arXiv subjects

Xiangru Chen

Publications and source records attributed to Xiangru Chen.

7 recordsLinked to original sources

arXiv2026

Spatio-Temporal Difference Guided Motion Deblurring with the Complementary Vision Sensor

Motion blur arises when rapid scene changes occur during the exposure period, collapsing rich intra-exposure motion into a single RGB frame. Without explicit structural or temporal cues, RGB-only deblurring is highly ill-posed and often fails under extreme motion. Inspired by the human visual system, brain-inspired vision sensors introduce temporally dense information to alleviate this problem. However, event cameras still suffer from event rate saturation under rapid motion, while the event modality entangles edge features and motion cues, which limits their effectiveness. As a recent breakthrough, the complementary vision sensor (CVS), Tianmouc, captures synchronized RGB frames together with high-frame-rate, multi-bit spatial difference (SD, encoding structural edges) and temporal difference (TD, encoding motion cues) data within a single RGB exposure, offering a promising solution for RGB deblurring under extreme dynamic scenes. To fully leverage these complementary modalities, we propose Spatio-Temporal Difference Guided Deblur Net (STGDNet), which adopts a recurrent multi-branch architecture that iteratively encodes and fuses SD and TD sequences to restore structure and color details lost in blurry RGB inputs. Our method outperforms current RGB or event-based approaches in both synthetic CVS dataset and real-world evaluations. Moreover, STGDNet exhibits strong generalization capability across over 100 extreme real-world scenarios. Project page: https://tmcDeblur.github.io/

cs.CV↗

arXiv2026

L-PCN: A Point Cloud Accelerator Exploiting Spatial Locality through Octree-based Islandization

Existing Point Cloud Networks (PCNs) have proven to achieve great success in many point cloud tasks such as object part segmentation, shape classification, and so on. The most popular point-based PCNs are usually composed of two sequential steps: Data Structuring (DS) and Feature Computation (FC). In this paper, we first describe an important characteristic of the PCN-specific DS step that has not been addressed in existing PCN accelerators: the spatial locality resulting from overlapping points of the gathered point subsets. Using algorithm-hardware co-design, L-PCN (Locality-aware PCN) proposes two novel techniques to exploit this characteristic to reduce the large amount of repetitive operations in the overall PCN. The first of which is a point cloud partitioning technique, Octree-based Islandization. Using Octree-based adjacency gathering, a point cloud is partitioned into islands in L-PCN, where the point subsets inside the same island exhibit a strong spatial correlation. After partitioning, L-PCN performs the rest of PCN steps at the granularity of islands. The second method of L-PCN is scheduling the intra-island computation with a Hub-based Scheduling to exploit the intra-island data reuse by dynamically caching, updating, and reusing the repeated data. The two methods are implemented in an Islandization Unit, which can be seamlessly integrated into standard PCN workflow. Our evaluation shows that based on our methods for exploiting spatial locality, L-PCN achieves a theoretical reduction in feature fetching ranging from 55.2% to 93.8% and in feature computation ranging from 45.4% to 80.6% during the PCN process. For experimentation, prototype L-PCN accelerators are implemented on the Intel Arria 10 GX FPGA. Experimental results prove that with the Islandization Unit as a plug-in, state-of-the-art PCN accelerators can achieve an additional speedup ranging from 1.2x to 3.2x.

cs.AR↗

arXiv2026

Implementing non-Abelian Hatano-Nelson model in electric circuits

Non-Hermitian systems generally host complex spectra that bring unique spectral topologies, leading to the spectral braiding and non-Hermitian skin effect. The experimental exploration of non-Hermitian physics is mainly concentrated in artificial systems due to the flexibility in the introduction of the non-Hermiticity, but to date has focused only on the systems without gauge fields or with Abelian gauge fields. Here, we propose a non-Abelian Hatano-Nelson model with a nonreciprocal U(2) gauge field. The gauge field induces two non-Hermitian phenomena: the first is the Hopf-link-shaped complex energy braiding, and the second is the bipolar skin effect arising under the non-Abelian condition. The non-Abelian Hatano-Nelson model is implemented in electric circuits, and the Hopf-link-shaped admittance spectra and bipolar skin admittance modes are observed. Our work enriches the experimental non-Hermitian physics, and provides an approach to designing multifunctional non-Hermitian devices.

quant-ph↗

arXiv2026

Observation of exceptional topology and nonlocal skin effect in Klein bottle electric circuits

