1 citations · 1 across the 24 of their papers we have counts for
25 papers
PLAYGROUND: Progressive Layout Generation with Render-Grounded Planning
Jaeho Lee, Junhwan Heo, Junghyun Park +5
Generating editable graphic designs requires arranging visual and textual elements into a coherent composition while preserving their content and editability. Although recent MLLM-…
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
Seokju Cho, Ryo Hachiuma, Abhishek Badki +8
Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-aug…
4DP-QA: Scalable QA for 4D Perception in Vision Language Models
Seokju Cho, Abhishek Badki, Hang Su +5
Despite recent advances, Vision Language Models (VLMs) still struggle to grasp the dynamics of the world. We note that the ability to reason about a 4D scene, challenging in itself…
Controllable Dynamic 3D Shape Generation via 3D Trajectories and Text
Jaeyeong Kim, Ines Kim, Jahyeok Koo +1
We introduce T2Mo, a feed-forward framework for controllable dynamic 3D shape generation conditioned on 3D trajectories and text. Due to the inherent ambiguity of language, generat…
MORPHOS: Autoregressive 4D Generation with Temporal Structured Latents
Minkyung Kwon, Jinhyeok Choi, Youngjin Shin +3
We present MORPHOS, a novel autoregressive framework that generates dynamic 3D assets from videos across diverse representations, including meshes, 3D Gaussians, and radiance field…
Learning Global Motion with Compact Gaussians for Feed-Forward 4D Reconstruction
Mungyeom Kim, Minkyeong Jeon, Honggyu An +10
Dynamic scene reconstruction from monocular video remains a fundamental challenge in computer vision. Existing feed-forward methods predict 3D Gaussians pixel-wise for each frame,…
DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models
Jaewon Min, Jaeeun Lee, Yeji Choi +7
Optical flow models trained on high-quality data often degrade severely when confronted with real-world corruptions such as blur, noise, and compression artifacts. To overcome this…
AgentRVOS: Reasoning over Object Tracks for Zero-Shot Referring Video Object Segmentation
Woojeong Jin, Jaeho Lee, Heeseong Shin +3
Referring Video Object Segmentation (RVOS) aims to segment a target object throughout a video given a natural language query. Training-free methods for this task follow a common pi…
TETO: Tracking Events with Teacher Observation for Motion Estimation and Frame Interpolation
Jini Yang, Eunbeen Hong, Soowon Son +4
Event cameras capture per-pixel brightness changes with microsecond resolution, offering continuous motion information lost between RGB frames. However, existing event-based motion…
Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representation
Jisoo Kim, Jungbin Cho, Sanghyeok Chu +9
Humans learn not only how their bodies move, but also how the surrounding world responds to their actions. In contrast, while recent Vision-Language-Action (VLA) models exhibit imp…
Unified Diffusion Transformer for High-fidelity Text-Aware Image Restoration
Jin Hyeon Kim, Paul Hyunbin Cho, Claire Kim +5
Text-Aware Image Restoration (TAIR) aims to recover high-quality images from low-quality inputs containing degraded textual content. While diffusion models provide strong generativ…
Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression
Jung Yi, Wooseok Jang, Paul Hyunbin Cho +3
Recent advances in autoregressive video diffusion have enabled real-time frame streaming, yet existing solutions still suffer from temporal repetition, drift, and motion decelerati…
Probing and Leveraging Video Diffusion Transformer Features for Robust Point Tracking
Soowon Son, Honggyu An, Jisu Nam +7
Despite achieving strong results on standard benchmarks, current point tracking methods rely on feature backbones that are rarely designed with the temporal coherence needed for ro…
MV-TAP: Tracking Any Point in Multi-View Videos
Jahyeok Koo, Inès Hyeonsu Kim, Mungyeom Kim +6
Multi-view camera systems enable rich observations of complex real-world scenes, and understanding dynamic objects in multi-view settings has become central to various applications…
MATRIX: Mask Track Alignment for Interaction-aware Video Generation
Siyoon Jin, Seongchan Kim, Dahyun Chung +5
Video DiTs have advanced video generation, yet they still struggle to model multi-instance or subject-object interactions. This raises a key question: How do these models internall…
AnthroTAP: Learning Point Tracking with Real-World Motion
Inès Hyeonsu Kim, Seokju Cho, Jahyeok Koo +5
Point tracking models often struggle to generalize to real-world videos because large-scale training data is predominantly synthetic$\unicode{x2014}$the only source currently feasi…
Emergent Temporal Correspondences from Video Diffusion Transformers
Jisu Nam, Soowon Son, Dahyun Chung +4
Recent advancements in video diffusion models based on Diffusion Transformers (DiTs) have achieved remarkable success in generating temporally coherent videos. Yet, a fundamental q…
Seurat: From Moving Points to Depth
Seokju Cho, Jiahui Huang, Seungryong Kim +1
Accurate depth estimation from monocular videos remains challenging due to ambiguities inherent in single-view geometry, as crucial depth cues like stereopsis are absent. However,…
Visual Persona: Foundation Model for Full-Body Human Customization
Jisu Nam, Soowon Son, Zhan Xu +6
We introduce Visual Persona, a foundation model for text-to-image full-body human customization that, given a single in-the-wild human image, generates diverse images of the indivi…
Exploring Temporally-Aware Features for Point Tracking
Inès Hyeonsu Kim, Seokju Cho, Jiahui Huang +3
Point tracking in videos is a fundamental task with applications in robotics, video editing, and more. While many vision tasks benefit from pre-trained feature backbones to improve…
Appearance Matching Adapter for Exemplar-based Semantic Image Synthesis in-the-Wild
Siyoon Jin, Jisu Nam, Jiyoung Kim +5
Exemplar-based semantic image synthesis generates images aligned with semantic content while preserving the appearance of an exemplar. Conventional structure-guidance models like C…
Local All-Pair Correspondence for Point Tracking
Seokju Cho, Jiahui Huang, Jisu Nam +3
We introduce LocoTrack, a highly accurate and efficient model designed for the task of tracking any point (TAP) across video sequences. Previous approaches in this task often rely…
Hybrid Video Diffusion Models with 2D Triplane and 3D Wavelet Representation
Kihong Kim, Haneol Lee, Jihye Park +4
Generating high-quality videos that synthesize desired realistic content is a challenging task due to their intricate high-dimensionality and complexity of videos. Several recent d…
MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation
Seyeon Kim, Siyoon Jin, Jihye Park +4
Conventional GAN-based models for talking head generation often suffer from limited quality and unstable training. Recent approaches based on diffusion models aimed to address thes…