14.06.2024
MCML at CVPR 2024
The IEEE/CVF Conference on Computer Vision and Pattern Recognition 2024 (CVPR 2024). Seattle, Washington, United States, June 17-21, 2024
We are happy to announce that MCML researchers are represented with 37 papers at CVPR 2024:
FaceTalk: Audio-Driven Motion Diffusion for Neural Parametric Head Models.
DOI.
Hybrid Functional Maps for Crease-Aware Non-Isometric Shape Matching.
DOI.
Sparse Views, Near Light: A Practical Paradigm for Uncalibrated Point-light Photometric Stereo.
DOI.
Spectral Meets Spatial: Harmonising 3D Shape Matching and Interpolation.
DOI.
SecondPose: SE(3)-Consistent Dual-Stream Feature Fusion for Category-Level Pose Estimation.
DOI.
SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors.
DOI.
FutureHuman3D: Forecasting Complex Long-Term 3D Human Behavior from Video Observations.
DOI.
Partial-to-Partial Shape Matching with Geometric Consistency.
DOI.
H-ViT: A Hierarchical Vision Transformer for Deformable Image Registration.
DOI.
MonoNPHM: Dynamic Head Reconstruction from Monocular Videos.
DOI.
Boosting Self-Supervision for Single-View Scene Completion via Knowledge Distillation.
DOI.
ViewDiff: 3D-Consistent Image Generation with Text-to-Image Models.
DOI.
MatchU: Matching Unseen Objects for 6D Pose Estimation from RGB-D Images.
DOI.
HouseCat6D -- A Large-Scale Multi-Modal Category Level 6D Object Perception Dataset with Household Objects in Realistic Scenarios.
DOI.
DiffusionAvatars: Deferred Diffusion for High-fidelity 3D Head Avatars.
DOI.
LightIt: Illumination Modeling and Control for Diffusion Models.
DOI.
Intrinsic Image Diffusion for Indoor Single-view Material Estimation.
DOI.
MultiDiff: Consistent Novel View Synthesis from a Single Image.
DOI.
Compressed 3D Gaussian Splatting for Accelerated Novel View Synthesis.
DOI.
GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians.
DOI.
Deep Video Codec Control for Vision Models. (Workshop paper).
PDF.
A Perspective on Deep Vision Performance with Standard Image and Video Codecs. (Workshop paper).
PDF.
UnScene3D: Unsupervised 3D Instance Segmentation for Indoor Scenes.
DOI.
MeshGPT: Generating Triangle Meshes with Decoder-Only Transformers.
DOI.
DPHMs: Diffusion Parametric Head Models for Depth-based Tracking.
DOI.
DiffuScene: Denoising Diffusion Models for Generative Indoor Scene Synthesis.
DOI.
SatSynth: Augmenting Image-Mask Pairs through Diffusion Models for Aerial Semantic Segmentation.
DOI.
Finsler-Laplace-Beltrami Operators with Application to Shape Analysis.
DOI.
Flattening the Parent Bias: Hierarchical Semantic Segmentation in the Poincaré Ball.
DOI.
Cache Me if You Can: Accelerating Diffusion Models through Block Caching.
DOI.
Dynamic LiDAR Re-simulation using Compositional Neural Fields.
DOI.
MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation. (Workshop paper).
URL.
14.06.2024
Related
©LMU/TUM
16.10.2024
MCML PI Alexander Fraser receives EU funding for research on LLMs
Our PI Alexander Fraser is leading a new EU-funded research initiative focused on advancing large language models (LLMs) and their societal impacts.
10.09.2024
MCML at ECML-PKDD 2024
We are happy to announce that MCML researchers are represented at ECML-PKDD 2024.
14.08.2024
MCML at ACL 2024
We are happy to announce that MCML researchers are represented at the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024).
20.07.2024
MCML at ICML 2024
We are happy to announce that MCML researchers are represented at the 41st International Conference on Machine Learning (ICML 2024).
15.07.2024
MCML at UAI 2024
We are happy to announce that MCML researchers are represented at the 40th Conference on Uncertainty in Artificial Intelligence (UAI 2024).