D geometries remains challenging due to the difficulty of representing non-Euclidean surfaces and maintaining topological consistenc…
Seeing through boxes: Non-Line-of-Sight 3D Reconstruction from Radar Signals
Jiachen Lu, Hailan Shanbhag, Haitham Al Hassanieh
Reconstructing object geometry from radio frequency (RF) signals is fundamentally challenging due to the lensless imaging nature of RF sensing, which leads to low spatial resolutio…
GeRaF: Neural Geometry Reconstruction from Radio Frequency Signals
Jiachen Lu, Hailan Shanbhag, Haitham Al Hassanieh
GeRaF is the first method to use neural implicit learning for near-range 3D geometry reconstruction from radio frequency (RF) signals. Unlike RGB or LiDAR-based methods, RF sensing…
PGR-Net: Prior-Guided ROI Reasoning Network for Brain Tumor MRI Segmentation
Jiacheng Lu, Hui Ding, Shiyu Zhang +1
Brain tumor MRI segmentation is essential for clinical diagnosis and treatment planning, enabling accurate lesion detection and radiotherapy target delineation. However, tumor lesi…
Enhancing 3D Semantic Scene Completion with a Refinement Module
Dunxing Zhang, Jiachen Lu, Han Yang +2
We propose ESSC-RM, a plug-and-play Enhancing framework for Semantic Scene Completion with a Refinement Module, which can be seamlessly integrated into existing SSC models. ESSC-RM…
M-Net: MRI Brain Tumor Sequential Segmentation Network via Mesh-Cast
Jiacheng Lu, Hui Ding, Shiyu Zhang +1
MRI tumor segmentation remains a critical challenge in medical imaging, where volumetric analysis faces unique computational demands due to the complexity of 3D data. The spatially…
SEGMN: A Structure-Enhanced Graph Matching Network for Graph Similarity Learning
Wenjun Wang, Jiacheng Lu, Kejia Chen +2
Graph similarity computation (GSC) aims to quantify the similarity score between two graphs. Although recent GSC methods based on graph neural networks (GNNs) take advantage of int…
LaneGraph2Seq: Lane Topology Extraction with Language Model via Vertex-Edge Encoding and Connectivity Enhancement
Renyuan Peng, Xinyue Cai, Hang Xu +4
Understanding road structures is crucial for autonomous driving. Intricate road structures are often depicted using lane graphs, which include centerline curves and connections for…
Translating Images to Road Network: A Sequence-to-Sequence Perspective
Jiachen Lu, Ming Nie, Bozhou Zhang +6
The extraction of road network is essential for the generation of high-definition maps since it enables the precise localization of road landmarks and their interconnections. Howev…
S-Agents: Self-organizing Agents in Open-ended Environments
Jiaqi Chen, Yuxian Jiang, Jiachen Lu +1
Leveraging large language models (LLMs), autonomous agents have significantly improved, gaining the ability to handle a variety of tasks. In open-ended settings, optimizing collabo…
S-NeRF++: Autonomous Driving Simulation via Neural Reconstruction and Generation
Yurui Chen, Junge Zhang, Ziyang Xie +4
Autonomous driving simulation system plays a crucial role in enhancing self-driving data and simulating complex and rare traffic scenarios, ensuring navigation safety. However, tra…
WoVoGen: World Volume-aware Diffusion for Controllable Multi-camera Driving Scene Generation
Jiachen Lu, Ze Huang, Zeyu Yang +2
Generating multi-camera street-view videos is critical for augmenting autonomous driving datasets, addressing the urgent demand for extensive and varied data. Due to the limitation…
Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping
Zijie Pan, Jiachen Lu, Xiatian Zhu +1
High-resolution 3D object generation remains a challenging task primarily due to the limited availability of comprehensive annotated training data. Recent advancements have aimed t…
SUIT: Learning Significance-guided Information for 3D Temporal Detection
Zheyuan Zhou, Jiachen Lu, Yihan Zeng +2
3D object detection from LiDAR point cloud is of critical importance for autonomous driving and robotics. While sequential point cloud has the potential to enhance 3D perception th…
Generative Semantic Segmentation
Jiaqi Chen, Jiachen Lu, Xiatian Zhu +1
We present Generative Semantic Segmentation (GSS), a generative learning approach for semantic segmentation. Uniquely, we cast semantic segmentation as an image-conditioned mask ge…
SeaFormer++: Squeeze-enhanced Axial Transformer for Mobile Visual Recognition
Qiang Wan, Zilong Huang, Jiachen Lu +2
Since the introduction of Vision Transformers, the landscape of many computer vision tasks (e.g., semantic segmentation), which has been overwhelmingly dominated by CNNs, recently…
Vision Transformers: From Semantic Segmentation to Dense Prediction
Li Zhang, Jiachen Lu, Sixiao Zheng +6
The emergence of vision transformers (ViTs) in image classification has shifted the methodologies for visual representation learning. In particular, ViTs learn visual representatio…
Softmax-free Linear Transformers
Jiachen Lu, Junge Zhang, Xiatian Zhu +3
Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. The self-attention mechanism underpinning the strength of ViTs has a quadratic complexity i…
Learning Ego 3D Representation as Ray Tracing
Jiachen Lu, Zheyuan Zhou, Xiatian Zhu +2
A self-driving perception model aims to extract 3D semantic representations from multiple cameras collectively into the bird's-eye-view (BEV) coordinate frame of the ego car in ord…
SOFT: Softmax-free Transformer with Linear Complexity
Jiachen Lu, Jinghan Yao, Junge Zhang +6
Vision transformers (ViTs) have pushed the state-of-the-art for various visual recognition tasks by patch-wise image tokenization followed by self-attention. However, the employmen…
Rethinking Semantic Segmentation from a Sequence-to-Sequence Perspective with Transformers
Sixiao Zheng, Jiachen Lu, Hengshuang Zhao +8
Most recent semantic segmentation methods adopt a fully-convolutional network (FCN) with an encoder-decoder architecture. The encoder progressively reduces the spatial resolution a…