Picture for Aljosa Smolic

Aljosa Smolic

StylePrompter: All Styles Need Is Attention

Add code
Jul 30, 2023
Figure 1 for StylePrompter: All Styles Need Is Attention
Figure 2 for StylePrompter: All Styles Need Is Attention
Figure 3 for StylePrompter: All Styles Need Is Attention
Figure 4 for StylePrompter: All Styles Need Is Attention
Viaarxiv icon

Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token

Add code
May 16, 2023
Figure 1 for Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token
Figure 2 for Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token
Figure 3 for Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token
Figure 4 for Blind Image Quality Assessment via Transformer Predicted Error Map and Perceptual Quality Token
Viaarxiv icon

BASICS: Broad quality Assessment of Static point clouds In Compression Scenarios

Add code
Feb 09, 2023
Figure 1 for BASICS: Broad quality Assessment of Static point clouds In Compression Scenarios
Figure 2 for BASICS: Broad quality Assessment of Static point clouds In Compression Scenarios
Figure 3 for BASICS: Broad quality Assessment of Static point clouds In Compression Scenarios
Figure 4 for BASICS: Broad quality Assessment of Static point clouds In Compression Scenarios
Viaarxiv icon

View Sub-sampling and Reconstruction for Efficient Light Field Compression

Aug 12, 2022
Figure 1 for View Sub-sampling and Reconstruction for Efficient Light Field Compression
Figure 2 for View Sub-sampling and Reconstruction for Efficient Light Field Compression
Figure 3 for View Sub-sampling and Reconstruction for Efficient Light Field Compression
Figure 4 for View Sub-sampling and Reconstruction for Efficient Light Field Compression
Viaarxiv icon

Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation

Aug 07, 2022
Figure 1 for Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation
Figure 2 for Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation
Figure 3 for Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation
Figure 4 for Jointformer: Single-Frame Lifting Transformer with Error Prediction and Refinement for 3D Human Pose Estimation
Viaarxiv icon

KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints

Add code
Jul 26, 2022
Figure 1 for KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
Figure 2 for KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
Figure 3 for KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
Figure 4 for KinePose: A temporally optimized inverse kinematics technique for 6DOF human pose estimation with biomechanical constraints
Viaarxiv icon

Image Aesthetics Assessment Using Graph Attention Network

Add code
Jun 28, 2022
Figure 1 for Image Aesthetics Assessment Using Graph Attention Network
Figure 2 for Image Aesthetics Assessment Using Graph Attention Network
Figure 3 for Image Aesthetics Assessment Using Graph Attention Network
Figure 4 for Image Aesthetics Assessment Using Graph Attention Network
Viaarxiv icon

TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding

Add code
Oct 17, 2021
Figure 1 for TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
Figure 2 for TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
Figure 3 for TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
Figure 4 for TEAM-Net: Multi-modal Learning for Video Action Recognition with Partial Decoding
Viaarxiv icon

Spectral analysis of re-parameterized light fields

Oct 12, 2021
Figure 1 for Spectral analysis of re-parameterized light fields
Figure 2 for Spectral analysis of re-parameterized light fields
Figure 3 for Spectral analysis of re-parameterized light fields
Figure 4 for Spectral analysis of re-parameterized light fields
Viaarxiv icon

Frequency Domain Loss Function for Deep Exposure Correction of Dark Images

Add code
May 21, 2021
Figure 1 for Frequency Domain Loss Function for Deep Exposure Correction of Dark Images
Figure 2 for Frequency Domain Loss Function for Deep Exposure Correction of Dark Images
Figure 3 for Frequency Domain Loss Function for Deep Exposure Correction of Dark Images
Figure 4 for Frequency Domain Loss Function for Deep Exposure Correction of Dark Images
Viaarxiv icon