1 citations · 3 across the 17 of their papers we have counts for
18 papers
Temporal Self-Distillation: Learning Visual State Tracking in Videos Without Supervision
Shravan Venkatraman, Wenshuai Zhao, Mohammad Hassan Vali +1
We introduce ST (Self-Supervised Self-Distillation over Time), which, to the best of our knowledge, is the first fully self-contained framework for continuous video state track…
SplatGuide: Geometric Priors from 3D Gaussians for Pose-Free Novel View Synthesis
Yejun Zhang, Zihan Wang, Xu Ji +8
Generating photorealistic novel views from unposed images requires both 3D geometric understanding and the ability to synthesize unseen content. A natural strategy combines feed-fo…
AV-JEPA: Extending LeJEPA to Audio-Visual Self-Supervised Learning
Benjamin Robson, Santeri Mentu, Wenshuai Zhao +1
We present AV-JEPA, an elegant multimodal extension of LeJEPA to audio-visual self-supervised learning. Using an early-fusion Vision Transformer and modality dropout as masking, th…
Point Tracking Improves World Action Models
Jiarui Guan, Wenshuai Zhao, Yue Pei +3
Robot policy learning benefits from world-action models that capture environment dynamics, but pixel-level prediction entangles dynamics with nuisance factors such as lighting and…
Cross-View Splatter: Feed-Forward View Synthesis with Georeferenced Images
Matias Turkulainen, Akshay Krishnan, Filippo Aleotti +6
We present Cross-View Splatter, a feed-forward method that predicts pixel-aligned Gaussian splats for outdoor scenes captured at ground level AND by satellite. Faithful reconstruct…
Latent-Compressed Variational Autoencoder for Video Diffusion Models
Jiarui Guan, Wenshuai Zhao, Zhengtao Zou +2
Video variational autoencoders (VAEs) used in latent diffusion models typically require a sufficiently large number of latent channels to ensure high-quality video reconstruction.…
PAWS: Perception of Articulation in the Wild at Scale from Egocentric Videos
Yihao Wang, Yang Miao, Wenshuai Zhao +8
Articulation perception aims to recover the motion and structure of articulated objects (e.g., drawers and cupboards), and is fundamental to 3D scene understanding in robotics, sim…
Sparsely Supervised Diffusion
Wenshuai Zhao, Zhiyuan Li, Yi Zhao +5
Diffusion models have shown remarkable success across a wide range of generative tasks. However, they often suffer from spatially inconsistent generation, arguably due to the inher…
Approximate Bayesian Inference via Bitstring Representations
Aleksanteri Sladek, Martin Trapp, Arno Solin
The machine learning community has recently put effort into quantized or low-precision arithmetics to scale large models. This paper proposes performing probabilistic inference in…
FIORD: A Fisheye Indoor-Outdoor Dataset with LIDAR Ground Truth for 3D Scene Reconstruction and Benchmarking
Ulas Gunes, Matias Turkulainen, Xuqian Ren +3
The development of large-scale 3D scene reconstruction and novel view synthesis methods mostly rely on datasets comprising perspective images with narrow fields of view (FoV). Whil…
Post-hoc Probabilistic Vision-Language Models
Anton Baumann, Rui Li, Marcus Klasson +5
Vision-language models (VLMs), such as CLIP and SigLIP, have found remarkable success in classification, retrieval, and generative tasks. For this, VLMs deterministically map image…
DeSplat: Decomposed Gaussian Splatting for Distractor-Free Rendering
Yihao Wang, Marcus Klasson, Matias Turkulainen +3
Gaussian splatting enables fast novel view synthesis in static 3D environments. However, reconstructing real-world environments remains challenging as distractors or occluders brea…
Streamlining Prediction in Bayesian Deep Learning
Rui Li, Marcus Klasson, Arno Solin +1
The rising interest in Bayesian deep learning (BDL) has led to a plethora of methods for estimating the posterior distribution. However, efficient computation of inferences, such a…
Privacy Leakage via Output Label Space and Differentially Private Continual Learning
Marlon Tobaben, Talal Alrawajfeh, Marcus Klasson +3
Differential privacy (DP) is a formal privacy framework that enables training machine learning (ML) models while protecting individuals' data. As pointed out by prior work, ML mode…
Sources of Uncertainty in 3D Scene Reconstruction
Marcus Klasson, Riccardo Mereu, Juho Kannala +1
The process of 3D scene reconstruction can be affected by numerous uncertainty sources in real-world scenes. While Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (GS) ach…
Flatness Improves Backbone Generalisation in Few-shot Classification
Rui Li, Martin Trapp, Marcus Klasson +1
Deployment of deep neural networks in real-world settings typically requires adaptation to new tasks with few examples. Few-shot classification (FSC) provides a solution to this pr…
Gaussian Splatting on the Move: Blur and Rolling Shutter Compensation for Natural Camera Motion
Otto Seiskari, Jerry Ylilammi, Valtteri Kaatrasalo +5
High-quality scene reconstruction and novel view synthesis based on Gaussian Splatting (3DGS) typically require steady, high-quality photographs, often impractical to capture with…
Subtractive Mixture Models via Squaring: Representation and Learning
Lorenzo Loconte, Aleksanteri M. Sladek, Stefan Mengel +4
Mixture models are traditionally represented and learned by adding several distributions as components. Allowing mixtures to subtract probability mass or density can drastically re…