Kyungdon Joo

Harin Park, Inha Lee, Minje Kim et al.

As service environments have become diverse, they have started to demand complicated tasks that are difficult for a single robot to complete. This change has led to an interest in multiple robots instead of a single robot. C-SLAM, as a fundamental technique for multiple service robots, needs to handle diverse challenges such as homogeneous scenes and dynamic objects to ensure that robots operate smoothly and perform their tasks safely. However, existing C-SLAM datasets do not include the various indoor service environments with the aforementioned challenges. To close this gap, we introduce a new multi-modal C-SLAM dataset for multiple service robots in various indoor service environments, called C-SLAM dataset in Service Environments (CSE). We use the NVIDIA Isaac Sim to generate data in various indoor service environments with the challenges that may occur in real-world service environments. By using simulation, we can provide accurate and precisely time-synchronized sensor data, such as stereo RGB, stereo depth, IMU, and ground truth (GT) poses. We configure three common indoor service environments (Hospital, Office, and Warehouse), each of which includes various dynamic objects that perform motions suitable to each environment. In addition, we drive three robots to mimic the actions of real service robots. Through these factors, we generate a more realistic C-SLAM dataset for multiple service robots. We demonstrate our dataset by evaluating diverse state-of-the-art single-robot SLAM and multi-robot SLAM methods. Our dataset is available at https://github.com/vision3d-lab/CSE_Dataset.

Jaehun Bang, Jinhyeok Kim, Minji Kim et al.

Open-vocabulary 3D scene understanding enables users to segment novel objects in complex 3D environments through natural language. However, existing approaches remain slow, memory-intensive, and overly complex due to iterative optimization and dense per-Gaussian feature assignments. To address this, we propose LightSplat, a fast and memory-efficient training-free framework that injects compact 2-byte semantic indices into 3D representations from multi-view images. By assigning semantic indices only to salient regions and managing them with a lightweight index-feature mapping, LightSplat eliminates costly feature optimization and storage overhead. We further ensure semantic consistency and efficient inference via single-step clustering that links geometrically and semantically related masks in 3D. We evaluate our method on LERF-OVS, ScanNet, and DL3DV-OVS across complex indoor-outdoor scenes. As a result, LightSplat achieves state-of-the-art performance with up to 50-400x speedup and 64x lower memory, enabling scalable language-driven 3D understanding. For more details, visit our project page https://vision3d-lab.github.io/lightsplat/.

Junsu Kim, Junhee Lee, Ukcheol Shin et al.

Understanding 3D scenes semantically and spatially is crucial for the safe navigation of robots and autonomous vehicles, aiding obstacle avoidance and accurate trajectory planning. Camera-based 3D semantic occupancy prediction, which infers complete voxel grids from 2D images, is gaining importance in robot vision for its resource efficiency compared to 3D sensors. However, this task inherently suffers from a 2D-3D discrepancy, where objects of the same size in 3D space appear at different scales in a 2D image depending on their distance from the camera due to perspective projection. To tackle this issue, we propose a novel framework called VPOcc that leverages a vanishing point (VP) to mitigate the 2D-3D discrepancy at both the pixel and feature levels. As a pixel-level solution, we introduce a VPZoomer module, which warps images by counteracting the perspective effect using a VP-based homography transformation. In addition, as a feature-level solution, we propose a VP-guided cross-attention (VPCA) module that performs perspective-aware feature aggregation, utilizing 2D image features that are more suitable for 3D space. Lastly, we integrate two feature volumes extracted from the original and warped images to compensate for each other through a spatial volume fusion (SVF) module. By effectively incorporating VP into the network, our framework achieves improvements in both IoU and mIoU metrics on SemanticKITTI and SSCBench-KITTI360 datasets. Additional details are available at https://vision3d-lab.github.io/vpocc/.

Dongjun Gu, Jaehyeok Shim, Jaehoon Jang et al.

Among various interactions between humans, such as eye contact and gestures, physical interactions by contact can act as an essential moment in understanding human behaviors. Inspired by this fact, given a 3D partner human with the desired interaction label, we introduce a new task of 3D human generation in terms of physical contact. Unlike previous works of interacting with static objects or scenes, a given partner human can have diverse poses and different contact regions according to the type of interaction. To handle this challenge, we propose a novel method of generating interactive 3D humans for a given partner human based on a guided diffusion framework. Specifically, we newly present a contact prediction module that adaptively estimates potential contact regions between two input humans according to the interaction label. Using the estimated potential contact regions as complementary guidances, we dynamically enforce ContactGen to generate interactive 3D humans for a given partner human within a guided diffusion model. We demonstrate ContactGen on the CHI3D dataset, where our method generates physically plausible and diverse poses compared to comparison methods.

