Publications
Our papers and articles
117 publications, auto-synced daily from OpenAlex.
-
M3ashy: Multi-modal material synthesis via hyperdiffusion
-
Multigranular evaluation for brain visual decoding
-
Physically Based Neural BRDF: A Framework for Physically Correct Material Reconstruction, Generation and Editing
-
Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos
-
Matryoshka Gaussian Splatting
-
PoseCraft: Tokenized 3D Body Landmark and Camera Conditioning for Photorealistic Human Image Synthesis
-
Learning-guided Kansa collocation for forward and inverse PDEs beyond linearity
-
Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidance
-
αsurf: Implicit surface reconstruction for semi-transparent and thin objects with decoupled geometry and opacity
-
Gaussian head & shoulders: High fidelity neural upper body avatars with anchor gaussian guided texture warping
-
Chord: Generation of collision-free, house-scale, and organized digital twins for 3d indoor scenes with controllable floor plans and optimal layouts
-
Multispectral fine-grained classification of blackgrass in wheat and barley crops
-
Exploring the visual feature space for multimodal neural decoding
-
Arf-plus: Controlling perceptual factors in artistic radiance fields for 3d scene stylization
-
Restereo: Diffusion stereo video generation and restoration
-
Demystifying noise: Role of randomness in generative AI: Demystifying randomness in generative AI
-
Demystifying noise: The role of randomness in generative AI
-
Features Emerge as Discrete States: The First Application of SAEs to 3D Representations
-
Twist and Compute: The Cost of Pose in 3D Generative Diffusion
-
Self-Supervised Implicit Attention Priors for Point Cloud Reconstruction
-
PSHead: 3D Head Reconstruction from a Single Image with Diffusion Prior and Self‐Enhancement
-
FreNBRDF: A Frequency-Rectified Neural Material Representation
-
SYM3D: Canonicalizing Triplanes via Symmetry for Single-View 3D Learning
-
Best Foot Forward: Robust Foot Reconstruction in-the-wild
-
Blue noise for diffusion models
-
Dream: Visual decoding from reversing human visual system
-
Umbrae: Unified multimodal brain decoding
-
Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front‐Facing Views
-
Feed-forward bullet-time reconstruction of dynamic scenes from monocular videos
-
Proceedings of the IEEE/CVF winter conference on applications of computer vision (WACV)
-
Zero-shot machine unlearning at scale via lipschitz regularization
-
Frepolad: Frequency-rectified point latent diffusion for point cloud generation
-
An information theoretic approach to machine unlearning
-
Hypernetworks for generalizable brdf representation
-
Physically based neural bidirectional reflectance distribution function
-
SYM3D: learning symmetric triplanes for better 3D-awareness of GANs
-
Inferring implicit 3D representations from human figures on pictorial maps
-
Neumadiff: Neural material synthesis via hyperdiffusion
-
NeRF as Pretraining at Scale: Generalizable 3D-Aware Semantic Representation Learning from View Prediction
-
Evolutive Rendering Models
-
Blue noise for diffusion models: Supplemental document
-
3d gan inversion with facial symmetry prior
-
CLIP-PAE: Projection-augmentation embedding to extract relevant features for a disentangled, interpretable and controllable text-guided face manipulation
-
Differentiable visual computing for inverse problems and machine learning
-
Cuf: Continuous upsampling filters
-
Neural fields with hard constraints of arbitrary differential order
-
Techniques for understanding how trained neural networks operate
-
Learning-based sampling for image matting
-
Hypernetworks for generalizable BRDF estimation
-
One-shot Detail Retouching with Patch Space Neural Transformation Blending
-
Multi-view video datasets for evaluation of NeRF and Neural View Synthesis methods
-
Kubric: A scalable dataset generator
-
D^ 2nerf: Self-supervised decoupling of dynamic and static objects from a monocular video
-
Controllable shadow generation using pixel height maps
-
Path Guiding Using Spatio‐Directional Mixture Models
-
Statistical shape representations for temporal registration of plant components in 3D
-
Instance segmentation, body part parsing, and pose estimation of human figures in pictorial maps
-
D2NeRF: Self-Supervised Decoupling of Dynamic and Static Objects from a Monocular Video. ArXiv abs/2205.15838 (2022)
-
One-shot Detail Retouching with Patch Space Neural Field based Transformation Blending.
-
Iso-points: Optimizing neural implicit surfaces with hybrid representations
-
Detection of pictorial map objects with convolutional neural networks
-
Joint estimation from images
-
Pose estimation and body tracking using an artificial neural network
-
Learning-based sampling for image matting
-
Robust Image Denoising using Kernel Predicting Networks.
-
Techniques for performing point-based inverse rendering
-
Inferring Implicit 3D Representations from Human Figures on Pictorial Maps
-
TensorFlow graphics: differentiable computer graphics in tensorflow
-
Gradient-based attribution methods
-
Differentiable surface splatting for point-based geometry processing
-
Explaining deep neural networks with a polynomial time algorithm for shapley value approximation
-
Learning-based sampling for natural image matting
-
Active mini-batch sampling using repulsive point processes
-
Tangent-space optimization for interactive animation control
-
Analysis of sample correlations for Monte Carlo rendering
-
Image processing system for downscaling images using perceptual downscaling method
-
Towards Storytelling with Animated Pictorial Map Objects–An Experiment with Convolutional Neural Networks
-
Pointpronets: Consolidation of point clouds with convolutional neural networks
-
A network architecture for point cloud classification via automatic depth images generation
-
Semantic segmentation for line drawing vectorization using neural networks
-
Monocular RGB hand pose inference from unsupervised refinable nets
-
A machine learning framework for full-reference 3D shape quality assessment
-
Sampling analysis using correlations for Monte Carlo rendering
-
Towards better understanding of gradient-based attribution methods for Deep Neural Networks. doi: 10.48550
-
Towards better understanding of gradient-based attribution methods for deep neural networks
-
Human shape from silhouettes using generative hks descriptors and cross-modal neural networks
-
Deepgarment: 3d garment shape estimation from a single image
-
How to refine 3d hand pose estimation from unlabelled depth data?
-
Enea Ceolini, A
-
General point sampling with adaptive density and correlations
-
Towards better understanding of gradient-based attribution methods for deep neural networksarXiv preprint
-
Ceolini Enea, Öztireli Cengiz, and Gross Markus. 2017. Towards better understanding of gradient-based attribution methods for deep neural networks
-
Diversified Mini-Batch Sampling using Repulsive Point Processes
-
Enea Ceolini, A. Cengiz Öztireli, and Markus H. Gross.“A unified view of gradient-based attribution methods for Deep Neural Networks.”
-
Hs-nets: Estimating human body shape from silhouettes with convolutional neural networks
-
Shape from selfies: Human body shape estimation using cca regression forests
-
Integration with stochastic point processes
-
Geometry representations with unsupervised feature learning
-
3D modeling with a symmetric sketch
-
Feature preserving point set surfaces based on non‐linear kernel regression