arXiv subjects

Sang-Hyun Lee

Publications and source records attributed to Sang-Hyun Lee.

13 recordsLinked to original sources

arXiv2026

Difix3D-W: Distractor-Free Few-Shot 3D Gaussian Splatting in the Wild

We propose Difix3D-W, a 3D novel sparse-view synthesis framework for unconstrained real-world scenarios that contain distractors, occlusion, and appearance variation. Unlike existing methods that primarily perform novel-view synthesis from a sparse set of constrained images without transient elements or leverage unconstrained dense image collections in real-world scenarios, our method utilize sparse unconstrained images, showing high-quality 3D rendering results. To do this, we introduce reference-guided view refinement with a redesigned one-step diffusion model using a transient mask and a reference image to mitigate artifacts in rendered views, enhancing the 3D representation in the Gaussian field. Furthermore, we address sparse regions in the Gaussian field leveraging sparsity-aware Gaussian replication strategy to amplify Gaussians in the sparse regions and alleviate deficient camera viewpoint issues. Finally, we utilize LoRA and regularization to maintain 3D multi-view consistency. Extensive experiments demonstrate that our method consistently outperforms existing methods. This advancement paves the way for realizing real-world scenarios without labor-intensive data acquisition.

cs.CV↗

arXiv2026

Rectifying Mask via Entropy for Distractor-Free 3DGS in Ambiguous Scenarios

We present RefineSplat, a systematic framework that effectively constructs transient masks to identify diverse ambiguous distractors. To do this, we qualitatively and quantitatively analyze issues and propose a novel entropy-aware adaptive masking method. Unlike existing approaches that struggle to distinguish transient elements from static scenes due to color or semantic ambiguity, RefineSplat captures ambiguous distractors leveraging entropy and instance masks. Furthermore, we propose a simple yet effective entropy-aware density control to align Gaussians in ambiguous scenarios considering Entropy-aware positional gradients. Additionally, to rigorously validate our method, we first create and release the Ambiguous wild dataset, including 18 scenes where distractors and static scenes are hard to distinguish due to color or semantic resemblances. Experimental results on various datasets demonstrate that RefineSplat shows state-of-the-art performance, showing distractor-free novel view synthesis.

cs.CV↗

arXiv2026

Domain Adaptation with Adaptive Imagination for Visual Reinforcement Learning under Limited Target Data

Sim-to-real transfer remains a major obstacle for reinforcement learning (RL), especially for vision-based control where image observations exacerbate the state-distribution shift between simulation and the real world. Domain adaptation (DA) is a promising remedy for this challenge. Prior sim-to-real DA works have demonstrated encouraging results, yet these approaches typically assume substantially more target data, which is not available in practice. Indeed, their performance degrades significantly when the target data budget is reduced. To address this challenge, we propose AIDA (Adaptive Imagination for Domain Adaptation), a domain adaptation framework for visual reinforcement learning that addresses sim-to-real transfer under scarce target data without requiring additional interaction with the target environment. Our key idea is adaptive imagination: generating reliable and semantic imagination rollouts to augment limited target data. Specifically, AIDA employs a distribution-shift-aware discriminator that truncates rollouts when imagined transitions drift into low-confidence regions, so that only reliable transitions contribute to the augmentation. On these reliable transitions, AIDA introduces a self-consistency loss that cycles through state -> image observation -> state, penalizing discrepancies between the original and reconstructed states. This provides additional adaptation signals beyond the scarce target data. Our experiments demonstrate that adaptive imagination effectively truncates unreliable rollouts. By enforcing a self-consistency loss on the resulting reliable transitions, AIDA learns semantically meaningful state representations and outperforms baselines across five MuJoCo tasks and two Gymnasium-Robotics tasks.

cs.AI↗

arXiv2026

Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL

Offline goal-conditioned reinforcement learning remains challenging for long-horizon tasks. While hierarchical approaches mitigate this issue by decomposing tasks, most existing methods rely on separate high- and low-level networks and generate only a single intermediate subgoal, leaving several structural limitations in long-horizon decision-making. To address this limitation, we draw inspiration from chain-of-thought reasoning and propose the Chain-of-Goals Hierarchical Policy (CoGHP), a novel framework that reformulates hierarchical decision-making as autoregressive sequence modeling within a unified architecture. Given a state and a final goal, CoGHP autoregressively generates a sequence of latent subgoals followed by the primitive action, where each latent subgoal acts as a reasoning step that conditions subsequent predictions. To implement this efficiently, we introduce an MLP-Mixer backbone, which supports cross-token communication and captures structural relationships among state, goal, latent subgoals, and action. Across challenging navigation and manipulation benchmarks, CoGHP consistently outperforms strong offline baselines, demonstrating improved performance on long-horizon tasks. Project page: https://wlsdn9350.github.io/projects/coghp/

cs.LG↗

arXiv2025

Autonomous Algorithm for Training Autonomous Vehicles with Minimal Human Intervention

