Search Results for author:
Found 29 papers, 13 papers with code
ComNeck: Bridging Compressed Image Latents and Multimodal LLMs via Universal Transform-Neck
MLLMs have extended the success of large language models to modalities (e. g. images) beyond text, but their billion scale hinders deployment on resource-constrained end devices.
OMRA: Online Motion Resolution Adaptation to Remedy Domain Shift in Learned Hierarchical B-frame Coding
To mitigate the domain shift, we present an online motion resolution adaptation (OMRA) method.
Transformer-based Learned Image Compression for Joint Decoding and Denoising
Instead of training separate decoders for these tasks, we incorporate two add-on modules to adapt a pre-trained image decoder from performing the standard image reconstruction to joint decoding and denoising.
LiDAR Depth Map Guided Image Compression Model
In this paper, we introduce a novel direction that harnesses LiDAR depth maps to enhance the compression of the corresponding RGB camera images.
Transformer-based Image Compression with Variable Image Quality Objectives
This paper presents a Transformer-based image compression system that allows for a variable image quality objective according to the user's preference.
Learning Continuous Exposure Value Representations for Single-Image HDR Reconstruction
To address this, we propose the continuous exposure value representation (CEVR), which uses an implicit function to generate LDR images with arbitrary EVs, including those unseen during training.
MoTIF: Learning Motion Trajectories with Local Implicit Neural Functions for Continuous Space-Time Video Super-Resolution
We motivate the use of forward motion from the perspective of learning individual motion trajectories, as opposed to learning a mixture of motion trajectories with backward motion.
TransTIC: Transferring Transformer-based Image Compression from Human Perception to Machine Perception
This work aims for transferring a Transformer-based image compression codec from human perception to machine perception without fine-tuning the codec.
Transformer-based Variable-rate Image Compression with Region-of-interest Control
Our prompt generation networks generate content-adaptive tokens according to the input image, an ROI mask, and a rate parameter.
Hierarchical B-frame Video Coding Using Two-Layer CANF without Motion Coding
The rate-distortion performance of our scheme is slightly lower than that of the state-of-the-art learned B-frame coding scheme, B-CANF, but outperforms other learned B-frame coding schemes.
Content-Adaptive Motion Rate Adaption for Learned Video Compression
This paper introduces an online motion rate adaptation scheme for learned video compression, with the aim of achieving content-adaptive coding on individual test sequences to mitigate the domain gap between training and test data.
Learned Hierarchical B-frame Coding with Adaptive Feature Modulation for YUV 4:2:0 Content
Most learned video codecs operate internally in the RGB domain for P-frame coding.
HuPR: A Benchmark for Human Pose Estimation Using Millimeter Wave Radar
In addition to the benchmark, we propose a cross-modality training framework that leverages the ground-truth 2D keypoints representing human body joints for training, which are systematically generated from the pre-trained 2D pose estimation network based on a monocular camera input image, avoiding laborious manual label annotation efforts.
Learned Video Compression for YUV 4:2:0 Content Using Flow-based Conditional Inter-frame Coding
To adapt our codec to YUV 4:2:0 content, we adopt a simple strategy of using space-to-depth and depth-to-space conversions.
Neural Frank-Wolfe Policy Optimization for Region-of-Interest Intra-Frame Coding with HEVC/H.265
Recently, the dual-critic design is proposed to update the actor by alternating the rate and distortion critics.
B-CANF: Adaptive B-frame Coding with Conditional Augmented Normalizing Flows
Our B*-frames allow greater flexibility in specifying the group-of-pictures (GOP) structure by reusing the B-frame codec to mimic P-frame coding, without the need for an additional, separate P-frame codec.
CANF-VC: Conditional Augmented Normalizing Flows for Video Compression
CANF-VC represents a new attempt that leverages the conditional ANF to learn a video generative model for conditional inter-frame coding.
Action-Constrained Reinforcement Learning for Frame-Level Bit Allocation in HEVC/H.265 through Frank-Wolfe Policy Optimization
More recently, the dual-critic design is proposed to update the actor network by alternating the rate and distortion critics.
ANFIC: Image Compression Using Augmented Normalizing Flows
This paper introduces an end-to-end learned image compression system, termed ANFIC, based on Augmented Normalizing Flows (ANF).
A Dual-Critic Reinforcement Learning Framework for Frame-level Bit Allocation in HEVC/H.265
This paper introduces a dual-critic reinforcement learning (RL) framework to address the problem of frame-level bit allocation in HEVC/H. 265.
Weakly-Supervised Image Semantic Segmentation Using Graph Convolutional Networks
One common approach to this task is to propagate the activation scores of Class Activation Maps (CAMs) using a random-walk mechanism in order to arrive at complete pseudo labels for training a semantic segmentation network in a fully-supervised manner.
Video Rescaling Networks with Joint Optimization Strategies for Downscaling and Upscaling
Our Long Short-Term Memory Video Rescaling Network (LSTM-VRN) leverages temporal information in the low-resolution video to form an explicit prediction of the missing high-frequency information for upscaling.
GSVNet: Guided Spatially-Varying Convolution for Fast Semantic Segmentation on Video
Moreover, we introduce a guided spatially-varying convolution for fusing segmentations derived from the previous and current frames, to mitigate propagation error and enable lightweight feature extraction on non-keyframes.
Class-incremental Learning with Rectified Feature-Graph Preservation
In this paper, we address the problem of distillation-based class-incremental learning with a single head.
Learning Priors for Adversarial Autoencoders
Most deep latent factor models choose simple priors for simplicity, tractability or not knowing what prior to use.
Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts
This paper tackles the problem of learning a questioner in the goal-oriented visual dialog task.
All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation
In this paper we tackle the problem of unsupervised domain adaptation for the task of semantic segmentation, where we attempt to transfer the knowledge learned upon synthetic datasets with ground-truth labels to real-world images without any annotation.
Ranked #25 on
Image-to-Image Translation
on SYNTHIA-to-Cityscapes
An Autoencoder-based Learned Image Compressor: Description of Challenge Proposal by NCTU
We propose a lossy image compression system using the deep-learning autoencoder structure to participate in the Challenge on Learned Image Compression (CLIC) 2018.