Symmetry and its representation play a crucial role in topological phases, including both Hermitian and non-Hermitian paradigms. In the presence of synthetic gauge field, spatial symmetries should be projectively represented, which can modify the Brillouin manifold. However, this is often overlooked in non-Hermitian systems. Here, we present that momentum-space non-symmorphic reflection symmetry, a typical projective symmetry, induce exceptional topology and the nonlocal skin effect in a two-dimensional non-Hermitian electric circuit. We observe the total topological charges 2, rather than 0, for all exceptional points in a Brillouin Klein bottle manifold, and the phase transition when an exceptional point crosses the antiparallel boundary and flips its topological charge. We further observe a novel skin effect that the skin modes at one side are nonlocally connected to those on the opposite side separated by half of the reciprocal lattice. Our results unveil the unique non-Hermitian phenomena enabled by the projective symmetry, and open avenues for exploring the non-Hermitian topology beyond Brillouin torus manifold.

cond-mat.mes-hall↗

arXiv2025

Higher-order exceptional ring semimetal with real hinge states in phononic crystals

Non-Hermitian topological phase, with the novel concepts such as exceptional points and skin effect, has opened up a new paradigm beyond Hermitian topological physics. Exceptional ring semimetal, featured by a stable ring of exceptional points in three dimensions, exhibits first-order topological properties, including topological surface states and surface-dependent skin effect. Nevertheless, despite extensive research on Hermitian higher-order insulators and semimetals, higher-order exceptional ring semimetal is just emerging. Here, we report the first realization of a higher-order Weyl exceptional ring semimetal in a three-dimensional lossy phononic crystal. The non-Hermitian higher-order topology reflects in the topological hinge states and hinge-dependent skin effect. Counterintuitively, the topological hinge states maintain purely real energy even under a high loss level, ensuring robust hinge-state propagation. Our findings evidence the non-Hermitian higher-order bulk-boundary correspondence of exceptional ring semimetal, and may pave the way to non-Hermitian functional acoustic devices.

cond-mat.mes-hall↗

arXiv2025

HgPCN: A Heterogeneous Architecture for E2E Embedded Point Cloud Inference

Point cloud is an important type of geometric data structure for many embedded applications such as autonomous driving and augmented reality. Current Point Cloud Networks (PCNs) have proven to achieve great success in using inference to perform point cloud analysis, including object part segmentation, shape classification, and so on. However, point cloud applications on the computing edge require more than just the inference step. They require an end-to-end (E2E) processing of the point cloud workloads: pre-processing of raw data, input preparation, and inference to perform point cloud analysis. Current PCN approaches to support end-to-end processing of point cloud workload cannot meet the real-time latency requirement on the edge, i.e., the ability of the AI service to keep up with the speed of raw data generation by 3D sensors. Latency for end-to-end processing of the point cloud workloads stems from two reasons: memory-intensive down-sampling in the pre-processing phase and the data structuring step for input preparation in the inference phase. In this paper, we present HgPCN, an end-to-end heterogeneous architecture for real-time embedded point cloud applications. In HgPCN, we introduce two novel methodologies based on spatial indexing to address the two identified bottlenecks. In the Pre-processing Engine of HgPCN, an Octree-Indexed-Sampling method is used to optimize the memory-intensive down-sampling bottleneck of the pre-processing phase. In the Inference Engine, HgPCN extends a commercial DLA with a customized Data Structuring Unit which is based on a Voxel-Expanded Gathering method to fundamentally reduce the workload of the data structuring step in the inference phase.

cs.AR↗

arXiv2021

Optimizing the Whole-life Cost in End-to-end CNN Acceleration

The acceleration of CNNs has gained increasing atten-tion since their success in computer vision. With the heterogeneous functional layers that cannot be pro-cessed by the accelerators proposed for convolution layers only, modern end-to-end CNN acceleration so-lutions either transform the diverse computation into matrix/vector arithmetic, which loses data reuse op-portunities in convolution, or introduce dedicated functional unit to each kind of layer, which results in underutilization and high update expense. To enhance the whole-life cost efficiency, we need an acceleration solution that is efficient in processing CNN layers and has the generality to apply to all kinds of existing and emerging layers. To this end, we pro-pose GCONV Chain, a method to convert the entire CNN computation into a chain of standard general convolutions (GCONV) that can be efficiently pro-cessed by the existing CNN accelerators. This paper comprehensively analyzes the GCONV Chain model and proposes a full-stack implementation to support GCONV Chain. On one hand, the results on seven var-ious CNNs demonstrate that GCONV Chain improves the performance and energy efficiency of existing CNN accelerators by an average of 3.4x and 3.2x re-spectively. On the other hand, we show that GCONV Chain provides low whole-life costs for CNN accelera-tion, including both developer efforts and total cost of ownership for the users.

cs.DC↗