Recent reinforcement learning (RL) algorithms have demonstrated impressive results in simulated driving environments. However, autonomous vehicles trained in simulation often struggle to work well in the real world due to the fidelity gap between simulated and real-world environments. While directly training real-world autonomous vehicles with RL algorithms is a promising approach to bypass the fidelity gap problem, it presents several challenges. One critical yet often overlooked challenge is the need to reset a driving environment between every episode. This reset process demands significant human intervention, leading to poor training efficiency in the real world. In this paper, we introduce a novel autonomous algorithm that enables off-the-shelf RL algorithms to train autonomous vehicles with minimal human intervention. Our algorithm reduces unnecessary human intervention by aborting episodes to prevent unsafe states and identifying informative initial states for subsequent episodes. The key idea behind identifying informative initial states is to estimate the expected amount of information that can be obtained from under-explored but reachable states. Our algorithm also revisits rule-based autonomous driving algorithms and highlights their benefits in safely returning an autonomous vehicle to initial states. To evaluate how much human intervention is required during training, we implement challenging urban driving tasks that require an autonomous vehicle to reset to initial states on its own. The experimental results show that our autonomous algorithm is task-agnostic and achieves competitive driving performance with much less human intervention than baselines.

cs.RO↗

arXiv2024

Safe and Efficient Trajectory Optimization for Autonomous Vehicles using B-spline with Incremental Path Flattening

Gradient-based trajectory optimization with B-spline curves is widely used for unmanned aerial vehicles (UAVs) due to its fast convergence and continuous trajectory generation. However, the application of B-spline curves for path-velocity coupled trajectory planning in autonomous vehicles (AVs) has been highly limited because it is challenging to reduce the over-approximation of the vehicle shape and to create a collision-free trajectory using B-spline curves while satisfying kinodynamic constraints. To address these challenges, this paper proposes novel disc-type swept volume (SV), incremental path flattening (IPF), and kinodynamic feasibility penalty methods. The disc-type SV estimation method is a new technique to reduce SV over-approximation and is used to find collision points for IPF. In IPF, the collision points are used to push the trajectory away from obstacles and to iteratively increase the curvature weight, thereby reducing SV and generating a collision-free trajectory. Additionally, to satisfy kinodynamic constraints for AVs using B-spline curves, we apply a clamped B-spline curvature penalty along with longitudinal and lateral velocity and acceleration penalties. Our experimental results demonstrate that our method outperforms state-of-the-art baselines in various simulated environments. We also conducted a real-world experiment using an AV, and our results validate the simulated tracking performance of the proposed approach.

cs.RO↗

arXiv2024

Results and Lessons Learned from Autonomous Driving Transportation Services in Airfield, Crowded Indoor, and Urban Environments

Autonomous vehicles have been actively investigated over the past few decades. Several recent works show the potential of autonomous vehicles in urban environments with impressive experimental results. However, these works note that autonomous vehicles are still occasionally inferior to expert drivers in complex scenarios. Furthermore, they do not focus on the possibilities of autonomous driving transportation services in other areas beyond urban environments. This paper presents the research results and lessons learned from autonomous driving transportation services in airfield, crowded indoor, and urban environments. We discuss how we address several unique challenges in these diverse environments. We also offer an overview of remaining challenges that have not received much attention but must be addressed. This paper aims to share our unique experience to support researchers who are interested in exploring autonomous driving transportation services in various real-world environments.

cs.RO↗

arXiv2024

Self-Supervised Curriculum Generation for Autonomous Reinforcement Learning without Task-Specific Knowledge

A significant bottleneck in applying current reinforcement learning algorithms to real-world scenarios is the need to reset the environment between every episode. This reset process demands substantial human intervention, making it difficult for the agent to learn continuously and autonomously. Several recent works have introduced autonomous reinforcement learning (ARL) algorithms that generate curricula for jointly training reset and forward policies. While their curricula can reduce the number of required manual resets by taking into account the agent's learning progress, they rely on task-specific knowledge, such as predefined initial states or reset reward functions. In this paper, we propose a novel ARL algorithm that can generate a curriculum adaptive to the agent's learning progress without task-specific knowledge. Our curriculum empowers the agent to autonomously reset to diverse and informative initial states. To achieve this, we introduce a success discriminator that estimates the success probability from each initial state when the agent follows the forward policy. The success discriminator is trained with relabeled transitions in a self-supervised manner. Our experimental results demonstrate that our ARL algorithm can generate an adaptive curriculum and enable the agent to efficiently bootstrap to solve sparse-reward maze navigation and manipulation tasks, outperforming baselines with significantly fewer manual resets.

cs.LG↗

arXiv2024

Imagination-Augmented Hierarchical Reinforcement Learning for Safe and Interactive Autonomous Driving in Urban Environments

