Search Results for author:
Found 41 papers, 26 papers with code
Spatial Hierarchy Aware Residual Pyramid Network for Time-of-Flight Depth Denoising
In this paper, we propose a Spatial Hierarchy Aware Residual Pyramid Network, called SHARP-Net, to remove the depth noise by fully exploiting the geometry information of the scene on different scales.
Event-Enhanced Blurry Video Super-Resolution
In this paper, we tackle the task of blurry video super-resolution (BVSR), aiming to generate high-resolution (HR) videos from low-resolution (LR) and blurry inputs.
Fine-Grained Evaluation of Large Vision-Language Models in Autonomous Driving
To further exploit the cognitive and reasoning interactions among the 5 domains for AD understanding, we start from a small-scale VLM and train the DS models on individual domain datasets (collected from 1. 4M DS QAs across public sources).
Denoising Designs-inherited Search Framework for Image Denoising
The parameters of our searched architecture are $1/3$ of Restormer's, and our method surpasses existing NAS-based denoising methods by $1. 50$ dB in the real-world dataset.
Spiking Point Transformer for Point Cloud Classification
To this end, we present Spiking Point Transformer (SPT), the first transformer-based SNN framework for point cloud classification.
S2D-LFE: Sparse-to-Dense Light Field Event Generation
For the first time to our knowledge, S2D-LFE enables controllable novel view synthesis only from sparse-view light field event (LFE) data, and addresses three critical challenges for the LFE generation task: simplicity, controllability, and consistency.
Incomplete Multi-modal Brain Tumor Segmentation via Learnable Sorting State Space Model
Brain tumor segmentation plays a crucial role in clinical diagnosis, yet the frequent unavailability of certain MRI modalities poses a significant challenge.
Event-boosted Deformable 3D Gaussians for Dynamic Scene Reconstruction
To address this, we introduce the first approach combining event cameras, which capture high-temporal-resolution, continuous motion data, with deformable 3D-GS for dynamic scene reconstruction.
D-FINE: Redefine Regression Task in DETRs as Fine-grained Distribution Refinement
When pretrained on Objects365, D-FINE-L / X attains 57. 1% / 59. 3% AP, surpassing all existing real-time detectors.
Ranked #2 on
Real-Time Object Detection
on MS COCO
Generalizable Non-Line-of-Sight Imaging with Learnable Physical Priors
Non-line-of-sight (NLOS) imaging, recovering the hidden volume from indirect reflections, has attracted increasing attention due to its potential applications.
Anatomical Consistency Distillation and Inconsistency Synthesis for Brain Tumor Segmentation with Missing Modalities
Through validation on the BraTS2018 and BraTS2020 datasets, ACDIS substantiates its efficacy in the segmentation of brain tumors with missing MRI modalities.
EE-MLLM: A Data-Efficient and Compute-Efficient Multimodal Large Language Model
While self-attention-based methods offer superior data efficiency due to their simple MLP architecture, they often suffer from lower computational efficiency due to concatenating visual and textual tokens as input for LLM.
CEIA: CLIP-Based Event-Image Alignment for Open-World Event-Based Understanding
In response to this challenge, CEIA learns to align event and image data as an alternative instead of directly aligning event and text data.
EvTexture: Event-driven Texture Enhancement for Video Super-Resolution
Our method, called EvTexture, leverages high-frequency details of events to better recover texture regions in VSR.
Ranked #1 on
Video Super-Resolution
on Vid4 - 4x upscaling
Visual Perception by Large Language Model's Weights
Following this paradigm, we propose VLoRA with the perceptual weights generator.
Multi-Modal Generative Embedding Model
Existing models usually tackle these two types of problems by decoupling language modules into a text decoder for generation, and a text encoder for embedding.
Scene Adaptive Sparse Transformer for Event-based Object Detection
However, they display inadequate sparsity and adaptability when applied to event-based object detection, since these approaches cannot balance the fine granularity of token-level sparsification and the efficiency of window-based Transformers, leading to reduced performance and efficiency.
Event-assisted Low-Light Video Object Segmentation
In the realm of video object segmentation (VOS), the challenge of operating under low-light conditions persists, resulting in notably degraded image quality and compromised accuracy when comparing query and memory frames for similarity computation.
Graph Relation Distillation for Efficient Biomedical Instance Segmentation
IGD constructs a graph representing instance features and relations, transferring these two types of knowledge by enforcing instance graph consistency.
Cross-Dimension Affinity Distillation for 3D EM Neuron Segmentation
Recent advancements utilize 3D CNNs to predict a 3D affinity map with improved accuracy but suffer from two challenges: high computational cost and limited input size especially for practical deployment for large-scale EM volumes.
