Dailan He
YOU?
Author Swipe
View article: CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression
CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression Open
Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the s…
View article: Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior
Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior Open
Recent advancements in diffusion models have been leveraged to address inverse problems without additional training, and Diffusion Posterior Sampling (DPS) (Chung et al., 2022a) is among the most popular approaches. Previous analyses sugge…
View article: VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping
VividFace: A Diffusion-Based Hybrid Framework for High-Fidelity Video Face Swapping Open
Video face swapping is becoming increasingly popular across various applications, yet existing methods primarily focus on static images and struggle with video face swapping because of temporal consistency and complex scenarios. In this pa…
View article: MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes
MEGA: Memory-Efficient 4D Gaussian Splatting for Dynamic Scenes Open
4D Gaussian Splatting (4DGS) has recently emerged as a promising technique for capturing complex dynamic 3D scenes with high fidelity. It utilizes a 4D Gaussian representation and a GPU-friendly rasterizer, enabling rapid rendering speeds.…
View article: Task-Aware Encoder Control for Deep Video Compression
Task-Aware Encoder Control for Deep Video Compression Open
Prior research on deep video compression (DVC) for machine tasks typically necessitates training a unique codec for each specific task, mandating a dedicated decoder per task. In contrast, traditional video codecs employ a flexible encoder…
View article: CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression
CAMSIC: Content-aware Masked Image Modeling Transformer for Stereo Image Compression Open
Existing learning-based stereo image codec adopt sophisticated transformation with simple entropy models derived from single image codecs to encode latent representations. However, those entropy models struggle to effectively capture the s…
View article: GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting
GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting Open
Implicit neural representations (INRs) recently achieved great success in image representation and compression, offering high visual quality and fast rendering speeds with 10-1000 FPS, assuming sufficient GPU resources are available. Howev…
View article: Boosting Neural Representations for Videos with a Conditional Decoder
Boosting Neural Representations for Videos with a Conditional Decoder Open
Implicit neural representations (INRs) have emerged as a promising approach for video storage and processing, showing remarkable versatility across various video tasks. However, existing methods often fail to fully leverage their represent…
View article: Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers
Consistency Model is an Effective Posterior Sample Approximation for Diffusion Inverse Solvers Open
Diffusion Inverse Solvers (DIS) are designed to sample from the conditional distribution $p_θ(X_0|y)$, with a predefined diffusion model $p_θ(X_0)$, an operator $f(\cdot)$, and a measurement $y=f(x'_0)$ derived from an unknown image $x'_0$…
View article: Idempotence and Perceptual Image Compression
Idempotence and Perceptual Image Compression Open
Idempotence is the stability of image codec to re-compression. At the first glance, it is unrelated to perceptual image compression. However, we find that theoretically: 1) Conditional generative model-based perceptual codec satisfies idem…
View article: Efficient Learned Lossless JPEG Recompression
Efficient Learned Lossless JPEG Recompression Open
JPEG is one of the most popular image compression methods. It is beneficial to compress those existing JPEG files without introducing additional distortion. In this paper, we propose a deep learning based method to further compress JPEG im…
View article: Conditional Perceptual Quality Preserving Image Compression
Conditional Perceptual Quality Preserving Image Compression Open
We propose conditional perceptual quality, an extension of the perceptual quality defined in \citet{blau2018perception}, by conditioning it on user defined information. Specifically, we extend the original perceptual quality $d(p_{X},p_{\h…
View article: KBNet: Kernel Basis Network for Image Restoration
KBNet: Kernel Basis Network for Image Restoration Open
How to aggregate spatial information plays an essential role in learning-based image restoration. Most existing CNN-based networks adopt static convolutional kernels to encode spatial information, which cannot aggregate spatial information…
View article: Multi-Sample Training for Neural Image Compression
Multi-Sample Training for Neural Image Compression Open
This paper considers the problem of lossy neural image compression (NIC). Current state-of-the-art (sota) methods adopt uniform posterior to approximate quantization noise, and single-sample pathwise estimator to approximate the gradient o…
View article: Bit Allocation using Optimization
Bit Allocation using Optimization Open
In this paper, we consider the problem of bit allocation in Neural Video Compression (NVC). First, we reveal a fundamental relationship between bit allocation in NVC and Semi-Amortized Variational Inference (SAVI). Specifically, we show th…
View article: Flexible Neural Image Compression via Code Editing
Flexible Neural Image Compression via Code Editing Open
Neural image compression (NIC) has outperformed traditional image codecs in rate-distortion (R-D) performance. However, it usually requires a dedicated encoder-decoder pair for each point on R-D curve, which greatly hinders its practical d…
View article: Evaluating the Practicality of Learned Image Compression
Evaluating the Practicality of Learned Image Compression Open
Learned image compression has achieved extraordinary rate-distortion performance in PSNR and MS-SSIM compared to traditional methods. However, it suffers from intensive computation, which is intolerable for real-world applications and lead…
View article: PO-ELIC: Perception-Oriented Efficient Learned Image Coding
PO-ELIC: Perception-Oriented Efficient Learned Image Coding Open
In the past years, learned image compression (LIC) has achieved remarkable performance. The recent LIC methods outperform VVC in both PSNR and MS-SSIM. However, the low bit-rate reconstructions of LIC suffer from artifacts such as blurring…
View article: Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain
Practical Learned Lossless JPEG Recompression with Multi-Level Cross-Channel Entropy Model in the DCT Domain Open
JPEG is a popular image compression method widely used by individuals, data center, cloud storage and network filesystems. However, most recent progress on image compression mainly focuses on uncompressed images while ignoring trillions of…
View article: ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding
ELIC: Efficient Learned Image Compression with Unevenly Grouped Space-Channel Contextual Adaptive Coding Open
Recently, learned image compression techniques have achieved remarkable performance, even surpassing the best manually designed lossy image coders. They are promising to be large-scale adopted. For the sake of practicality, a thorough inve…
View article: Post-Training Quantization for Cross-Platform Learned Image Compression
Post-Training Quantization for Cross-Platform Learned Image Compression Open
It has been witnessed that learned image compression has outperformed conventional image coding techniques and tends to be practical in industrial applications. One of the most critical issues that need to be considered is the non-determin…
View article: TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding
TransRefer3D: Entity-and-Relation Aware Transformer for Fine-Grained 3D Visual Grounding Open
Recently proposed fine-grained 3D visual grounding is an essential and challenging task, whose goal is to identify the 3D object referred by a natural language sentence from other distractive objects of the same category. Existing works us…
View article: HLIC: Harmonizing Optimization Metrics in Learned Image Compression by Reinforcement Learning
HLIC: Harmonizing Optimization Metrics in Learned Image Compression by Reinforcement Learning Open
Learned image compression is making good progress in recent years. Peak signal-to-noise ratio (PSNR) and multi-scale structural similarity (MS-SSIM) are the two most popular evaluation metrics. As different metrics only reflect certain asp…
View article: Checkerboard Context Model for Efficient Learned Image Compression
Checkerboard Context Model for Efficient Learned Image Compression Open
For learned image compression, the autoregressive context model is proved effective in improving the rate-distortion (RD) performance. Because it helps remove spatial redundancies among latent representations. However, the decoding process…
View article: Coarse-to-Fine Image Inpainting via Region-wise Convolutions and Non-Local Correlation
Coarse-to-Fine Image Inpainting via Region-wise Convolutions and Non-Local Correlation Open
Recently deep neural networks have achieved promising performance for filling large missing regions in image inpainting tasks. They usually adopted the standard convolutional architecture over the corrupted image, where the same convolutio…