6 papers
iARCS: Iterative Agentic RL for Controllable 3D Scene Generation
Saugat Adhikari, Ashok Prasad Neupane, Pramish Paudel +2
Synthetic 3D scene generation is increasingly used as a data source for computer vision and embodied AI, but existing generators often optimize perceptual realism without reliably…
SA-VIS: Sparse frame Annotations for training Video Instance Segmentation
Edoardo Mello Rella, Ajad Chhatkuli, Shipra Jain +2
Recent online video instance segmentation (VIS) methods have achieved impressive results, thus becoming the preferred approach to segment instances in videos. Despite the resurgenc…
Inferring Compositional 4D Scenes without Ever Seeing One
Ahmet Berke Gokmen, Ajad Chhatkuli, Luc Van Gool +1
Scenes in the real world are often composed of several static and dynamic objects. Capturing their 4-dimensional structures, composition and spatio-temporal configuration in-the-wi…
EgoNight: Towards Egocentric Vision Understanding at Night with a Challenging Benchmark
Deheng Zhang, Yuqian Fu, Runyi Yang +9
Most existing benchmarks for understanding egocentric vision focus primarily on daytime scenarios, overlooking the low-light conditions that are inevitable in real-world applicatio…
Enhancing Semantic Segmentation with Continual Self-Supervised Pre-training
Brown Ebouky, Ajad Chhatkuli, Cristiano Malossi +3
Self-supervised learning (SSL) has emerged as a central paradigm for training foundation models by leveraging large-scale unlabeled datasets, often producing representations with s…
One2Any: One-Reference 6D Pose Estimation for Any Object
Mengya Liu, Siyuan Li, Ajad Chhatkuli +3
6D object pose estimation remains challenging for many applications due to dependencies on complete 3D models, multi-view images, or training limited to specific object categories.…