arXiv subjects

Janne Heikkilä

Publications and source records attributed to Janne Heikkilä.

At least 19 recordsLinked to original sources

arXiv2026

Scene-Agnostic Object-Centric Representation Learning for 3D Gaussian Splatting

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 supervision signals from foundation models are not fundamentally object-centric and often require additional mask pre/post-processing or specialized training and loss design to resolve mask identity conflicts across views. The learned identity of the 3D scene is scene-dependent, limiting generalizability across scenes. Therefore, we propose a dataset-level, object-centric supervision scheme to learn object representations in 3D Gaussian Splatting (3DGS). Building on a pre-trained slot attention-based Global Object Centric Learning (GOCL) module, we learn a scene-agnostic object codebook that provides consistent, identity-anchored representations across views and scenes. By coupling the codebook with the module's unsupervised object masks, we can directly supervise the identity features of 3D Gaussians without additional mask pre-/post-processing or explicit multi-view alignment. The learned scene-agnostic codebook enables object supervision and identification without per-scene fine-tuning or retraining. Our method thus introduces unsupervised object-centric learning (OCL) into 3DGS, yielding more structured representations and better generalization for downstream tasks such as robotic interaction, scene understanding, and cross-scene generalization.

cs.CV↗

arXiv2026

OP2GS: Object-Aware 3D Gaussian Splatting with Dual-Opacity Primitives

3D Gaussian Splatting (3DGS) provides an explicit and efficient scene representation, but its primitives lack inherent object-level identity, hindering downstream tasks such as open-vocabulary scene understanding. Existing methods typically address this by either distilling high-dimensional feature embeddings into Gaussians or by lifting 2D mask labels into 3D via heuristic refinement. However, feature-based approaches incur heavy storage and decoding overhead, while lifting-based pipelines remain vulnerable to label contamination: Gaussians necessary for appearance reconstruction often receive incorrect object labels during 2D-to-3D projection. We propose OP2GS, an object-aware Gaussian representation that augments each primitive with an explicit instance identity and a dedicated instance opacity $σ^{*}$ for object-mask rendering. The original opacity $σ$ remains responsible for visual reconstruction, while $σ^{*}$ models whether a Gaussian should contribute to a particular object mask. This dual-opacity formulation decouples visual existence from instance occupancy: mislabeled Gaussians can remain available for image rendering while becoming transparent in the object-mask branch. To learn this representation, we introduce a random object loss that optimizes the 1D instance occupancy field using the standard transmittance-based visibility of 3DGS. Semantic descriptors are then attached at the object level through multi-view aggregation, eliminating per-Gaussian feature storage. Compared with feature-training approaches, OP2GS achieves competitive open-vocabulary performance while significantly reducing computational overhead. Compared with training-free pipelines, it leverages physically consistent occupancy learning to resolve visibility ambiguities.

cs.CV↗

arXiv2026

Differentiable Ray Tracing with Gaussians for Unified Radio Propagation Simulation and View Synthesis

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 rather than ray-intersectable geometry. In contrast, radio-frequency (RF) digital twins require deterministic multi-bounce paths, where the geometry dictates trajectories and their associated attenuation and delay. We introduce a framework enabling differentiable RF propagation simulation directly within visually reconstructed neural scenes, allowing point-to-point path computation between arbitrary 3D locations while preserving high-quality visual rendering. Unlike conventional RF simulation pipelines that rely on manually constructed meshes, we embed Gaussian primitives into a hardware-accelerated ray tracing structure as the underlying spatial representation. By extracting physically meaningful channel impulse responses from visual-only reconstructions, we provide cross-modal evidence that neural reconstructions can serve as unified spatial representations for both electromagnetic propagation simulation and photorealistic view synthesis.

