arXiv subjects

Taehyun Rhee

Publications and source records attributed to Taehyun Rhee.

6 recordsLinked to original sources

arXiv2026

Mover360: Controllable Object Manipulation in 360{\deg} Panoramic Images

We present Mover360, a controllable object manipulation framework for 360{\deg} images. Unlike perspective images, 360{\deg} images in equirectangular projection (ERP) exhibit horizontal wrap-around, latitude-dependent distortion, and global scene continuity, which makes object-level edits difficult for existing perspective editors to produce and for users to specify. To address this, Mover360 centers on object Translation (relocating a specified object within an existing panorama) while supporting reference-guided Insert and Remove as auxiliary tasks. Its interface unifies point-, bbox-, and mask-guided control by encoding each task into a fixed prompt and a compact, ERP-aligned instruction map. In the default point mode, a single click relocates an object, allowing the model to infer a plausible size, support, and illumination using panoramic context and an auxiliary depth condition. Structurally, Mover360 is a lightweight adaptation of a pretrained diffusion transformer. To generate paired supervision, we construct a UE5 data-generation pipeline with surface-aware object placement and randomized illumination, yielding large-scale paired data and a dual-domain benchmark of synthetic and real panoramas with ground truth for all three tasks. Across both test domains and two evaluation protocols, Mover360 outperforms strong baselines for perspective editing, insertion, and inpainting in reconstruction fidelity, semantic consistency, and distributional quality. Code and our benchmark dataset are available at https://zhonghaoyi.github.io/Mover360/.

cs.CV↗

arXiv2025

SE360: Semantic Edit in 360$^\circ$ Panoramas via Hierarchical Data Construction

While instruction-based image editing is emerging, extending it to 360$^\circ$ panoramas introduces additional challenges. Existing methods often produce implausible results in both equirectangular projections (ERP) and perspective views. To address these limitations, we propose SE360, a novel framework for multi-condition guided object editing in 360$^\circ$ panoramas. At its core is a novel coarse-to-fine autonomous data generation pipeline without manual intervention. This pipeline leverages a Vision-Language Model (VLM) and adaptive projection adjustment for hierarchical analysis, ensuring the holistic segmentation of objects and their physical context. The resulting data pairs are both semantically meaningful and geometrically consistent, even when sourced from unlabeled panoramas. Furthermore, we introduce a cost-effective, two-stage data refinement strategy to improve data realism and mitigate model overfitting to erase artifacts. Based on the constructed dataset, we train a Transformer-based diffusion model to allow flexible object editing guided by text, mask, or reference image in 360$^\circ$ panoramas. Our experiments demonstrate that our method outperforms existing methods in both visual quality and semantic accuracy.

cs.CV↗

arXiv2025

Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites

Consistent and natural camera lens blur is important for seamlessly blending 3D virtual objects into photographed real-scenes. Since lens blur typically varies with scene depth, the placement of virtual objects and their corresponding blur levels significantly affect the visual fidelity of mixed reality compositions. Existing pipelines often rely on camera parameters (e.g., focal length, focus distance, aperture size) and scene depth to compute the circle of confusion (CoC) for realistic lens blur rendering. However, such information is often unavailable to ordinary users, limiting the accessibility and generalizability of these methods. In this work, we propose a novel compositing approach that directly estimates the CoC map from RGB images, bypassing the need for scene depth or camera metadata. The CoC values for virtual objects are inferred through a linear relationship between its signed CoC map and depth, and realistic lens blur is rendered using a neural reblurring network. Our method provides flexible and practical solution for real-world applications. Experimental results demonstrate that our method achieves high-fidelity compositing with realistic defocus effects, outperforming state-of-the-art techniques in both qualitative and quantitative evaluations.

cs.CV↗

arXiv2025

TouchWalker: Real-Time Avatar Locomotion from Touchscreen Finger Walking

We present TouchWalker, a real-time system for controlling full-body avatar locomotion using finger-walking gestures on a touchscreen. The system comprises two main components: TouchWalker-MotionNet, a neural motion generator that synthesizes full-body avatar motion on a per-frame basis from temporally sparse two-finger input, and TouchWalker-UI, a compact touch interface that interprets user touch input to avatar-relative foot positions. Unlike prior systems that rely on symbolic gesture triggers or predefined motion sequences, TouchWalker uses its neural component to generate continuous, context-aware full-body motion on a per-frame basis-including airborne phases such as running, even without input during mid-air steps-enabling more expressive and immediate interaction. To ensure accurate alignment between finger contacts and avatar motion, it employs a MoE-GRU architecture with a dedicated foot-alignment loss. We evaluate TouchWalker in a user study comparing it to a virtual joystick baseline with predefined motion across diverse locomotion tasks. Results show that TouchWalker improves users' sense of embodiment, enjoyment, and immersion.

cs.HC↗

arXiv2023

Simulating the Geometric Growth of the Marine Sponge Crella Incrustans

Simulating marine sponge growth helps marine biologists analyze, measure, and predict the effects that the marine environment has on marine sponges, and vice versa. This paper describes a way to simulate and grow geometric models of the marine sponge Crella incrustans while considering environmental factors including fluid flow and nutrients. The simulation improves upon prior work by changing the skeletal architecture of the sponge in the growth model to better suit the structure of Crella incrustans. The change in skeletal architecture and other simulation parameters are then evaluated qualitatively against photos of a real-life Crella incrustans sponge. The results support the hypothesis that changing the skeletal architecture from radiate accretive to Halichondrid produces a sponge model which is closer in resemblance to Crella incrustans than the prior work.

cs.GR↗

arXiv2022

Deep Portrait Delighting

We present a deep neural network for removing undesirable shading features from an unconstrained portrait image, recovering the underlying texture. Our training scheme incorporates three regularization strategies: masked loss, to emphasize high-frequency shading features; soft-shadow loss, which improves sensitivity to subtle changes in lighting; and shading-offset estimation, to supervise separation of shading and texture. Our method demonstrates improved delighting quality and generalization when compared with the state-of-the-art. We further demonstrate how our delighting method can enhance the performance of light-sensitive computer vision tasks such as face relighting and semantic parsing, allowing them to handle extreme lighting conditions.

cs.CV↗