Seungoh Han, Jaehoon Jang, Hyunsu Kim et al.

Recent advances in 3D Gaussian Splatting (3DGS) have enabled real-time novel view synthesis (NVS) with impressive quality in indoor scenes. However, achieving high-fidelity rendering requires meticulously captured images covering the entire scene, limiting accessibility for general users. We aim to develop a practical 3DGS-based NVS framework using simple panorama-style motion with a handheld camera (e.g., mobile device). While convenient, this rotation-dominant motion and narrow baseline make accurate camera pose and 3D point estimation challenging, especially in textureless indoor scenes. To address these challenges, we propose LighthouseGS, a novel framework inspired by the lighthouse-like sweeping motion of panoramic views. LighthouseGS leverages rough geometric priors, such as mobile device camera poses and monocular depth estimation, and utilizes the planar structures often found in indoor environments. We present a new initialization method called plane scaffold assembly to generate consistent 3D points on these structures, followed by a stable pruning strategy to enhance geometry and optimization stability. Additionally, we introduce geometric and photometric corrections to resolve inconsistencies from motion drift and auto-exposure in mobile devices. Tested on collected real and synthetic indoor scenes, LighthouseGS delivers photorealistic rendering, surpassing state-of-the-art methods and demonstrating the potential for panoramic view synthesis and object placement.

Jaehyeok Shim, Kyungdon Joo

We propose a novel concept of dual and integrated latent topologies (DITTO in short) for implicit 3D reconstruction from noisy and sparse point clouds. Most existing methods predominantly focus on single latent type, such as point or grid latents. In contrast, the proposed DITTO leverages both point and grid latents (i.e., dual latent) to enhance their strengths, the stability of grid latents and the detail-rich capability of point latents. Concretely, DITTO consists of dual latent encoder and integrated implicit decoder. In the dual latent encoder, a dual latent layer, which is the key module block composing the encoder, refines both latents in parallel, maintaining their distinct shapes and enabling recursive interaction. Notably, a newly proposed dynamic sparse point transformer within the dual latent layer effectively refines point latents. Then, the integrated implicit decoder systematically combines these refined latents, achieving high-fidelity 3D reconstruction and surpassing previous state-of-the-art methods on object- and scene-level datasets, especially in thin and detailed structures.

Jaehoon Jang, Inha Lee, Minje Kim et al.

Indoor scenes we are living in are visually homogenous or textureless, while they inherently have structural forms and provide enough structural priors for 3D scene reconstruction. Motivated by this fact, we propose a structure-aware online signed distance fields (SDF) reconstruction framework in indoor scenes, especially under the Atlanta world (AW) assumption. Thus, we dub this incremental SDF reconstruction for AW as AiSDF. Within the online framework, we infer the underlying Atlanta structure of a given scene and then estimate planar surfel regions supporting the Atlanta structure. This Atlanta-aware surfel representation provides an explicit planar map for a given scene. In addition, based on these Atlanta planar surfel regions, we adaptively sample and constrain the structural regularity in the SDF reconstruction, which enables us to improve the reconstruction quality by maintaining a high-level structure while enhancing the details of a given scene. We evaluate the proposed AiSDF on the ScanNet and ReplicaCAD datasets, where we demonstrate that the proposed framework is capable of reconstructing fine details of objects implicitly, as well as structures explicitly in room-scale scenes.

Sangjune Park, Inhyeok Choi, Donghyeon Soon et al.

Dance is a form of human motion characterized by emotional expression and communication, playing a role in various fields such as music, virtual reality, and content creation. Existing methods for dance generation often fail to adequately capture the inherently sequential, rhythmical, and music-synchronized characteristics of dance. In this paper, we propose \emph{MambaDance}, a new dance generation approach that leverages a Mamba-based diffusion model. Mamba, well-suited to handling long and autoregressive sequences, is integrated into our two-stage diffusion architecture, substituting off-the-shelf Transformer. Additionally, considering the critical role of musical beats in dance choreography, we propose a Gaussian-based beat representation to explicitly guide the decoding of dance sequences. Experiments on AIST++ and FineDance datasets for each sequence length show that our proposed method effectively generates plausible dance movements while reflecting essential characteristics, consistently from short to long dances, compared to the previous methods. Additional qualitative results and demo videos are available at \small{https://vision3d-lab.github.io/mambadance}.

Jinhyeok Kim, Jaehun Bang, Seunghyun Seo et al.

