- Read more about PROGRESSIVE PASSIVE NON-LINE-OF-SIGHT IMAGING WITH LARGE MODEL PRIORS
- Log in to post comments
Passive non-line-of-sight (NLOS) imaging has developed rapidly in recent years. However, existing models generally suffer from low-quality reconstruction due to the severe loss of information during the projection process. This paper proposes a two-stage passive NLOS imaging approach, aimed at reconstructing high-quality complicated hidden scenes. In the first stage, we train a coarse reconstruction network based on the optimal transport principle and using vector quantization to learn discrete priors for projection image encoding.
- Categories:
- Read more about Supplementary Materials for "EXPLAINING 3D OBJECT DETECTION THROUGH SHAPLEY VALUE-BASED ATTRIBUTION MAP"
- Log in to post comments
Supplementary materials of ICIP 2024
Title: "EXPLAINING 3D OBJECT DETECTION THROUGH SHAPLEY VALUE-BASED ATTRIBUTION MAP"
- Categories:
- Read more about SUPPLEMENTARY MATERIAL - SWISS: FLEXIBLE, UNIFIED WEAKLY-SUPERVISED INSTANCE SEGMENTATION UTILIZING FOUNDATION MODELS
- Log in to post comments
Supplementary material of ICIP 2024 submission SWISS: FLEXIBLE, UNIFIED WEAKLY-SUPERVISED INSTANCE SEGMENTATION UTILIZING FOUNDATION MODELS
- Categories:
- Read more about Towards Validating Face Editing Ability in Generative Models (Supp)
- Log in to post comments
The document is the supplementary materials of the paper of "Towards Validating Face Editing Ability in Generative Models" to provide more quantitative and qualitative results complementing the main paper.
- Categories:
- Read more about SimSAM: Simple Siamese Representations Based Semantic Affinity Matrix for Unsupervised Image Segmentation
- 1 comment
- Log in to post comments
Recent developments in self-supervised learning (SSL) have made it possible to learn data representations without the need for annotations.
, which enhances the performance of various downstream tasks.
- Categories:
- Read more about Supplementary Video - Unsupervised Coordinate-Based Video Denoising
- 1 comment
- Log in to post comments
In this paper, we introduce a novel unsupervised video denoising deep learning approach that can help to mitigate data scarcity issues and shows robustness against different noise patterns, enhancing its broad applicability. Our method comprises three modules: a Feature generator creating features maps, a Denoise-Net generating denoised but slightly blurry reference frames, and a Refine-Net re-introducing high-frequency details.
- Categories:
- Read more about FINE-GRAINED TEXT TO IMAGE SYNTHESIS SUPPLEMENTARY MATERIALS
- Log in to post comments
FINE-GRAINED TEXT TO IMAGE SYNTHESIS SUPPLEMENTARY MATERIALS
- Categories:
- Read more about Frequency Modulated Deformable Transformer for Underwater Image Enhancement
- Log in to post comments
Underwater images often suffer from degradation due to refraction, back-scattering, and absorption, resulting in color cast, blur, and limited visibility. Such degradation hampers higher-level computer vision applications in autonomous underwater vehicles. Existing methods for enhancing degraded images often fail to preserve fine edges and true colors. Hence, an effective pre-processing network is vital for underwater image enhancement. Addressing this need, we propose a frequency modulated deformable transformer network.
- Categories:
- Read more about Supplementary Material: Latent Enhancing AutoEncoder for Occluded Image Classification
- Log in to post comments
This document provides supplementary material for the paper titled “Latent Enhancing AutoEncoder for Occluded Image Classification” submitted to the regular track of the ICIP 2024. This document consists of details of the architecture of the LEARN, illustration of improvements in inter-class differentiability in latent space for OccludedPASCAL3D+ dataset (hereafter referred to as Pascal), and detailed classification results.
- Categories:
- Read more about Supplementary of Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correction
- Log in to post comments
Supplementary of Learning with Instance-Dependent Noisy Labels by Anchor Hallucination and Hard Sample Label Correction
- Categories: