Search Results for author:
Found 11 papers, 11 papers with code
Offboard Occupancy Refinement with Hybrid Propagation for Autonomous Driving
Vision-based occupancy prediction, also known as 3D Semantic Scene Completion (SSC), presents a significant challenge in computer vision.
Towards Precise 3D Human Pose Estimation with Multi-Perspective Spatial-Temporal Relational Transformers
Due to the challenges in data collection, mainstream datasets of 3D human pose estimation are primarily composed of multi-view video data collected in laboratory environments, which contains rich spatial-temporal correlation information besides the image frame content.
Rethinking Event-based Human Pose Estimation with 3D Event Representations
Experiments on EV-3DPW demonstrate that the robustness of our proposed 3D representation methods compared to traditional RGB images and event frame techniques under the same backbones.
Context Perception Parallel Decoder for Scene Text Recognition
We first present an empirical study of AR decoding in STR, and discover that the AR decoder not only models linguistic context, but also provides guidance on visual context perception.
Ranked #1 on
Scene Text Recognition
on CUTE80
(using extra training data)
Towards Anytime Optical Flow Estimation with Event Cameras
We then propose EVA-Flow, an EVent-based Anytime Flow estimation network to produce high-frame-rate event optical flow with only low-frame-rate optical flow ground truth for supervision.
Beyond the Field-of-View: Enhancing Scene Visibility and Perception with Clip-Recurrent Transformer
In this paper, we propose the concept of online video inpainting for autonomous vehicles to expand the field of view, thereby enhancing scene visibility, perception, and system safety.
Ranked #1 on
Seeing Beyond the Visible
on KITTI360-EX
PP-OCRv3: More Attempts for the Improvement of Ultra Lightweight OCR System
For text recognizer, the base model is replaced from CRNN to SVTR, and we introduce lightweight text recognition network SVTR LCNet, guided training of CTC by attention, data augmentation strategy TextConAug, better pre-trained model by self-supervised TextRotNet, UDML, and UIM to accelerate the model and improve the effect.
SVTR: Scene Text Recognition with a Single Visual Model
Dominant scene text recognition models commonly contain two building blocks, a visual model for feature extraction and a sequence model for text transcription.
Ranked #16 on
Scene Text Recognition
on ICDAR2013
PanoFlow: Learning 360° Optical Flow for Surrounding Temporal Understanding
PanoFlow achieves state-of-the-art performance on the public OmniFlowNet and the established FlowScape benchmarks.
CSFlow: Learning Optical Flow via Cross Strip Correlation for Autonomous Driving
In this paper, we propose a new deep network architecture for optical flow estimation in autonomous driving--CSFlow, which consists of two novel modules: Cross Strip Correlation module (CSC) and Correlation Regression Initialization module (CRI).
PP-OCR: A Practical Ultra Lightweight OCR System
Meanwhile, several pre-trained models for the Chinese and English recognition are released, including a text detector (97K images are used), a direction classifier (600K images are used) as well as a text recognizer (17. 9M images are used).
