arXiv subjects

Taeho Kang

Publications and source records attributed to Taeho Kang.

8 recordsLinked to original sources

arXiv2026

Look Before You Edit: Attention-Guided Camera Placement and Multi-View Alignment for 3D Gaussian Splatting Editing

Text-driven 3D scene editing with 3D Gaussian Splatting (3DGS) typically applies a 2D diffusion editor to views rendered from fixed training cameras, limiting both the spatial coverage of edits and the user's freedom to target specific objects in complex scenes. We present LB-Edit, a framework that addresses two coupled problems: where to place editing cameras for localized edits, and how to make per-view edits agree with one another so that the 3D scene remains consistent after fine-tuning. First, Attention-Guided Editing Camera Placement (ACP) probes the diffusion model's self- and cross-attention at multiple candidate camera distances to find where attention is well-contained in the region of interest, then places a compact, geometrically diverse editing camera set at that attention-optimal distance. Second, Multi-view Attention Alignment (MAA) steers the editor toward the same edit across views along two axes: it aligns appearance by sharing self-attention features via token-level correspondence, and aligns spatial location by lifting cross-attention maps onto the 3D Gaussians as a shared 3D attention field, suppressing both appearance and spatial drift. Experiments on multi-object and single-object scenes show that our method achieves the highest user preference in instruction fidelity, multi-view consistency, and editing locality, using as few as 5 editing views and reducing latency by up to 7x over existing methods.

cs.CV↗

arXiv2026

Cross-View Yaw Estimation in Location Uncertainty with Line-Aligning Yaw Scoring

Accurate yaw estimation is a bottleneck in cross-view localization between ground view and Bird's Eye View (BEV). Existing methods couple yaw with translation and rely on height or projection assumptions that degrade under large yaw ambiguity. We disentangle yaw from location accuracy and introduce LAYS, a radially invariant line-consensus voting method. By exploiting the radial invariance of our formulation, we achieve sub-degree yaw precision via 3D voting over all candidate poses, while eliminating the need for accurate location. Our key observation is that a ground-image column matched to BEV pixels induces the same yaw across all camera positions along the radial direction of the pixels. LAYS matches BEV pixels to ground columns using feature similarity and accumulates the induced yaw votes into discrete 3D bins, where correct correspondences along the radial line concentrate into a sharp peak for the correct yaw. Experiments on Mapillary, Ford, KITTI, and VIGOR show significant gains under unknown yaw, particularly for normal FoV with unknown yaw (+28$\sim$45\%p), and using LAYS as a yaw prior improves downstream 3-DoF localization.

cs.CV↗

arXiv2026

I see artifacts: ICA-based EEG artifact removal does not improve deep network decoding across three BCI tasks

In this paper, we conduct a detailed investigation on the effect of independent component (IC)-based noise rejection methods in neural network classifier-based decoding of electroencephalography (EEG) data in different task datasets. We apply a pipeline matrix of two popular different independent component (IC) decomposition methods (Infomax and Adaptive Mixture Independent Component Analysis (AMICA)) with three different component rejection strategies (none, ICLabel, and multiple artifact rejection algorithm [MARA]) on three different EEG datasets (motor imagery, long-term memory formation, and visual memory). We cross-validate processed data from each pipeline with three architectures commonly used for EEG classification (two convolutional neural networks and one long short-term memory-based model. We compare decoding performances on within-participant and within-dataset levels.Our results show that the benefit from using IC-based noise rejection for decoding analyses is at best minor, as component-rejected data did not show consistently better performance than data without rejections; especially given the significant computational resources required for independent component analysis (ICA) computations.

cs.HC↗

arXiv2025

Clustered Error Correction with Grouped 4D Gaussian Splatting

Existing 4D Gaussian Splatting (4DGS) methods struggle to accurately reconstruct dynamic scenes, often failing to resolve ambiguous pixel correspondences and inadequate densification in dynamic regions. We address these issues by introducing a novel method composed of two key components: (1) Elliptical Error Clustering and Error Correcting Splat Addition that pinpoints dynamic areas to improve and initialize fitting splats, and (2) Grouped 4D Gaussian Splatting that improves consistency of mapping between splats and represented dynamic objects. Specifically, we classify rendering errors into missing-color and occlusion types, then apply targeted corrections via backprojection or foreground splitting guided by cross-view color consistency. Evaluations on Neural 3D Video and Technicolor datasets demonstrate that our approach significantly improves temporal consistency and achieves state-of-the-art perceptual rendering quality, improving 0.39dB of PSNR on the Technicolor Light Field dataset. Our visualization shows improved alignment between splats and dynamic objects, and the error correction method's capability to identify errors and properly initialize new splats. Our implementation details and source code are available at https://github.com/tho-kn/cem-4dgs.

