8 papers
What You Ask is What You Ground: Bridging Question Intent to Temporal Evidence for Grounded VideoQA
Jinhwan Seo, Kyubeom Han, Jumin Lee +2
We study a critical yet overlooked failure mode in Grounded Video Question Answering: question-invariant grounding, where models predict nearly identical temporal segments for diff…
Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering
Sebin Lee, Jumin Lee, Taeyeon Kim +3
Rapidly-exploring random trees (RRTs) have been widely adopted for robot motion planning due to their robustness and theoretical guarantees. However, existing RRT-based planners re…
VERIA: Verification-Centric Multimodal Instance Augmentation for Long-Tailed 3D Object Detection
Jumin Lee, Siyeong Lee, Namil Kim +1
Long-tail distributions in driving datasets pose a fundamental challenge for 3D perception, as rare classes exhibit substantial intra-class diversity yet available samples cover th…
MorphGS: Morphology-Adaptive Articulated 3D Motion Transfer from Videos
Taeyeon Kim, Youngju Na, Jumin Lee +3
Transferring articulated motion from monocular videos to rigged 3D characters is challenging due to pose ambiguity in 2D observations and morphological differences between source a…
Pose-free 3D Gaussian splatting via shape-ray estimation
Youngju Na, Taeyeon Kim, Jumin Lee +3
While generalizable 3D Gaussian splatting enables efficient, high-quality rendering of unseen scenes, it heavily depends on precise camera poses for accurate geometry. In real-worl…
Regularizing Dynamic Radiance Fields with Kinematic Fields
Woobin Im, Geonho Cha, Sebin Lee +4
This paper presents a novel approach for reconstructing dynamic radiance fields from monocular videos. We integrate kinematics with dynamic radiance fields, bridging the gap betwee…
Extending Segment Anything Model into Auditory and Temporal Dimensions for Audio-Visual Segmentation
Juhyeong Seon, Woobin Im, Sebin Lee +2
Audio-visual segmentation (AVS) aims to segment sound sources in the video sequence, requiring a pixel-level understanding of audio-visual correspondence. As the Segment Anything M…
SemCity: Semantic Scene Generation with Triplane Diffusion
Jumin Lee, Sebin Lee, Changho Jo +3
We present "SemCity," a 3D diffusion model for semantic scene generation in real-world outdoor environments. Most 3D diffusion models focus on generating a single object, synthetic…