Related papers: Cross-Color Channel Perceptually Adaptive Quantiza…
Vision-Language Models (VLMs) have demonstrated strong performance on multimodal reasoning tasks, but their deployment remains challenging due to high inference latency and computational cost, particularly when processing high-resolution…
A novel coding strategy for block-based compressive sens-ing named spatially directional predictive coding (SDPC) is proposed, which efficiently utilizes the intrinsic spatial cor-relation of natural images. At the encoder, for each block…
Model quantization reduces neural network parameter precision to achieve compression, but often compromises accuracy. Existing post-training quantization (PTQ) methods employ iterative parameter updates to preserve accuracy under high…
A quantitative analysis of post-VVC luma and chroma intra tools is presented, focusing on their statistical behaviors, in terms of block selection rate under different conditions. The aim is to provide insights to the standardization…
The growth in video Internet traffic and advancements in video attributes such as framerate, resolution, and bit-depth boost the demand to devise a large-scale, highly efficient video encoding environment. This is even more essential for…
Quantization is a fundamental optimization for many machine-learning use cases, including compressing gradients, model weights and activations, and datasets. The most accurate form of quantization is \emph{adaptive}, where the error is…
Large Vision-Language Models (VLMs) excel at general visual reasoning tasks but exhibit sharp performance degradation when applied to novel domains with substantial distribution shifts from pretraining data. Existing domain adaptation…
Image Quality Assessment (IQA) aims to evaluate the perceptual quality of images based on human subjective perception. Existing methods generally combine multiscale features to achieve high performance, but most rely on straightforward…
Mixture-of-Experts(MoE) Vision-Language Models (VLMs) offer remarkable performance but incur prohibitive memory and computational costs, making compression essential. Post-Training Quantization (PTQ) is an effective training-free technique…
This paper accelerates video perception, such as semantic segmentation and human pose estimation, by levering cross-frame redundancies. Unlike the existing approaches, which avoid redundant computations by warping the past features using…
The application of the context-adaptive entropy model significantly improves the rate-distortion (R-D) performance, in which hyperpriors and autoregressive models are jointly utilized to effectively capture the spatial redundancy of the…
In streaming media services, video transcoding is a common practice to alleviate bandwidth demands. Unfortunately, traditional methods employing a uniform rate factor (RF) across all videos often result in significant inefficiencies.…
Video Quality Assessment (VQA), which intends to predict the perceptual quality of videos, has attracted increasing attention. Due to factors like motion blur or specific distortions, the quality of different regions in a video varies.…
Scalable lossless video coding is an important aspect for many professional applications. Wavelet-based video coding decomposes an input sequence into a lowpass and a highpass subband by filtering along the temporal axis. The lowpass…
Deep image compression systems mainly contain four components: encoder, quantizer, entropy model, and decoder. To optimize these four components, a joint rate-distortion framework was proposed, and many deep neural network-based methods…
Fully test-time adaptation aims to adapt the network model based on sequential analysis of input samples during the inference stage to address the cross-domain performance degradation problem of deep neural networks. This work is based on…
We present the Colorization Transformer, a novel approach for diverse high fidelity image colorization based on self-attention. Given a grayscale image, the colorization proceeds in three steps. We first use a conditional autoregressive…
In this paper, we propose a preprocessing method for conventional image and video encoders that can make these existing encoders content-aware. By going through our process, a higher quality parameter could be set on a traditional encoder…
The ability to localize transmission loss change to a subset of links in optical networks is crucial for maintaining network reliability, performance and security. \emph{Quantum probes}, implemented by sending blocks of $n$ coherent-state…
Pretraining 3D encoders by aligning with Contrastive Language Image Pretraining (CLIP) has emerged as a promising direction to learn generalizable representations for 3D scene understanding. In this paper, we propose UniScene3D, a…