23 citations · 36 across the 29 of their papers we have counts for
32 papers
OP2GS: Object-Aware 3D Gaussian Splatting with Dual-Opacity Primitives
Guiyu Liu, Niklas Vaara, Janne Mustaniemi +2
3D Gaussian Splatting (3DGS) provides an explicit and efficient scene representation, but its primitives lack inherent object-level identity, hindering downstream tasks such as ope…
Differentiable Ray Tracing with Gaussians for Unified Radio Propagation Simulation and View Synthesis
Niklas Vaara, Lam Huynh, Pekka Sangi +2
Explicit neural representations such as 3D Gaussian Splatting (3DGS) enable high-fidelity and real-time novel view synthesis, yet optimize for alpha-composited optical appearance r…
Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting
Tsuheng Hsu, Guiyu Liu, Juho Kannala +1
Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level 3D segmentation. However, the su…
Towards an Automated Multimodal Approach for Video Summarization: Building a Bridge Between Text, Audio and Facial Cue-Based Summarization
Md Moinul Islam, Sofoklis Kakouros, Janne Heikkilä +1
The increasing volume of video content in educational, professional, and social domains necessitates effective summarization techniques that go beyond traditional unimodal approach…
Uncovering Bias in Foundation Models: Impact, Testing, Harm, and Mitigation
Shuzhou Sun, Li Liu, Yongxiang Liu +4
Bias in Foundation Models (FMs) - trained on vast datasets spanning societal and historical knowledge - poses significant challenges for fairness and equity across fields such as h…
Ray Launching-Based Computation of Exact Paths with Noisy Dense Point Clouds
Niklas Vaara, Pekka Sangi, Miguel Bordallo López +1
Point clouds have been a recent interest for ray tracing-based radio channel characterization, as sensors such as RGB-D cameras and laser scanners can be utilized to generate an ac…
GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting
Dingding Cai, Janne Heikkilä, Esa Rahtu
This paper introduces GS-Pose, a unified framework for localizing and estimating the 6D pose of novel objects. GS-Pose begins with a set of posed RGB images of a previously unseen…
A Ray Launching Approach for Computing Exact Paths with Point Clouds
Niklas Vaara, Pekka Sangi, Miguel Bordallo López +1
Ray tracing is a deterministic method that produces propagation paths between a transmitter and a receiver. The simulation accuracy is significantly influenced by the environment d…
DiverseDream: Diverse Text-to-3D Synthesis with Augmented Text Embedding
Uy Dieu Tran, Minh Luu, Phong Ha Nguyen +2
Text-to-3D synthesis has recently emerged as a new approach to sampling 3D models by adopting pretrained text-to-image models as guiding visual priors. An intriguing but underexplo…
Unbiased Scene Graph Generation via Two-stage Causal Modeling
Shuzhou Sun, Shuaifeng Zhi, Qing Liao +2
Despite the impressive performance of recent unbiased Scene Graph Generation (SGG) methods, the current debiasing literature mainly focuses on the long-tailed distribution problem,…
Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation
Mayu Otani, Riku Togashi, Yu Sawai +5
Human evaluation is critical for validating the performance of text-to-image generative models, as this highly cognitive process requires deep comprehension of text and images. How…
MSDA: Monocular Self-supervised Domain Adaptation for 6D Object Pose Estimation
Dingding Cai, Janne Heikkilä, Esa Rahtu
Acquiring labeled 6D poses from real images is an expensive and time-consuming task. Though massive amounts of synthetic RGB images are easy to obtain, the models trained on them s…
BS3D: Building-scale 3D Reconstruction from RGB-D Images
Janne Mustaniemi, Juho Kannala, Esa Rahtu +2
Various datasets have been proposed for simultaneous localization and mapping (SLAM) and related problems. Existing datasets often include small environments, have incomplete groun…
Sparse resultant based minimal solvers in computer vision and their connection with the action matrix
Snehal Bhayani, Janne Heikkilä, Zuzana Kukelova
Many computer vision applications require robust and efficient estimation of camera geometry from a minimal number of input data measurements, i.e., solving minimal problems in a R…
Partially calibrated semi-generalized pose from hybrid point correspondences
Snehal Bhayani, Viktor Larsson, Torsten Sattler +2
In this paper we study the problem of estimating the semi-generalized pose of a partially calibrated camera, i.e., the pose of a perspective camera with unknown focal length w.r.t.…
SC6D: Symmetry-agnostic and Correspondence-free 6D Object Pose Estimation
Dingding Cai, Janne Heikkilä, Esa Rahtu
This paper presents an efficient symmetry-agnostic and correspondence-free framework, referred to as SC6D, for 6D object pose estimation from a single monocular RGB image. SC6D req…
Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis
Phong Nguyen-Ha, Lam Huynh, Esa Rahtu +2
We present CG-NeRF, a cascade and generalizable neural radiance fields method for view synthesis. Recent generalizing view synthesis methods can render high-quality novel views usi…
OVE6D: Object Viewpoint Encoding for Depth-based 6D Object Pose Estimation
Dingding Cai, Janne Heikkilä, Esa Rahtu
This paper proposes a universal framework, called OVE6D, for model-based 6D object pose estimation from a single depth image and a target object mask. Our model is trained using pu…
AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval
Riku Togashi, Mayu Otani, Yuta Nakashima +3
Evaluation measures have a crucial impact on the direction of research. Therefore, it is of utmost importance to develop appropriate and reliable evaluation measures for new applic…
Optimal Correction Cost for Object Detection Evaluation
Mayu Otani, Riku Togashi, Yuta Nakashima +3
Mean Average Precision (mAP) is the primary evaluation measure for object detection. Although object detection has a broad range of applications, mAP evaluates detectors in terms o…
Fast Neural Architecture Search for Lightweight Dense Prediction Networks
Lam Huynh, Esa Rahtu, Jiri Matas +1
We present LDP, a lightweight dense prediction neural architecture search (NAS) framework. Starting from a pre-defined generic backbone, LDP applies the novel Assisted Tabu Search…
Free-Viewpoint RGB-D Human Performance Capture and Rendering
Phong Nguyen-Ha, Nikolaos Sarafianos, Christoph Lassner +2
Capturing and faithfully rendering photo-realistic humans from novel views is a fundamental problem for AR/VR applications. While prior work has shown impressive performance captur…
Lightweight Monocular Depth with a Novel Neural Architecture Search Method
Lam Huynh, Phong Nguyen, Jiri Matas +2
This paper presents a novel neural architecture search method, called LiDNAS, for generating lightweight monocular depth estimation models. Unlike previous neural architecture sear…
Monocular Depth Estimation Primed by Salient Point Detection and Normalized Hessian Loss
Lam Huynh, Matteo Pedone, Phong Nguyen +3
Deep neural networks have recently thrived on single image depth estimation. That being said, current developments on this topic highlight an apparent compromise between accuracy a…