Sina Honari — accepted AI-conference papers

2026

Face2Scene: Using Facial Degradation as an Oracle for Diffusion-Based Scene Restoration

Amirhossein Kazerouni, Maitreya Suin, Tristan Aumentado-Armstrong, Sina Honari, Amanpreet Walia, Iqbal Mohomed +3

CVPR 2026

Recent advances in image restoration have enabled high-fidelity recovery of faces from degraded inputs using reference-based face restoration models (Ref-FR). However, such methods focus solely on facial regions, neglecting degradation across the full scene, including body and background, which limi

Cited by 0 Source ↗Scholar ↗

2023

Perspective Aware Road Obstacle Detection

Krzysztof Lis, Sina Honari, Pascal Fua, Mathieu Salzmann

RA-L 2023

While road obstacle detection techniques have become increasingly effective, they typically ignore the fact that, in practice, the apparent size of the obstacles decreases as their distance to the vehicle increases. In this letter, we account for this by computing a scale map encoding the apparent s

Cited by 10 Source ↗code ↗Scholar ↗

2022

Adversarial Parametric Pose Prior

Andrey Davydov, Anastasia Remizova, Victor Constantin, Sina Honari, Mathieu Salzmann, Pascal Fua

CVPR 2022oral

The Skinned Multi-Person Linear (SMPL) model represents human bodies by mapping pose and shape parameters to body meshes. However, not all pose and shape parameter values yield physically-plausible or even realistic body meshes. In other words, SMPL is under-constrained and may yield invalid results…

Cited by 44 PDF ↗code ↗Scholar ↗

2021

Benchmarking Bias Mitigation Algorithms in Representation Learning through Fairness Metrics

Charan Reddy, Deepak Sharma, Soroush Mehri, Adriana Romero-Soriano, Samira Shabanian, Sina Honari

NeurIPS 2021poster

With the recent expanding attention of machine learning researchers and practitioners to fairness, there is a void of a common framework to analyze and compare the capabilities of proposed models in deep representation learning. In this paper, we evaluate different fairness methods trained with deep…

Cited by 36 Source ↗code ↗Scholar ↗

2021

SegmentMeIfYouCan: A Benchmark for Anomaly Segmentation

Robin Chan, Krzysztof Lis, Svenja Uhlemeyer, Hermann Blum, Sina Honari, Roland Siegwart +3

NeurIPS 2021poster

State-of-the-art semantic or instance segmentation deep neural networks (DNNs) are usually trained on a closed set of semantic classes. As such, they are ill-equipped to handle previously-unseen objects. However, detecting and localizing such objects is crucial for safety-critical applications such…

Cited by 155 Source ↗code ↗Scholar ↗

2020

Lightweight Multi-View 3D Pose Estimation Through Camera-Disentangled Representation

Edoardo Remelli, Shangchen Han, Sina Honari, Pascal Fua, Robert Wang

CVPR 2020poster

We present a lightweight solution to recover 3D pose from multi-view images captured with spatially calibrated cameras. Building upon recent advances in interpretable representation learning, we exploit 3D geometry to fuse input images into a unified latent representation of pose, which is disentang…

Cited by 147 PDF ↗Scholar ↗

2019

On Adversarial Mixup Resynthesis

Christopher Beckham, Sina Honari, Vikas Verma, Alex M Lamb, Farnoosh Ghadiri, R Devon Hjelm +2

NeurIPS 2019poster

In this paper, we explore new approaches to combining information encoded within the learned representations of auto-encoders. We explore models that are capable of combining the attributes of multiple inputs such that a resynthesised output is trained to fool an adversarial discriminator for real v…

Cited by 79 Source ↗PDF ↗code ↗Scholar ↗

2018

Depth-Based 3D Hand Pose Estimation: From Current Achievements to Future Goals

Shanxin Yuan, Guillermo Garcia-Hernando, Björn Stenger, Gyeongsik Moon, Ju Yong Chang, Kyoung Mu Lee +18

CVPR 2018poster

In this paper, we strive to answer two questions: What is the current state of 3D hand pose estimation from depth images? And, what are the next challenges that need to be tackled? Following the successful Hands In the Million Challenge (HIM2017), we investigate the top 10 state-of-the-art methods o…

Cited by 277 Source ↗PDF ↗Scholar ↗

2018

Improving Landmark Localization With Semi-Supervised Learning

Sina Honari, Pavlo Molchanov, Stephen Tyree, Pascal Vincent, Christopher Pal, Jan Kautz

CVPR 2018poster

We present two techniques to improve landmark localization in images from partially annotated datasets. Our primary goal is to leverage the common situation where precise landmark locations are only provided for a small data subset, but where class labels for classification or regression tasks relat…

Cited by 211 Source ↗PDF ↗Scholar ↗

2018

Unsupervised Depth Estimation, 3D Face Rotation and Replacement

Joel Ruben Antony Moniz, Christopher Beckham, Simon Rajotte, Sina Honari, Chris Pal

NeurIPS 2018poster

We present an unsupervised approach for learning to estimate three dimensional (3D) facial structure from a single image while also predicting 3D viewpoint transformations that match a desired pose and facial geometry. We achieve this by inferring the depth of facial keypoints of an input image in a…

Cited by 43 Source ↗PDF ↗code ↗Scholar ↗

2017

Learning to Generate Samples from Noise through Infusion Training

Florian Bordes, Sina Honari, Pascal Vincent

ICLR 2017poster

In this work, we investigate a novel training procedure to learn a generative model as the transition operator of a Markov chain, such that, when applied repeatedly on an unstructured random noise sample, it will denoise it into a sample that matches the target distribution from the training set. Th…

Cited by 46 Source ↗Scholar ↗

2016

Recombinator Networks: Learning Coarse-To-Fine Feature Aggregation

Sina Honari, Jason Yosinski, Pascal Vincent, Christopher Pal

CVPR 2016spotlight

Deep neural networks with alternating convolutional, max-pooling and decimation layers are widely used in state of the art architectures for computer vision. Max-pooling purposefully discards precise spatial information in order to create features that are more robust, and typically organized as low…

Cited by 156 PDF ↗code ↗Scholar ↗