Author name cluster

Yuanbo Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

2 author rows

AAAI Conference 2025 Conference Paper

Separating the Wheat from the Chaff: Spatio-Temporal Transformer with View-interweaved Attention for Photon-Efficient Depth Sensing

Letian Yu
Jiaxi Yang
Bo Dong
Qirui Bao
Yuanbo Wang
Felix Heide
Xiaopeng Wei
Xin Yang

Time-resolved imaging is an emerging sensing modality that has been shown to enable advanced applications, including remote sensing, fluorescence lifetime imaging, and even non-line-of-sight sensing. Single-photon avalanche diodes (SPADs) outperform relevant time-resolved imaging technologies thanks to their excellent photon sensitivity and superior temporal resolution on the order of tens of picoseconds. The capability of exceeding the sensing limits of conventional cameras for SPADs also draws attention to the photon-efficient imaging area. However, photon-efficient imaging under degraded conditions with low photon counts and low signal-to-background ratio (SBR) still remains an inevitable challenge. In this paper, we propose a spatio-temporal transformer network for photon-efficient imaging under low-flux scenarios. In particular, we introduce a view-interweaved attention mechanism (VIAM) to extract both spatial-view and temporal-view self-attention in each transformer block. We also design an adaptive-weighting scheme to dynamically adjust the weights between different views of self-attention in VIAM for different signal-to-background levels. We extensively validate and demonstrate the effectiveness of our approach on the simulated Middlebury dataset and a specially self-collected dataset with real-world-captured SPAD measurements and well-annotated ground truth depth maps.

PDF Details DOI

IROS Conference 2024 Conference Paper

Event-intensity Stereo with Cross-modal Fusion and Contrast

Yuanbo Wang
Shanglai Qu
Tianyu Meng
Yan Cui
Haiyin Piao
Xiaopeng Wei
Xin Yang 0011

For binocular stereo, traditional cameras excel in capturing fine details and texture information but are limited in terms of dynamic range and their ability to handle rapid motion. On the contrary, event cameras provide pixel-level intensity changes with low latency and a wide dynamic range, albeit at the cost of less detail in their output. It is natural to leverage the strengths of both modalities. We solve this problem by introducing a cross-modal fusion module that learns a visual representation from both sensor inputs. Additionally, we extract and compare dense event-intensity stereo pair features by contrasting “pairs of event-intensity pairs from different views and different modalities and different timestamps”. This provides the flexibility in masking hard negatives and enables networks to effectively combine event-intensity signals within a contrastive learning framework, leading to an improved matching accuracy and facilitating more accurate estimation of disparity. Experimental results validate the effectiveness of our model and the improvement of disparity estimation accuracy.

Details

IJCAI Conference 2018 Conference Paper

Active Object Reconstruction Using a Guided View Planner

Xin Yang
Yuanbo Wang
Yaru Wang
Baocai Yin
Qiang Zhang
Xiaopeng Wei
Hongbo Fu

Inspired by the recent advance of image-based object reconstruction using deep learning, we present an active reconstruction model using a guided view planner. We aim to reconstruct a 3D model using images observed from a planned sequence of informative and discriminative views. But where are such informative and discriminative views around an object? To address this we propose a unified model for view planning and object reconstruction, which is utilized to learn a guided information acquisition model and to aggregate information from a sequence of images for reconstruction. Experiments show that our model (1) increases our reconstruction accuracy with an increasing number of views (2) and generally predicts a more informative sequence of views for object reconstruction compared to other alternative methods.

PDF Details

RLDM Conference 2015 Conference Abstract

Balancing the Moral Bank: Neural Mechanisms of Reciprocity

Yuanbo Wang
Jorie Koster-Hale
Fiery Cushman

Reciprocity depends on two processes: encoding information about social partners’ generosity, and retrieving that information in order to guide subsequent choice. We know much about these processes in isolation, but less about the way in which they are integrated. In this study we identify neural correlates of encoding and retrieval that underlie reciprocity in a sequential prisoner’s dilemma. We recruited twenty-nine subjects to play a round-robin economic game in the fMRI scanner. Each participant interacted with multiple players characterized by variable degrees of generosity. Based on prior research and computational models (see Koster-Hale, & Saxe, 2013 for a review), we predicted that participants would maintain player-specific representations of the probability of giving via a prediction error update mechanism. Further, we predicted that the current value of this ‘generosity’ parameter would be recalled during opportunities for reciprocation. We find evidence for signals of both types in dorsomedial prefrontal cortex (dmPFC): BOLD signal tracks prediction error values during encoding (update), and generosity parameters during reciprocity (retrieval). This echoes prior research on the role of dmPFC in trust (Behrens, et al. , 2009). Notably, these signals track lack of generosity. Specifically, we observed decreased activation in the region for unpredicted generous behavior during encoding, and decreased activation when reciprocating to a generous partner. Thus, our results suggest that dmPFC may be responsible for storing and retrieving information about other’s social behaviors, specifically negative character traits and then using them to guide reciprocity.

PDF Details