cs.CV↗

arXiv2026

Solving Minimal Problems Without Matrix Inversion Using FFT-Based Interpolation

Estimating camera geometry typically involves solving minimal problems formulated as systems of multivariate polynomial equations, which often pose computational challenges when using existing Gröbner-basis or resultant-based methods due to matrix inversion needed in the online solver. Here we propose a sampling-based, matrix inversion-free method that constructs the solvers using sparse hidden-variable resultants. The determinant polynomial in the hidden variable is efficiently reconstructed via inverse fast Fourier transform interpolation from sampled evaluations, avoiding symbolic expansion. Solving this polynomial yields the hidden variable, and the remaining unknowns are recovered by identifying rank-1 deficient submatrices and applying Cramer's rule. A greatest common divisor-based criterion ensures robust submatrix identification under noise. Experiments on diverse minimal problems demonstrate that the proposed solver achieves strong numerical stability and competitive runtime, particularly for small-scale problems, providing a practical alternative to traditional Gröbner-basis and resultant-based solvers.

cs.CV↗

arXiv2025

An End-to-End Depth-Based Pipeline for Selfie Image Rectification

Portraits or selfie images taken from a close distance typically suffer from perspective distortion. In this paper, we propose an end-to-end deep learning-based rectification pipeline to mitigate the effects of perspective distortion. We learn to predict the facial depth by training a deep CNN. The estimated depth is utilized to adjust the camera-to-subject distance by moving the camera farther, increasing the camera focal length, and reprojecting the 3D image features to the new perspective. The reprojected features are then fed to an inpainting module to fill in the missing pixels. We leverage a differentiable renderer to enable end-to-end training of our depth estimation and feature extraction nets to improve the rectified outputs. To boost the results of the inpainting module, we incorporate an auxiliary module to predict the horizontal movement of the camera which decreases the area that requires hallucination of challenging face parts such as ears. Unlike previous works, we process the full-frame input image at once without cropping the subject's face and processing it separately from the rest of the body, eliminating the need for complex post-processing steps to attach the face back to the subject's body. To train our network, we utilize the popular game engine Unreal Engine to generate a large synthetic face dataset containing various subjects, head poses, expressions, eyewear, clothes, and lighting. Quantitative and qualitative results show that our rectification pipeline outperforms previous methods, and produces comparable results with a time-consuming 3D GAN-based method while being more than 260 times faster.

cs.CV↗

arXiv2025

Differentiable High-Performance Ray Tracing-Based Simulation of Radio Propagation with Point Clouds

Ray tracing is a widely used deterministic method for radio propagation simulations, capable of producing physically accurate multipath components. The accuracy depends on the quality of the environment model and its electromagnetic properties. Recent advances in computer vision and machine learning have made it possible to reconstruct detailed environment models augmented with semantic segmentation labels. In this letter, we propose a differentiable ray tracing-based radio propagation simulator that operates directly on point clouds. We showcase the efficiency of our method by simulating multi-bounce propagation paths with up to five interactions with specular reflections and diffuse scattering in two indoor scenarios, each completing in less than 90 ms. Lastly, we demonstrate how the differentiability of electromagnetic computations can be combined with segmentation labels to learn the electromagnetic properties of the environment.

eess.SP↗

arXiv2025

Towards an Automated Multimodal Approach for Video Summarization: Building a Bridge Between Text, Audio and Facial Cue-Based Summarization

The increasing volume of video content in educational, professional, and social domains necessitates effective summarization techniques that go beyond traditional unimodal approaches. This paper proposes a behaviour-aware multimodal video summarization framework that integrates textual, audio, and visual cues to generate timestamp-aligned summaries. By extracting prosodic features, textual cues and visual indicators, the framework identifies semantically and emotionally important moments. A key contribution is the identification of bonus words, which are terms emphasized across multiple modalities and used to improve the semantic relevance and expressive clarity of the summaries. The approach is evaluated against pseudo-ground truth (pGT) summaries generated using LLM-based extractive method. Experimental results demonstrate significant improvements over traditional extractive method, such as the Edmundson method, in both text and video-based evaluation metrics. Text-based metrics show ROUGE-1 increasing from 0.4769 to 0.7929 and BERTScore from 0.9152 to 0.9536, while in video-based evaluation, our proposed framework improves F1-Score by almost 23%. The findings underscore the potential of multimodal integration in producing comprehensive and behaviourally informed video summaries.