Hierarchical reinforcement learning (HRL) incorporates temporal abstraction into reinforcement learning (RL) by explicitly taking advantage of hierarchical structure. Modern HRL typically designs a hierarchical agent composed of a high-level policy and low-level policies. The high-level policy selects which low-level policy to activate at a lower frequency and the activated low-level policy selects an action at each time step. Recent HRL algorithms have achieved performance gains over standard RL algorithms in synthetic navigation tasks. However, we cannot apply these HRL algorithms to real-world navigation tasks. One of the main challenges is that real-world navigation tasks require an agent to perform safe and interactive behaviors in dynamic environments. In this paper, we propose imagination-augmented HRL (IAHRL) that efficiently integrates imagination into HRL to enable an agent to learn safe and interactive behaviors in real-world navigation tasks. Imagination is to predict the consequences of actions without interactions with actual environments. The key idea behind IAHRL is that the low-level policies imagine safe and structured behaviors, and then the high-level policy infers interactions with surrounding objects by interpreting the imagined behaviors. We also introduce a new attention mechanism that allows our high-level policy to be permutation-invariant to the order of surrounding objects and to prioritize our agent over them. To evaluate IAHRL, we introduce five complex urban driving tasks, which are among the most challenging real-world navigation tasks. The experimental results indicate that IAHRL enables an agent to perform safe and interactive behaviors, achieving higher success rates and lower average episode steps than baselines.

cs.LG↗

arXiv2023

Occlusion-aware Risk Assessment and Driving Strategy for Autonomous Vehicles Using Simplified Reachability Quantification

One of the unresolved challenges for autonomous vehicles is safe navigation among occluded pedestrians and vehicles. Previous approaches included generating phantom vehicles and assessing their risk, but they often made the ego vehicle overly conservative or could not conduct a real-time risk assessment in heavily occluded situations. We propose an efficient occlusion-aware risk assessment method using simplified reachability quantification that quantifies the reachability of phantom agents with a simple distribution model on phantom agents' state. Furthermore, we propose a driving strategy for safe and efficient navigation in occluded areas that sets the speed limit of an autonomous vehicle using the risk of phantom agents. Simulations were conducted to evaluate the performance of the proposed method in various occlusion scenarios involving other vehicles and obstacles. Compared with the baseline case of no occlusion-aware risk assessment, the proposed method increased the traversal time of an intersection by 1.48 times but decreased the average collision rate and discomfort score by up to 6.14 times and 5.03 times, respectively. The proposed method has shown the state-of-the-art level of time efficiency with constant time complexity and computational time less than 5 ms.

cs.RO↗

arXiv2020

Determination of strain rate in modelling belt-flesh-pelvis interaction during frontal crashes

Obesity is associated with higher fatality risk and altered distribution of occupant injuries in motor vehicle crashes partially because of the increased depth of abdominal soft tissue, which results in limited and delayed engagement of the lap belt with the pelvis and increases the risk of pelvis submarining under the lap belt exposing occupant abdomen to belt loading.

physics.app-ph↗

arXiv2016

Robust singlet dimers with fragile ordering in two-dimensional honeycomb lattice of Li$_2$RuO$_3$

When an electronic system has strong correlations and a large spin-orbit interaction, it often exhibits a plethora of mutually competing quantum phases. How a particular quantum ground state is selected out of several possibilities is a very interesting question. However, equally fascinating is how such a quantum entangled state breaks up due to perturbation. This important question has relevance in very diverse fields of science from strongly correlated electron physics to quantum information. Here we report that a quantum entangled dimerized state or valence bond crystal (VBC) phase of Li2RuO3 shows nontrivial doping dependence as we perturb the Ru honeycomb lattice by replacing Ru with Li. Through extensive experimental studies, we demonstrate that the VBC phase melts into a valence bond liquid phase of the RVB (resonating valence bond) type. This system offers an interesting playground where one can test and refine our current understanding of the quantum competing phases in a single compound.

cond-mat.str-el↗

arXiv2014

Successive spin-flop transitions of Neel-type antiferromagnet Li$_2$MnO$_3$ single crystal with honeycomb-lattice

We have carried out high magnetic field studies of single-crystalline Li$_2$MnO$_3$, a honeycomb lattice antiferromagnet. Its magnetic phase diagram was mapped out using magnetization measurements at applied fields up to 35 T. Our results show that it undergoes two successive meta-magnetic transitions around 9 T fields applied perpendicular to the ab-plane (along the c*-axis). These phase transitions are completely absent in the magnetization measured with field applied along the ab-plane. In order to understand this magnetic phase diagram, we developed a mean-field model starting from the correct Neel-type magnetic structure, consistent with our single crystal neutron diffraction data at zero field. Our model calculations succeeded in explaining the two meta-magnetic transitions that arise when Li$_2$MnO$_3$ enters two different spin-flop phases from the zero field Neel phase.

cond-mat.str-el↗