Reconstructing object deformation from a single image remains a significant challenge in computer vision and graphics. Existing methods typically rely on multi-view video to recover deformation, limiting their applicability under constrained scenarios. To address this, we propose DeformSplat, a novel framework that effectively guides 3D Gaussian deformation from only a single image. Our method introduces two main technical contributions. First, we present Gaussian-to-Pixel Matching which bridges the domain gap between 3D Gaussian representations and 2D pixel observations. This enables robust deformation guidance from sparse visual cues. Second, we propose Rigid Part Segmentation consisting of initialization and refinement. This segmentation explicitly identifies rigid regions, crucial for maintaining geometric coherence during deformation. By combining these two techniques, our approach can reconstruct consistent deformations from a single image. Extensive experiments demonstrate that our approach significantly outperforms existing methods and naturally extends to various applications,such as frame interpolation and interactive object manipulation.

Wonjun Jo, Kwon Byung-Ki, Kim Ji-Yeon et al.

LiDAR is a crucial sensor in autonomous driving, commonly used alongside cameras. By exploiting this camera-LiDAR setup and recent advances in image representation learning, prior studies have shown the promising potential of image-to-LiDAR distillation. These prior arts focus on the designs of their own losses to effectively distill the pre-trained 2D image representations into a 3D model. However, the other parts of the designs have been surprisingly unexplored. We find that fundamental design elements, e.g., the LiDAR coordinate system, quantization according to the existing input interface, and data utilization, are more critical than developing loss functions, which have been overlooked in prior works. In this work, we show that simple fixes to these designs notably outperform existing methods by 16% in 3D semantic segmentation on the nuScenes dataset and 13% in 3D object detection on the KITTI dataset in downstream task performance. We focus on overlooked design choices along the spatial and temporal axes. Spatially, prior work has used cylindrical coordinate and voxel sizes without considering their side effects yielded with a commonly deployed sparse convolution layer input interface, leading to spatial quantization errors in 3D models. Temporally, existing work has avoided cumbersome data curation by discarding unsynced data, limiting the use to only the small portion of data that is temporally synced across sensors. We analyze these effects and propose simple solutions for each overlooked aspect.

Xin Shen, Kyungdon Joo, Jean Oh

We propose an end-to-end deep learning approach to rectify fisheye images and simultaneously calibrate camera intrinsic and distortion parameters. Our method consists of two parts: a Quick Image Rectification Module developed with a Pix2Pix GAN and Wasserstein GAN (W-Pix2PixGAN), and a Calibration Module with a CNN architecture. Our Quick Rectification Network performs robust rectification with good resolution, making it suitable for constant calibration in camera-based surveillance equipment. To achieve high-quality calibration, we use the straightened output from the Quick Rectification Module as a guidance-like semantic feature map for the Calibration Module to learn the geometric relationship between the straightened feature and the distorted feature. We train and validate our method with a large synthesized dataset labeled with well-simulated parameters applied to a perspective image dataset. Our solution has achieved robust performance in high-resolution with a significant PSNR value of 22.343.

Kim Youwang, Kim Ji-Yeon, Kyungdon Joo et al.

We propose an end-to-end unified 3D mesh recovery of humans and quadruped animals trained in a weakly-supervised way. Unlike recent work focusing on a single target class only, we aim to recover 3D mesh of broader classes with a single multi-task model. However, there exists no dataset that can directly enable multi-task learning due to the absence of both human and animal annotations for a single object, e.g., a human image does not have animal pose annotations; thus, we have to devise a new way to exploit heterogeneous datasets. To make the unstable disjoint multi-task learning jointly trainable, we propose to exploit the morphological similarity between humans and animals, motivated by animal exercise where humans imitate animal poses. We realize the morphological similarity by semantic correspondences, called sub-keypoint, which enables joint training of human and animal mesh regression branches. Besides, we propose class-sensitive regularization methods to avoid a mean-shape bias and to improve the distinctiveness across multi-classes. Our method performs favorably against recent uni-modal models on various human and animal datasets while being far more compact.

Jaesung Choe, Kyungdon Joo, Tooba Imtiaz et al.

Stereo-LiDAR fusion is a promising task in that we can utilize two different types of 3D perceptions for practical usage -- dense 3D information (stereo cameras) and highly-accurate sparse point clouds (LiDAR). However, due to their different modalities and structures, the method of aligning sensor data is the key for successful sensor fusion. To this end, we propose a geometry-aware stereo-LiDAR fusion network for long-range depth estimation, called volumetric propagation network. The key idea of our network is to exploit sparse and accurate point clouds as a cue for guiding correspondences of stereo images in a unified 3D volume space. Unlike existing fusion strategies, we directly embed point clouds into the volume, which enables us to propagate valid information into nearby voxels in the volume, and to reduce the uncertainty of correspondences. Thus, it allows us to fuse two different input modalities seamlessly and regress a long-range depth map. Our fusion is further enhanced by a newly proposed feature extraction layer for point clouds guided by images: FusionConv. FusionConv extracts point cloud features that consider both semantic (2D image domain) and geometric (3D domain) relations and aid fusion at the volume. Our network achieves state-of-the-art performance on the KITTI and the Virtual-KITTI datasets among recent stereo-LiDAR fusion methods.