cs.CV↗

arXiv2025

A Reverse Causal Framework to Mitigate Spurious Correlations for Debiasing Scene Graph Generation

Existing two-stage Scene Graph Generation (SGG) frameworks typically incorporate a detector to extract relationship features and a classifier to categorize these relationships; therefore, the training paradigm follows a causal chain structure, where the detector's inputs determine the classifier's inputs, which in turn influence the final predictions. However, such a causal chain structure can yield spurious correlations between the detector's inputs and the final predictions, i.e., the prediction of a certain relationship may be influenced by other relationships. This influence can induce at least two observable biases: tail relationships are predicted as head ones, and foreground relationships are predicted as background ones; notably, the latter bias is seldom discussed in the literature. To address this issue, we propose reconstructing the causal chain structure into a reverse causal structure, wherein the classifier's inputs are treated as the confounder, and both the detector's inputs and the final predictions are viewed as causal variables. Specifically, we term the reconstructed causal paradigm as the Reverse causal Framework for SGG (RcSGG). RcSGG initially employs the proposed Active Reverse Estimation (ARE) to intervene on the confounder to estimate the reverse causality, \ie the causality from final predictions to the classifier's inputs. Then, the Maximum Information Sampling (MIS) is suggested to enhance the reverse causality estimation further by considering the relationship information. Theoretically, RcSGG can mitigate the spurious correlations inherent in the SGG framework, subsequently eliminating the induced biases. Comprehensive experiments on popular benchmarks and diverse SGG frameworks show the state-of-the-art mean recall rate.

cs.CV↗

arXiv2025

A Conic Transformation Approach for Solving the Perspective-Three-Point Problem

We propose a conic transformation method to solve the Perspective-Three-Point (P3P) problem. In contrast to the current state-of-the-art solvers, which formulate the P3P problem by intersecting two conics and constructing a degenerate conic to find the intersection, our approach builds upon a new formulation based on a transformation that maps the two conics to a new coordinate system, where one of the conics becomes a standard parabola in a canonical form. This enables expressing one variable in terms of the other variable, and as a consequence, substantially simplifies the problem of finding the conic intersection. Moreover, the polynomial coefficients are fast to compute, and we only need to determine the real-valued intersection points, which avoids the requirement of using computationally expensive complex arithmetic. While the current state-of-the-art methods reduce the conic intersection problem to solving a univariate cubic equation, our approach, despite resulting in a quartic equation, is still faster thanks to this new simplified formulation. Extensive evaluations demonstrate that our method achieves higher speed while maintaining robustness and stability comparable to state-of-the-art methods.

cs.CV↗

arXiv2025

A Causal Adjustment Module for Debiasing Scene Graph Generation

While recent debiasing methods for Scene Graph Generation (SGG) have shown impressive performance, these efforts often attribute model bias solely to the long-tail distribution of relationships, overlooking the more profound causes stemming from skewed object and object pair distributions. In this paper, we employ causal inference techniques to model the causality among these observed skewed distributions. Our insight lies in the ability of causal inference to capture the unobservable causal effects between complex distributions, which is crucial for tracing the roots of model bias. Specifically, we introduce the Mediator-based Causal Chain Model (MCCM), which, in addition to modeling causality among objects, object pairs, and relationships, incorporates mediator variables, i.e., cooccurrence distribution, for complementing the causality. Following this, we propose the Causal Adjustment Module (CAModule) to estimate the modeled causal structure, using variables from MCCM as inputs to produce a set of adjustment factors aimed at correcting biased model predictions. Moreover, our method enables the composition of zero-shot relationships, thereby enhancing the model's ability to recognize such relationships. Experiments conducted across various SGG backbones and popular benchmarks demonstrate that CAModule achieves state-of-the-art mean recall rates, with significant improvements also observed on the challenging zero-shot recall rate metric.