ART$\boldsymbol{\cdot}$V: Auto-Regressive Text-to-Video Generation with Diffusion Models
Second, it preserves the high-fidelity generation ability of the pre-trained image diffusion models by making only minimal network modifications.
GET: Group Event Transformer for Event-Based Vision
Event cameras are a type of novel neuromorphic sen-sor that has been gaining increasing attention.
Ranked #2 on
Classification
on N-CARS
EGVD: Event-Guided Video Deraining
In this paper, we approach video deraining by employing an event camera.
Domain Adaptive Synapse Detection with Weak Point Annotations
In the second stage, we improve model generalizability on target data by regenerating square masks to get high-quality pseudo labels.
Deep Multi-Threshold Spiking-UNet for Image Processing
Furthermore, we adopt a flow-based training method to fine-tune the converted models, reducing time steps while preserving performance.
Toward Real-World Light Field Super-Resolution
Deep learning has opened up new possibilities for light field super-resolution (SR), but existing methods trained on synthetic datasets with simple degradations (e. g., bicubic downsampling) suffer from poor performance when applied to complex real-world scenarios.
Image Captioning with Multi-Context Synthetic Data
This potential can be harnessed to create synthetic image-text pairs for training captioning models.
A Soma Segmentation Benchmark in Full Adult Fly Brain
Finally, we provide quantitative and qualitative benchmark comparisons on the testset to validate the superiority of the proposed method, as well as preliminary statistics of the reconstructed somas in the full adult fly brain from the biological perspective.
Progressive Spatio-Temporal Alignment for Efficient Event-Based Motion Estimation
In addition, a dynamic batch size strategy is applied to adaptively adjust the batch size so that all events in the batch are consistent with the current motion model.
Depth Estimation From Indoor Panoramas With Neural Scene Representation
Depth estimation from indoor panoramas is challenging due to the equirectangular distortions of panoramas and inaccurate matching.
NLOST: Non-Line-of-Sight Imaging With Transformer
Specifically, after extracting the shallow features with the assistance of physics-based priors, we design two spatial-temporal self attention encoders to explore both local and global correlations within 3D NLOS data by splitting or downsampling the features into different scales, respectively.
Unsupervised Video Deraining with An Event Camera
Current unsupervised video deraining methods are inefficient in modeling the intricate spatio-temporal properties of rain, which leads to unsatisfactory results.
Learning Cross-Representation Affinity Consistency for Sparsely Supervised Biomedical Instance Segmentation
Sparse instance-level supervision has recently been explored to address insufficient annotation in biomedical instance segmentation, which is easier to annotate crowded instances and better preserves instance completeness for 3D volumetric datasets compared to common semi-supervision. In this paper, we propose a sparsely supervised biomedical instance segmentation framework via cross-representation affinity consistency regularization.
Event-Based Blurry Frame Interpolation Under Blind Exposure
Therefore, we first propose an exposure estimation strategy guided by event streams to estimate the lost exposure prior, transforming the blind exposure problem well-posed.
Degradation-agnostic Correspondence from Resolution-asymmetric Stereo
Interestingly, we find that, although a stereo matching network trained with the photometric loss is not optimal, its feature extractor can produce degradation-agnostic and matching-specific features.
Retinal Vessel Segmentation with Pixel-wise Adaptive Filters
Accurate retinal vessel segmentation is challenging because of the complex texture of retinal vessels and low imaging contrast.
Exploiting Rigidity Constraints for LiDAR Scene Flow Estimation
Previous LiDAR scene flow estimation methods, especially recurrent neural networks, usually suffer from structure distortion in challenging cases, such as sparse reflection and motion occlusions.
EDPN: Enhanced Deep Pyramid Network for Blurry Image Restoration
Image deblurring has seen a great improvement with the development of deep neural networks.
Advanced Deep Networks for 3D Mitochondria Instance Segmentation
Mitochondria instance segmentation from electron microscopy (EM) images has seen notable progress since the introduction of deep learning methods.
Ranked #1 on
3D Instance Segmentation
on MitoEM
Event-Based Video Reconstruction Using Transformer
Event cameras, which output events by detecting spatio-temporal brightness changes, bring a novel paradigm to image sensors with high dynamic range and low latency.
Ranked #2 on
Event-based Object Segmentation
on DSEC-SEG
Event-based Object Segmentation
Event-Based Video Reconstruction
+1
Depth Acquisition from Density Modulated Binary Patterns
First, we propose an algorithm to design the patterns to carry more phase information without compromising the depth reconstruction from a single captured image as with Kinect.
