6 papers
CL4D: Contrastive Language-4D Pretraining for Vision-Language Reasoning in Dynamic Scenes
Kumal Hewagamage, Isuranga Senavirathne, Sasika Amarasinghe +4
4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vision encoders are largely limited…
DARB-Splatting: Generalizing Splatting with Decaying Anisotropic Radial Basis Functions
Hashiru Pramuditha, Vinasirajan Viruthshaan, Vishagar Arunan +4
Splatting-based 3D reconstruction methods have gained popularity with the advent of 3D Gaussian Splatting, efficiently synthesizing high-quality novel views. These methods commonly…
SemAlign: Language Guided Semi-supervised Domain Generalization
Muditha Fernando, Kajhanan Kailainathan, Krishnakanth Nagaratnam +2
Semi-supervised Domain Generalization (SSDG) addresses the challenge of generalizing to unseen target domains with limited labeled data. Existing SSDG methods highlight the importa…
CrossJEPA: Cross-Modal Joint-Embedding Predictive Architecture for Efficient 3D Representation Learning from 2D Images
Avishka Perera, Kumal Hewagamage, Saeedha Nazar +4
Image-to-point cross-modal learning has emerged to address the scarcity of large-scale 3D datasets in 3D representation learning. However, current methods that leverage 2D data oft…
Test-Time Optimization for Domain Adaptive Open Vocabulary Segmentation
Ulindu De Silva, Didula Samaraweera, Sasini Wanigathunga +4
We present Seg-TTO, a novel framework for zero-shot, open-vocabulary semantic segmentation (OVSS), designed to excel in specialized domain tasks. While current open-vocabulary appr…
A Feature Generator for Few-Shot Learning
Heethanjan Kanagalingam, Thenukan Pathmanathan, Navaneethan Ketheeswaran +3
Few-shot learning (FSL) aims to enable models to recognize novel objects or classes with limited labelled data. Feature generators, which synthesize new data points to augment limi…