cs.CV↗

arXiv2025

Uncovering Bias in Foundation Models: Impact, Testing, Harm, and Mitigation

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 healthcare, education, and finance. These biases, rooted in the overrepresentation of stereotypes and societal inequalities in training data, exacerbate real-world discrimination, reinforce harmful stereotypes, and erode trust in AI systems. To address this, we introduce Trident Probe Testing (TriProTesting), a systematic testing method that detects explicit and implicit biases using semantically designed probes. Here we show that FMs, including CLIP, ALIGN, BridgeTower, and OWLv2, demonstrate pervasive biases across single and mixed social attributes (gender, race, age, and occupation). Notably, we uncover mixed biases when social attributes are combined, such as gender x race, gender x age, and gender x occupation, revealing deeper layers of discrimination. We further propose Adaptive Logit Adjustment (AdaLogAdjustment), a post-processing technique that dynamically redistributes probability power to mitigate these biases effectively, achieving significant improvements in fairness without retraining models. These findings highlight the urgent need for ethical AI practices and interdisciplinary solutions to address biases not only at the model level but also in societal structures. Our work provides a scalable and interpretable solution that advances fairness in AI systems while offering practical insights for future research on fair AI technologies.

cs.LG↗

arXiv2024

GS-Pose: Generalizable Segmentation-based 6D Object Pose Estimation with 3D Gaussian Splatting

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 object and builds three distinct representations stored in a database. At inference, GS-Pose operates sequentially by locating the object in the input image, estimating its initial 6D pose using a retrieval approach, and refining the pose with a render-and-compare method. The key insight is the application of the appropriate object representation at each stage of the process. In particular, for the refinement step, we leverage 3D Gaussian splatting, a novel differentiable rendering technique that offers high rendering speed and relatively low optimization time. Off-the-shelf toolchains and commodity hardware, such as mobile phones, can be used to capture new objects to be added to the database. Extensive evaluations on the LINEMOD and OnePose-LowTexture datasets demonstrate excellent performance, establishing the new state-of-the-art. Project page: https://dingdingcai.github.io/gs-pose.

cs.CV↗

arXiv2024

Ray Launching-Based Computation of Exact Paths with Noisy Dense Point Clouds

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 accurate virtual copy of a physical environment. In this paper, a novel ray launching algorithm is presented, which operates directly on noisy point clouds acquired from sensor data. It produces coarse paths that are further refined to exact paths consisting of reflections and diffractions. A commercial ray tracing tool is utilized as the baseline for validating the simulated paths. A significant majority of the baseline paths is found. The robustness to noise is examined by artificially applying noise along the normal vector of each point. It is observed that the proposed method is capable of adapting to noise and finds similar paths compared to the baseline path trajectories with noisy point clouds. This is prevalent especially if the normal vectors of the points are estimated accurately. Lastly, a simulation is performed with a reconstructed point cloud and compared against channel measurements and the baseline paths. The resulting paths demonstrate similarity with the baseline path trajectories and exhibit an analogous pattern to the aggregated impulse response extracted from the measurements. Code available at https://github.com/nvaara/NimbusRT

eess.SP↗

arXiv2024

A Ray Launching Approach for Computing Exact Paths with Point Clouds

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 details. One way to capture the environment with great precision is the utilization of depth sensors and cameras. Such reconstructed environment is in the form of a point cloud. However, utilizing such data directly in ray tracing, a key aspect on vision-aided wireless communications, often involves a significant trade-off between accuracy and execution time. In this paper, we propose an open source novel and fast point cloud-based ray launching algorithm that produces exact paths, which provide a good basis for accurate modeling of radio channel characteristics. In experiments, preliminary validation of the ray tracer output is obtained with the aid of a commercial ray tracer.

eess.SP↗

arXiv2023

Sparse resultant based minimal solvers in computer vision and their connection with the action matrix

