88 citations · 226 across the 15 of their papers we have counts for
14 papers · 1 filter
Diversify Diffusion with Temperature Sampling and Variance-Corrective Time Shifting
Peizhuo Li, Emre Aksan, Alexandru-Eugen Ichim +2
Diffusion models faithfully reproduce their training distribution, but also inherit its imbalances and leave rare or under-represented modes hard to reach. A natural inference-time…
DCGrasp: Distance-aware Controllable Grasp Generation
Hiroyasu Akada, Jesús Pérez, Emre Aksan +6
Generating 3D hand-object interactions is essential for applications in robotics, AR/VR, and synthetic data generation, where flexible controllability and strong generalization to…
VEPHand: View-Efficient Photometric Hand Performance Capture at Scale
Zhengyang Shen, Kai-Hung Chang, Erroll Wood +18
Robust, high-fidelity 3D hand capture, while fundamental to digital human creation, remains challenging with practical multi-view systems that balance rich photometry with the geom…
ECHO: Ego-Centric modeling of Human-Object interactions
Ilya A. Petrov, Vladimir Guzov, Riccardo Marin +5
Modeling human-object interactions (HOI) from an egocentric perspective is a critical yet challenging task, particularly when relying on sparse signals from wearable devices like s…
Optimizing Diffusion Noise Can Serve As Universal Motion Priors
Korrawe Karunratanakul, Konpat Preechakul, Emre Aksan +3
We propose Diffusion Noise Optimization (DNO), a new method that effectively leverages existing motion diffusion models as motion priors for a wide range of motion-related tasks. I…
Reconstructing Action-Conditioned Human-Object Interactions Using Commonsense Knowledge Priors
Xi Wang, Gen Li, Yen-Ling Kuo +3
We present a method for inferring diverse 3D models of human-object interactions from images. Reasoning about how humans interact with objects in complex scenes from a single 2D im…
LiP-Flow: Learning Inference-time Priors for Codec Avatars via Normalizing Flows in Latent Space
Emre Aksan, Shugao Ma, Akin Caliskan +5
Neural face avatars that are trained from multi-view data captured in camera domes can produce photo-realistic 3D reconstructions. However, at inference time, they must be driven b…
D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions
Sammy Christen, Muhammed Kocabas, Emre Aksan +3
We introduce the dynamic grasp synthesis task: given an object with a known 6D pose and a grasp reference, our goal is to generate motions that move the object to a target 6D pose.…
Convolutional Autoencoders for Human Motion Infilling
Manuel Kaufmann, Emre Aksan, Jie Song +3
In this paper we propose a convolutional autoencoder to address the problem of motion infilling for 3D human motion data. Given a start and end sequence, motion infilling aims to c…
Towards End-to-end Video-based Eye-Tracking
Seonwook Park, Emre Aksan, Xucong Zhang +1
Estimating eye-gaze from images alone is a challenging task, in large parts due to un-observable person-specific factors. Achieving high accuracy typically requires labeled data fr…
A Spatio-temporal Transformer for 3D Human Motion Prediction
Emre Aksan, Manuel Kaufmann, Peng Cao +1
We propose a novel Transformer-based architecture for the task of generative modelling of 3D human motion. Previous work commonly relies on RNN-based models considering shorter for…
Structured Prediction Helps 3D Human Motion Modelling
Emre Aksan, Manuel Kaufmann, Otmar Hilliges
Human motion prediction is a challenging and important task in many computer vision application domains. Existing work only implicitly models the spatial structure of the human ske…
Guiding InfoGAN with Semi-Supervision
Adrian Spurr, Emre Aksan, Otmar Hilliges
In this paper we propose a new semi-supervised GAN architecture (ss-InfoGAN) for image synthesis that leverages information from few labels (as little as 0.22%, max. 10% of the dat…
Learning Human Motion Models for Long-term Predictions
Partha Ghosh, Jie Song, Emre Aksan +1
We propose a new architecture for the learning of predictive spatio-temporal motion models from data alone. Our approach, dubbed the Dropout Autoencoder LSTM, is capable of synthes…