9 citations · 11 across the 9 of their papers we have counts for
12 papers · 1 filter
GraphWrit3R: End-to-End 3D Scene Graph Writing
Luka Milivojevic, Nikola Popovic, Sayan Deb Sarkar +4
3D scene graphs provide a structured representation of complex environments by encoding objects, their semantic attributes, and the spatial and functional relationships between the…
Chorus: Multi-Teacher Pretraining for Holistic 3D Gaussian Scene Encoding
Yue Li, Qi Ma, Runyi Yang +8
While 3DGS has emerged as a high-fidelity scene representation, encoding rich, general-purpose features directly from its primitives remains under-explored. We address this gap by…
SceneSplat++: A Large Dataset and Comprehensive Benchmark for Language Gaussian Splatting
Mengjiao Ma, Qi Ma, Yue Li +10
3D Gaussian Splatting (3DGS) serves as a highly performant and efficient encoding of scene geometry, appearance, and semantics. Moreover, grounding language in 3D scenes has proven…
SceneSplat: Gaussian Splatting-based Scene Understanding with Vision-Language Pretraining
Yue Li, Qi Ma, Runyi Yang +10
Recognizing arbitrary or previously unseen categories is essential for comprehensive real-world 3D scene understanding. Currently, all existing methods rely on 2D or textual modali…
Leveraging Driver Field-of-View for Multimodal Ego-Trajectory Prediction
M. Eren Akbiyik, Nedko Savov, Danda Pani Paudel +5
Understanding drivers' decision-making is crucial for road safety. Although predicting the ego-vehicle's path is valuable for driver-assistance systems, existing methods mainly foc…
Model-aware 3D Eye Gaze from Weak and Few-shot Supervisions
Nikola Popovic, Dimitrios Christodoulou, Danda Pani Paudel +2
The task of predicting 3D eye gaze from eye images can be performed either by (a) end-to-end learning for image-to-gaze mapping or by (b) fitting a 3D eye model onto images. The fo…
Surface Normal Clustering for Implicit Representation of Manhattan Scenes
Nikola Popovic, Danda Pani Paudel, Luc Van Gool
Novel view synthesis and 3D modeling using implicit neural field representation are shown to be very effective for calibrated multi-view cameras. Such representations are known to…
Gradient Obfuscation Checklist Test Gives a False Sense of Security
Nikola Popovic, Danda Pani Paudel, Thomas Probst +1
One popular group of defense techniques against adversarial attacks is based on injecting stochastic noise into the network. The main source of robustness of such stochastic defens…
Spatially Multi-conditional Image Generation
Ritika Chakraborty, Nikola Popovic, Danda Pani Paudel +2
In most scenarios, conditional image generation can be thought of as an inversion of the image understanding process. Since generic image understanding involves solving multiple ta…
Improving the Behaviour of Vision Transformers with Token-consistent Stochastic Layers
Nikola Popovic, Danda Pani Paudel, Thomas Probst +1
We introduce token-consistent stochastic layers in vision transformers, without causing any severe drop in performance. The added stochasticity improves network calibration, robust…
Rethinking Global Context in Crowd Counting
Guolei Sun, Yun Liu, Thomas Probst +3
This paper investigates the role of global context for crowd counting. Specifically, a pure transformer is used to extract features with global information from overlapping image p…
CompositeTasking: Understanding Images by Spatial Composition of Tasks
Nikola Popovic, Danda Pani Paudel, Thomas Probst +2
We define the concept of CompositeTasking as the fusion of multiple, spatially distributed tasks, for various aspects of image understanding. Learning to perform spatially distribu…