AIConfPaper
← Search

Suman Saha

8 accepted papers

2025

GEM: A Generalizable Ego-Vision Multimodal World Model for Fine-Grained Ego-Motion, Object Dynamics, and Scene Composition Control

Mariam Hassan, Sebastian Stapf, Ahmad Rahimi, Pedro M B Rezende, Yasaman Haghighi, David Brüggemann +14
CVPR 2025poster

We present GEM, a Generalizable Ego-vision Multimodal world model that predicts future frames using a reference frame, sparse features, human poses, and ego-trajectories. Hence, our model has precise control over object dynamics, ego-agent motion and human poses. GEM generates paired RGB and depth o…

Cited by 8Source ↗PDF ↗code ↗Scholar ↗
2024

Four Ways to Improve Verbo-visual Fusion for Dense 3D Visual Grounding

Ozan Unal*, Christos Sakaridis, Suman Saha, Luc Van Gool
ECCV 2024poster

"3D visual grounding is the task of localizing the object in a 3D scene which is referred by a description in natural language. With a wide range of applications ranging from autonomous indoor robotics to AR/VR, the task has recently risen in popularity. A common formulation to tackle 3D visual grou…

Cited by 14Source ↗PDF ↗code ↗Scholar ↗
2023

EDAPS: Enhanced Domain-Adaptive Panoptic Segmentation

Suman Saha, Lukas Hoyer, Anton Obukhov, Dengxin Dai, Luc Van Gool
ICCV 2023poster

With autonomous industries on the rise, domain adaptation of the visual perception stack is an important research direction due to the cost savings promise. Much prior art was dedicated to domain-adaptive semantic segmentation in the synthetic-to-real context. Despite being a crucial output of the p…

Cited by 14PDF ↗code ↗Scholar ↗
2021

Learning To Relate Depth and Semantics for Unsupervised Domain Adaptation

Suman Saha, Anton Obukhov, Danda Pani Paudel, Menelaos Kanakis, Yuhua Chen, Stamatios Georgoulis +1
CVPR 2021poster

We present an approach for encoding visual task relationships to improve model performance in an Unsupervised Domain Adaptation (UDA) setting. Semantic segmentation and monocular depth estimation are shown to be complementary tasks; in a multi-task learning setting, a proper encoding of their relati…

Cited by 70PDF ↗code ↗Scholar ↗
2021

Three Ways To Improve Semantic Segmentation With Self-Supervised Depth Estimation

Lukas Hoyer, Dengxin Dai, Yuhua Chen, Adrian Koring, Suman Saha, Luc Van Gool
CVPR 2021poster

Training deep networks for semantic segmentation requires large amounts of labeled training data, which presents a major challenge in practice, as labeling segmentation masks is a highly labor-intensive process. To address this issue, we present a framework for semi-supervised semantic segmentation,…

Cited by 115PDF ↗code ↗Scholar ↗
2020

Reparameterizing Convolutions for Incremental Multi-Task Learning without Task Interference

Menelaos Kanakis, David Bruggemann, Suman Saha, Stamatios Georgoulis, Anton Obukhov, Luc Van Gool
ECCV 2020poster

Multi-task networks are commonly utilized to alleviate the need for a large number of highly specialized single-task networks. However, two common challenges in developing multi-task models are often overlooked in literature. First, enabling the model to be inherently incremental, continuously incor…

Cited by 104Source ↗PDF ↗code ↗Scholar ↗
2017

Online Real-Time Multiple Spatiotemporal Action Localisation and Prediction

Gurkirt Singh, Suman Saha, Michael Sapienza, Philip H. S. Torr, Fabio Cuzzolin
ICCV 2017poster

We present a deep-learning framework for real-time multiple spatio-temporal (S/T) action localisation and classification. Current state-of-the-art approaches work offline, and are too slow to be useful in real-world settings. To overcome their limitations we introduce two major developments. Firstly…

Cited by 384PDF ↗Scholar ↗