7 citations · 19 across the 23 of their papers we have counts for
24 papers · 1 filter
GeoFix: Geometry Fixing for 4D Consistent Generation
Yeobin Hong, Hyojun Go, Dohun Lee +7
Video diffusion models increasingly serve as priors for 4D generation, but the generated videos often lack geometric consistency. Recent approaches address this through post-traini…
GenRec: Knowing Where to Reconstruct and Where to Generate
Ata Çelen, Jaewoo Jung, Federico Tombari +4
Generative novel view synthesis from sparse input images is rarely all reconstruction or all generation: pixels visible in some source view have a unique correct value modulated on…
Map-Det3D: Metric Feed-Forward 3D Reconstruction Prior for Multi-view 3D Object Detection from Streaming Inputs
Yung-Hsu Yang, Luigi Piccinelli, Samuel Rota Bulò +7
Metric 3D object detection is a core capability for embodied agents, yet most reliable systems lean on depth sensors, trading away cost, power, and integration simplicity. This mot…
PROSE: Training-Free Egocentric Scene Registration with Vision-Language Models
Zhiang Chen, Nahyuk Lee, Boyang Sun +4
Registering two captures of the same indoor space taken at different times underpins persistent spatial memory for robots and AR systems, yet the realistic version of this task is…
ZipSplat: Fewer Gaussians, Better Splats
Alexander Veicht, Sunghwan Hong, Dániel Baráth +1
Feed-forward 3D Gaussian Splatting reconstructs scenes from images in seconds. Pixel-aligned methods keep every Gaussian grounded in an observation, but produce redundant, potentia…
Entropy-Gradient Grounding: Training-Free Evidence Retrieval in Vision-Language Models
Marcel Gröpl, Jaewoo Jung, Seungryong Kim +2
Despite rapid progress, pretrained vision-language models still struggle when answers depend on tiny visual details or on combining clues spread across multiple regions, as in docu…
TORA: Topological Representation Alignment for 3D Shape Assembly
Nahyuk Lee, Zhiang Chen, Marc Pollefeys +1
Flow-matching methods for 3D shape assembly learn point-wise velocity fields that transport parts toward assembled configurations, yet they receive no explicit guidance about which…
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…
ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision
A. Said Gurbuz, Sunghwan Hong, Ahmed Nassar +2
Modern computer-use agents (CUA) must perceive a screen as a structured state, what elements are visible, where they are, and what text they contain, before they can reliably groun…
Emergent Outlier View Rejection in Visual Geometry Grounded Transformers
Jisang Han, Sunghwan Hong, Jaewoo Jung +5
Reliable 3D reconstruction from in-the-wild image collections is often hindered by "noisy" images-irrelevant inputs with little or no view overlap with others. While traditional St…
LitePT: Lighter Yet Stronger Point Transformer
Yuanwen Yue, Damien Robert, Jianyuan Wang +4
Modern neural architectures for 3D point cloud processing contain both convolutional layers and attention blocks, but the best way to assemble them remains unclear. We analyse the…
C3G: Learning Compact 3D Representations with 2K Gaussians
Honggyu An, Jaewoo Jung, Mungyeom Kim +10
Reconstructing and understanding 3D scenes from unposed sparse views in a feed-forward manner remains as a challenging task in 3D computer vision. Recent approaches use per-pixel 3…
Visual Representation Alignment for Multimodal Large Language Models
Heeji Yoon, Jaewoo Jung, Junwan Kim +10
Multimodal large language models (MLLMs) trained with visual instruction tuning have achieved strong performance across diverse tasks, yet they remain limited in vision-centric tas…
3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation
JoungBin Lee, Jaewoo Jung, Jisang Han +6
We present 3DScenePrompt, a framework that generates the next video chunk from arbitrary-length input while enabling precise camera control and preserving scene consistency. Unlike…
Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers
Chaehyun Kim, Heeseong Shin, Eunbeen Hong +5
Text-to-image diffusion models excel at translating language prompts into photorealistic images by implicitly grounding textual concepts through their cross-modal attention mechani…
DUSt3R: Enhancing 3D Reconstruction for Dynamic Scenes
Jisang Han, Honggyu An, Jaewoo Jung +7
In this work, we address the task of 3D reconstruction in dynamic scenes, where object motions frequently degrade the quality of previous 3D pointmap regression methods, such as DU…
Cross-View Completion Models are Zero-shot Correspondence Estimators
Honggyu An, Jinhyeon Kim, Seonghoon Park +4
In this work, we explore new perspectives on cross-view completion learning by drawing an analogy to self-supervised correspondence learning. Through our analysis, we demonstrate t…
PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting
Sunghwan Hong, Jaewoo Jung, Heeseong Shin +4
We consider the problem of novel view synthesis from unposed images in a single feed-forward. Our framework capitalizes on fast speed, scalability, and high-quality 3D reconstructi…
Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
Heeseong Shin, Chaehyun Kim, Sunghwan Hong +4
Large-scale vision-language models like CLIP have demonstrated impressive open-vocabulary capabilities for image-level tasks, excelling in recognizing what objects are present. How…
Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence
Sunghwan Hong, Seokju Cho, Seungryong Kim +1
This paper introduces a Transformer-based integrative feature and cost aggregation network designed for dense matching tasks. In the context of dense matching, many works benefit f…
Unifying Correspondence, Pose and NeRF for Pose-Free Novel View Synthesis from Stereo Pairs
Sunghwan Hong, Jaewoo Jung, Heeseong Shin +3
This work delves into the task of pose-free novel view synthesis from stereo pairs, a challenging and pioneering task in 3D vision. Our innovative framework, unlike any before, sea…
DirecT2V: Large Language Models are Frame-Level Directors for Zero-Shot Text-to-Video Generation
Susung Hong, Junyoung Seo, Heeseong Shin +2
In the paradigm of AI-generated content (AIGC), there has been increasing attention to transferring knowledge from pre-trained text-to-image (T2I) models to text-to-video (T2V) gen…
CAT-Seg: Cost Aggregation for Open-Vocabulary Semantic Segmentation
Seokju Cho, Heeseong Shin, Sunghwan Hong +3
Open-vocabulary semantic segmentation presents the challenge of labeling each pixel within an image based on a wide range of text descriptions. In this work, we introduce a novel c…
Neural Matching Fields: Implicit Representation of Matching Fields for Visual Correspondence
Sunghwan Hong, Jisu Nam, Seokju Cho +4
Existing pipelines of semantic correspondence commonly include extracting high-level semantic features for the invariance against intra-class variations and background clutters. Th…