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 RANSAC framework. Minimal problems are usually formulated as complex systems of sparse polynomials. The systems usually are overdetermined and consist of polynomials with algebraically constrained coefficients. Most state-of-the-art efficient polynomial solvers are based on the action matrix method that has been automated and highly optimized in recent years. On the other hand, the alternative theory of sparse resultants and Newton polytopes has been less successful for generating efficient solvers, primarily because the polytopes do not respect the constraints on the coefficients. Therefore, in this paper, we propose a simple iterative scheme to test various subsets of the Newton polytopes and search for the most efficient solver. Moreover, we propose to use an extra polynomial with a special form to further improve the solver efficiency via a Schur complement computation. We show that for some camera geometry problems our extra polynomial-based method leads to smaller and more stable solvers than the state-of-the-art Grobner basis-based solvers. The proposed method can be fully automated and incorporated into existing tools for automatic generation of efficient polynomial solvers. It provides a competitive alternative to popular Grobner basis-based methods for minimal problems in computer vision. We also study the conditions under which the minimal solvers generated by the state-of-the-art action matrix-based methods and the proposed extra polynomial resultant-based method, are equivalent. Specifically we consider a step-by-step comparison between the approaches based on the action matrix and the sparse resultant, followed by a set of substitutions, which would lead to equivalent minimal solvers.

cs.CV↗

arXiv2023

Unbiased Scene Graph Generation via Two-stage Causal Modeling

Despite the impressive performance of recent unbiased Scene Graph Generation (SGG) methods, the current debiasing literature mainly focuses on the long-tailed distribution problem, whereas it overlooks another source of bias, i.e., semantic confusion, which makes the SGG model prone to yield false predictions for similar relationships. In this paper, we explore a debiasing procedure for the SGG task leveraging causal inference. Our central insight is that the Sparse Mechanism Shift (SMS) in causality allows independent intervention on multiple biases, thereby potentially preserving head category performance while pursuing the prediction of high-informative tail relationships. However, the noisy datasets lead to unobserved confounders for the SGG task, and thus the constructed causal models are always causal-insufficient to benefit from SMS. To remedy this, we propose Two-stage Causal Modeling (TsCM) for the SGG task, which takes the long-tailed distribution and semantic confusion as confounders to the Structural Causal Model (SCM) and then decouples the causal intervention into two stages. The first stage is causal representation learning, where we use a novel Population Loss (P-Loss) to intervene in the semantic confusion confounder. The second stage introduces the Adaptive Logit Adjustment (AL-Adjustment) to eliminate the long-tailed distribution confounder to complete causal calibration learning. These two stages are model agnostic and thus can be used in any SGG model that seeks unbiased predictions. Comprehensive experiments conducted on the popular SGG backbones and benchmarks show that our TsCM can achieve state-of-the-art performance in terms of mean recall rate. Furthermore, TsCM can maintain a higher recall rate than other debiasing methods, which indicates that our method can achieve a better tradeoff between head and tail relationships.

cs.CV↗

arXiv2023

Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation

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. However, our survey of 37 recent papers reveals that many works rely solely on automatic measures (e.g., FID) or perform poorly described human evaluations that are not reliable or repeatable. This paper proposes a standardized and well-defined human evaluation protocol to facilitate verifiable and reproducible human evaluation in future works. In our pilot data collection, we experimentally show that the current automatic measures are incompatible with human perception in evaluating the performance of the text-to-image generation results. Furthermore, we provide insights for designing human evaluation experiments reliably and conclusively. Finally, we make several resources publicly available to the community to facilitate easy and fast implementations.

cs.CV↗

arXiv2023

MSDA: Monocular Self-supervised Domain Adaptation for 6D Object Pose Estimation

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 suffer from noticeable performance degradation due to the synthetic-to-real domain gap. To mitigate this degradation, we propose a practical self-supervised domain adaptation approach that takes advantage of real RGB(-D) data without needing real pose labels. We first pre-train the model with synthetic RGB images and then utilize real RGB(-D) images to fine-tune the pre-trained model. The fine-tuning process is self-supervised by the RGB-based pose-aware consistency and the depth-guided object distance pseudo-label, which does not require the time-consuming online differentiable rendering. We build our domain adaptation method based on the recent pose estimator SC6D and evaluate it on the YCB-Video dataset. We experimentally demonstrate that our method achieves comparable performance against its fully-supervised counterpart while outperforming existing state-of-the-art approaches.

cs.CV↗