Iro Laina

21

Papers

105

Total Citations

Papers (21)

Diffusion Models for Open-Vocabulary Segmentation

SHAP-EDITOR: Instruction-Guided Latent 3D Editing in Seconds

AutoPartGen: Autoregressive 3D Part Generation and Discovery

AnimalClue: Recognizing Animals by their Traces

IM-3D: Iterative Multiview Diffusion and Reconstruction for High-Quality 3D Generation

CNN-SLAM: Real-Time Dense Monocular SLAM With Learned Depth Prediction

Guide Me: Interacting With Deep Networks

Semantic Image Manipulation Using Scene Graphs

Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization

RealFusion: 360deg Reconstruction of Any Object From a Single Image

Learning in an Uncertain World: Representing Ambiguity Through Multiple Hypotheses

Towards Unsupervised Image Captioning With Shared Multimodal Embeddings

PartGen: Part-level 3D Generation and Reconstruction with Multi-view Diffusion Models

Layered Motion Fusion: Lifting Motion Segmentation to 3D in Egocentric Videos

Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction

SynCity: Training-Free Generation of 3D Cities

Quantifying Learnability and Describability of Visual Concepts Emerging in Representation Learning

Unsupervised Part Discovery from Contrastive Reconstruction

Unsupervised Multi-Object Segmentation by Predicting Probable Motion Patterns

Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

EPIC Fields: Marrying 3D Geometry and Video Understanding