Related papers: ROI-based Deep Image Compression with Implicit Bit…
The semantic representation of deep features is essential for image context understanding, and effective fusion of features with different semantic representations can significantly improve the model's performance on salient object…
Interior tomography is a typical strategy for radiation dose reduction in computed tomography, where only a certain region-of-interest (ROI) is scanned. However, given the truncated projection data, ROI reconstruction by conventional…
In this work, we propose a new paradigm of iterative model-based reconstruction algorithms for providing real-time solution for zooming-in and refining a region of interest in medical and clinical tomographic images. This algorithmic…
Edge caching can effectively reduce backhaul burden at core network and increase quality-ofservice at wireless edge nodes. However, the beneficial role of edge caching cannot be fully realized when the offloading link is in deep fade.…
Location information is proven to benefit the deep learning models on capturing the manifold structure of target objects, and accordingly boosts the accuracy of medical image segmentation. However, most existing methods encode the location…
This paper presents a novel approach for enabling robust robotic perception in dark environments using infrared (IR) stream. IR stream is less susceptible to noise than RGB in low-light conditions. However, it is dominated by active emitter…
Instruction-guided image editing requires balancing target modification with non-target preservation. Recently, flow-based models have emerged as a strong and increasingly adopted backbone for instruction-guided image editing, thanks to…
Hierarchical LiDAR geometry compression encodes voxel occupancies from low to high bit-depths, yet prior methods treat each depth independently and re-estimate local context from coordinates at every level, limiting compression efficiency.…
The primary challenge in accelerating image super-resolution lies in reducing computation while maintaining performance and adaptability. Motivated by the observation that high-frequency regions (e.g., edges and textures) are most critical…
Steered-Mixtures-of-Experts (SMoE) models provide sparse, edge-aware representations, applicable to many use-cases in image processing. This includes denoising, super-resolution and compression of 2D- and higher dimensional pixel data.…
We consider the problem of lossy image compression with deep latent variable models. State-of-the-art methods build on hierarchical variational autoencoders (VAEs) and learn inference networks to predict a compressible latent representation…
Measurement-critical ultrasound tasks often depend on a small anatomical region, making global reconstruction metrics an unreliable proxy for clinical fidelity. We propose an ROI-aware representation learning framework and instantiate it…
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…
Fourier-encoded implicit neural representations (INRs) have shown strong capability in modeling continuous signals from discrete samples. However, conventional Fourier feature mappings use a fixed set of frequencies over the entire spatial…
We present Deep Compression Autoencoder (DC-AE), a new family of autoencoder models for accelerating high-resolution diffusion models. Existing autoencoder models have demonstrated impressive results at a moderate spatial compression ratio…
This paper proposes a novel Non-Local Attention Optimized Deep Image Compression (NLAIC) framework, which is built on top of the popular variational auto-encoder (VAE) structure. Our NLAIC framework embeds non-local operations in the…
Implicit representation mapping (IRM) can translate image features to any continuous resolution, showcasing its potent capability for ultra-high-resolution image segmentation refinement. Current IRM-based methods for refining…
Recent advancements in deep learning-based image compression are notable. However, prevalent schemes that employ a serial context-adaptive entropy model to enhance rate-distortion (R-D) performance are markedly slow. Furthermore, the…
The exploration of mutual-benefit cross-domains has shown great potential toward accurate self-supervised depth estimation. In this work, we revisit feature fusion between depth and semantic information and propose an efficient local…
Surveillance and security scenarios usually require high efficient facial image compression scheme for face recognition and identification. While either traditional general image codecs or special facial image compression schemes only…