CaesarNeRF: Calibrated Semantic Representation for Few-shot Generalizable Neural Rendering

1 code implementation • 27 Nov 2023 • Haidong Zhu, Tianyu Ding, Tianyi Chen, Ilya Zharkov, Ram Nevatia, Luming Liang

CaesarNeRF explicitly models pose differences of reference views to combine scene-level semantic representations, providing a calibrated holistic understanding.

Few-Shot Learning Neural Rendering

LoRAShear: Efficient Large Language Model Structured Pruning and Knowledge Recovery

1 code implementation • 24 Oct 2023 • Tianyi Chen, Tianyu Ding, Badal Yadav, Ilya Zharkov, Luming Liang

Large Language Models (LLMs) have transformed the landscape of artificial intelligence, while their enormous size presents significant challenges in terms of computational costs.

Language Modelling Large Language Model +1

MMVP: Motion-Matrix-based Video Prediction

1 code implementation • ICCV 2023 • Yiqi Zhong, Luming Liang, Ilya Zharkov, Ulrich Neumann

A central challenge of video prediction lies where the system has to reason the objects' future motions from image frames while simultaneously maintaining the consistency of their appearances across frames.

motion prediction Video Prediction

Automated Search-Space Generation Neural Architecture Search

1 code implementation • 25 May 2023 • Tianyi Chen, Luming Liang, Tianyu Ding, Ilya Zharkov

To search an optimal sub-network within a general deep neural network (DNN), existing neural architecture search (NAS) methods typically rely on handcrafting a search space beforehand.

Neural Architecture Search

OTOV2: Automatic, Generic, User-Friendly

1 code implementation • 13 Mar 2023 • Tianyi Chen, Luming Liang, Tianyu Ding, Zhihui Zhu, Ilya Zharkov

We propose the second generation of Only-Train-Once (OTOv2), which first automatically trains and compresses a general DNN only once from scratch to produce a more compact model with competitive performance without fine-tuning.

Model Compression

Sparsity-guided Network Design for Frame Interpolation

1 code implementation • 9 Sep 2022 • Tianyu Ding, Luming Liang, Zhihui Zhu, Tianyi Chen, Ilya Zharkov

As a result, we achieve a considerable performance gain with a quarter of the size of the original AdaCoF.

CF-YOLO: Cross Fusion YOLO for Object Detection in Adverse Weather with a High-quality Real Snow Dataset

no code implementations • 3 Jun 2022 • Qiqi Ding, Peng Li, Xuefeng Yan, Ding Shi, Luming Liang, Weiming Wang, Haoran Xie, Jonathan Li, Mingqiang Wei

To our knowledge, RSOD is the first quantitatively evaluated and graded snowy OD dataset.

object-detection Object Detection

RSTT: Real-time Spatial Temporal Transformer for Space-Time Video Super-Resolution

1 code implementation • CVPR 2022 • Zhicheng Geng, Luming Liang, Tianyu Ding, Ilya Zharkov

Space-time video super-resolution (STVSR) is the task of interpolating videos with both Low Frame Rate (LFR) and Low Resolution (LR) to produce High-Frame-Rate (HFR) and also High-Resolution (HR) counterparts.

Space-time Video Super-resolution Video Frame Interpolation +1

Only Train Once: A One-Shot Neural Network Training And Pruning Framework

1 code implementation • NeurIPS 2021 • Tianyi Chen, Bo Ji, Tianyu Ding, Biyi Fang, Guanyi Wang, Zhihui Zhu, Luming Liang, Yixin Shi, Sheng Yi, Xiao Tu

Structured pruning is a commonly used technique in deploying deep neural networks (DNNs) onto resource-constrained devices.

CDFI: Compression-Driven Network Design for Frame Interpolation

1 code implementation • CVPR 2021 • Tianyu Ding, Luming Liang, Zhihui Zhu, Ilya Zharkov

DNN-based frame interpolation--that generates the intermediate frames given two consecutive frames--typically relies on heavy model architectures with a huge number of features, preventing them from being deployed on systems with limited resources, e. g., mobile devices.

Video Frame Interpolation

ImagePairs: Realistic Super Resolution Dataset via Beam Splitter Camera Rig

no code implementations • 18 Apr 2020 • Hamid Reza Vaezi Joze, Ilya Zharkov, Karlton Powell, Carl Ringler, Luming Liang, Andy Roulston, Moshe Lutz, Vivek Pradeep

To our knowledge this is the most complete dataset for super resolution, ISP and image quality enhancement.

Benchmarking BIG-bench Machine Learning +1

DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks

1 code implementation • 27 Aug 2019 • Sen Deng, Mingqiang Wei, Jun Wang, Luming Liang, Haoran Xie, Meng Wang

We have validated our approach on four recognized datasets (three synthetic and one real-world).

Rain Removal

Convolutional Neural Network with Median Layers for Denoising Salt-and-Pepper Contaminations

1 code implementation • 18 Aug 2019 • Luming Liang, Sen Deng, Lionel Gueguen, Mingqiang Wei, Xinming Wu, Jing Qin

We propose a deep fully convolutional neural network with a new type of layer, named median layer, to restore images contaminated by the salt-and-pepper (s&p) noise.

Salt-And-Pepper Noise Removal