Jaesung Choe, Kyungdon Joo, Francois Rameau et al.

This paper presents a stereo object matching method that exploits both 2D contextual information from images as well as 3D object-level information. Unlike existing stereo matching methods that exclusively focus on the pixel-level correspondence between stereo images within a volumetric space (i.e., cost volume), we exploit this volumetric structure in a different manner. The cost volume explicitly encompasses 3D information along its disparity axis, therefore it is a privileged structure that can encapsulate the 3D contextual information from objects. However, it is not straightforward since the disparity values map the 3D metric space in a non-linear fashion. Thus, we present two novel strategies to handle 3D objectness in the cost volume space: selective sampling (RoISelect) and 2D-3D fusion (fusion-by-occupancy), which allow us to seamlessly incorporate 3D object-level information and achieve accurate depth performance near the object boundary regions. Our depth estimation achieves competitive performance in the KITTI dataset and the Virtual-KITTI 2.0 dataset.

Jinsun Park, Kyungdon Joo, Zhe Hu et al.

In this paper, we propose a robust and efficient end-to-end non-local spatial propagation network for depth completion. The proposed network takes RGB and sparse depth images as inputs and estimates non-local neighbors and their affinities of each pixel, as well as an initial depth map with pixel-wise confidences. The initial depth prediction is then iteratively refined by its confidence and non-local spatial propagation procedure based on the predicted non-local neighbors and corresponding affinities. Unlike previous algorithms that utilize fixed-local neighbors, the proposed algorithm effectively avoids irrelevant local neighbors and concentrates on relevant non-local neighbors during propagation. In addition, we introduce a learnable affinity normalization to better learn the affinity combinations compared to conventional methods. The proposed algorithm is inherently robust to the mixed-depth problem on depth boundaries, which is one of the major issues for existing depth estimation/completion algorithms. Experimental results on indoor and outdoor datasets demonstrate that the proposed algorithm is superior to conventional algorithms in terms of depth completion accuracy and robustness to the mixed-depth problem. Our implementation is publicly available on the project page.

Tae-Hyun Oh, Kyungdon Joo, Neel Joshi et al.

Cinemagraphs are a compelling way to convey dynamic aspects of a scene. In these media, dynamic and still elements are juxtaposed to create an artistic and narrative experience. Creating a high-quality, aesthetically pleasing cinemagraph requires isolating objects in a semantically meaningful way and then selecting good start times and looping periods for those objects to minimize visual artifacts (such a tearing). To achieve this, we present a new technique that uses object recognition and semantic segmentation as part of an optimization method to automatically create cinemagraphs from videos that are both visually appealing and semantically meaningful. Given a scene with multiple objects, there are many cinemagraphs one could create. Our method evaluates these multiple candidates and presents the best one, as determined by a model trained to predict human preferences in a collaborative way. We demonstrate the effectiveness of our approach with multiple results and a user study.

Kyungdon Joo, Tae-Hyun Oh, Junsik Kim et al.

Most man-made environments, such as urban and indoor scenes, consist of a set of parallel and orthogonal planar structures. These structures are approximated by the Manhattan world assumption, in which notion can be represented as a Manhattan frame (MF). Given a set of inputs such as surface normals or vanishing points, we pose an MF estimation problem as a consensus set maximization that maximizes the number of inliers over the rotation search space. Conventionally, this problem can be solved by a branch-and-bound framework, which mathematically guarantees global optimality. However, the computational time of the conventional branch-and-bound algorithms is rather far from real-time. In this paper, we propose a novel bound computation method on an efficient measurement domain for MF estimation, i.e., the extended Gaussian image (EGI). By relaxing the original problem, we can compute the bound with a constant complexity, while preserving global optimality. Furthermore, we quantitatively and qualitatively demonstrate the performance of the proposed method for various synthetic and real-world data. We also show the versatility of our approach through three different applications: extension to multiple MF estimation, 3D rotation based video stabilization, and vanishing point estimation (line clustering).

Inwook Shim, Seunghak Shin, Yunsu Bok et al.

This paper presents a vision system and a depth processing algorithm for DRC-HUBO+, the winner of the DRC finals 2015. Our system is designed to reliably capture 3D information of a scene and objects robust to challenging environment conditions. We also propose a depth-map upsampling method that produces an outliers-free depth map by explicitly handling depth outliers. Our system is suitable for an interactive robot with real-world that requires accurate object detection and pose estimation. We evaluate our depth processing algorithm over state-of-the-art algorithms on several synthetic and real-world datasets.