cs.CV↗

arXiv2024

Attention-Propagation Network for Egocentric Heatmap to 3D Pose Lifting

We present EgoTAP, a heatmap-to-3D pose lifting method for highly accurate stereo egocentric 3D pose estimation. Severe self-occlusion and out-of-view limbs in egocentric camera views make accurate pose estimation a challenging problem. To address the challenge, prior methods employ joint heatmaps-probabilistic 2D representations of the body pose, but heatmap-to-3D pose conversion still remains an inaccurate process. We propose a novel heatmap-to-3D lifting method composed of the Grid ViT Encoder and the Propagation Network. The Grid ViT Encoder summarizes joint heatmaps into effective feature embedding using self-attention. Then, the Propagation Network estimates the 3D pose by utilizing skeletal information to better estimate the position of obscure joints. Our method significantly outperforms the previous state-of-the-art qualitatively and quantitatively demonstrated by a 23.9\% reduction of error in an MPJPE metric. Our source code is available in GitHub.

cs.CV↗

arXiv2023

Ego3DPose: Capturing 3D Cues from Binocular Egocentric Views

We present Ego3DPose, a highly accurate binocular egocentric 3D pose reconstruction system. The binocular egocentric setup offers practicality and usefulness in various applications, however, it remains largely under-explored. It has been suffering from low pose estimation accuracy due to viewing distortion, severe self-occlusion, and limited field-of-view of the joints in egocentric 2D images. Here, we notice that two important 3D cues, stereo correspondences, and perspective, contained in the egocentric binocular input are neglected. Current methods heavily rely on 2D image features, implicitly learning 3D information, which introduces biases towards commonly observed motions and leads to low overall accuracy. We observe that they not only fail in challenging occlusion cases but also in estimating visible joint positions. To address these challenges, we propose two novel approaches. First, we design a two-path network architecture with a path that estimates pose per limb independently with its binocular heatmaps. Without full-body information provided, it alleviates bias toward trained full-body distribution. Second, we leverage the egocentric view of body limbs, which exhibits strong perspective variance (e.g., a significantly large-size hand when it is close to the camera). We propose a new perspective-aware representation using trigonometry, enabling the network to estimate the 3D orientation of limbs. Finally, we develop an end-to-end pose reconstruction network that synergizes both techniques. Our comprehensive evaluations demonstrate that Ego3DPose outperforms state-of-the-art models by a pose estimation error (i.e., MPJPE) reduction of 23.1% in the UnrealEgo dataset. Our qualitative results highlight the superiority of our approach across a range of scenarios and challenges.

cs.CV↗

arXiv2023

Gotta Go Fast: Measuring Input/Output Latencies of Virtual Reality 3D Engines for Cognitive Experiments

Virtual Reality (VR) is seeing increased adoption across many fields. The field of experimental cognitive science is also testing utilization of the technology combined with physiological measures such as electroencephalography (EEG) and eye tracking. Quantitative measures of human behavior and cognition process, however, are sensitive to minuscule time resolutions that are often overlooked in the scope of consumer-level VR hardware and software stacks. In this preliminary study, we implement VR testing environments in two prominent 3D Virtual Reality frameworks (Unity and Unreal Engine) to measure latency values for stimulus onset execution code to Head-Mount Display (HMD) pixel change, as well as the latency between human behavioral response input to its registration in the engine environment under a typical cognitive experiment hardware setup. We find that whereas the specifics of the latency may further be influenced by different hardware and software setups, the variations in consumer hardware is apparent regardless and report detailed statistics on these latencies. Such consideration should be taken into account when designing VR-based cognitive experiments that measure human behavior.

cs.HC↗

arXiv2023

The Capella Program: Toward A Space-only High-frequency Radio VLBI Network Formed by Small Satellites in Low Earth Orbits

Very long baseline radio interferometry (VLBI) with ground-based observatories is limited by the size of Earth, the geographic distribution of antennas, and the transparency of the atmosphere. In this whitepaper, we present a design for a space-to-space VLBI program composed of two missions: Mimosa, a pathfinder, and Capella, a science-grade VLBI observatory. Mimosa is a two-element space-to-space radio interferometer composed of two small (250 kg) satellites on co-planar polar circular low Earth orbits. Using single-band, single-circular polarization heterodyne HEMT receivers operating at frequencies around 100 GHz, the interferometer is able to achieve a near-perfect visibility plane coverage and an angular resolution of approximately 35 microarcsec. Capella comprises four small (500 kg) satellites in two orthogonal polar low-Earth orbit planes. With single-band heterodyne receivers operating at frequencies around 690 GHz, the interferometer is able to achieve angular resolutions of approximately 7 microarcsec. Within a total observing time of three days, a near-complete uv plane coverage can be reached. The technology for all key components required - radio telescope, receiver, sampler, recorder, frequency standard, positioning system, data downlink, and pointing control system - is already available, partially off-the-shelf. Capella will be able to address a range of science cases, including: the shadows of supermassive black holes; the acceleration and collimation zones of plasma jets emitted from the vicinity of supermassive black holes; the chemical composition of accretion flows into active galactic nuclei through observations of molecular absorption lines; mapping supermassive binary black holes; the magnetic activity of stars; and nova eruptions of symbiotic binary stars -- and, like any substantially new observing technique, has the potential for unexpected discoveries.

astro-ph.IM↗