7/31 Friday (Online) | 8/2 Sunday | 8/3 Monday | 8/4 Tuesday | 8/5 Wednesday | |||
09:00 | Oral 3 (좌장: 이수찬 교수/국민대) ■ 9:00 - 10:00 | Mentoring (좌장: 김선옥 교수/항공대, 김동진 교수/한양대) ■ 9:00 - 10:00 | |||||
| 09:30 | Opening ■ 9:30 - 10:00 | ||||||
| 10:00 | Workshop 1 ■ 10:00 - 10:30 | Oral 1 (좌장: 김태현 교수/한양대) | Oral 4 (좌장: 윤국진 교수/KAIST) | Oral 6 (좌장: 곽수하 교수/POSTECH) | |||
| 10:30 | Workshop 2 ■ 10:35 - 11:05 | ||||||
| 11:00 | Workshop 3 ■ 11:10 - 12:00 |
■ 11:00 - 12:00 | Keynote 2 (좌장: 한보형 교수/서울대) ■ 11:00 - 12:00 | Keynote 3 (좌장: 이승용 교수/POSTECH) | |||
| 11:30 | |||||||
| 12:00 | Lunch(Not provided) ■ 12:00 - 13:30 | Lunch(Not provided) ■ 12:00 - 13:30 | Lunch(Not provided) ■ 12:00 - 13:30 |
(좌장: 박재식 교수/서울대)
| |||
| 12:30 | Lunch(Not provided) ■ 12:30 - 14:00 | ||||||
| 13:00 | |||||||
| 13:30 | Tutorial 1 ■ 13:30 - 14:45 | Oral 2 (좌장: 최종현 교수/서울대) | Oral 5 (좌장: 심현정 교수/KAIST) | ||||
| 14:00 | Oral 7 (좌장: 황원준 교수/고려대) | ||||||
| 14:30 |
(좌장: 최진우 교수/경희대)
| Industry 2 (좌장: 김승룡 교수/KAIST) | |||||
| 15:00 | Tutorial 2 ■ 15:00 - 16:15 | Oral 8 (좌장: 오태현 교수/KAIST) | |||||
| Poster 1 ■ 15:15 - 16:45
| |||||||
| 15:30 | Poster 2 ■ 15:30 - 17:00 | ||||||
| 16:00 | KCCV 프로그램 위원회 ■ 16:00 - 17:00 | Poster 3 ■ 16:00 - 17:30 | |||||
| 16:30 | Tutorial 3 ■ 16:30 - 17:45 | ||||||
| 17:00 | Doctoral Colloquium (좌장: 최종원 교수/중앙대,황성재 교수/연세대) | KCVS 총회 ■ 17:00 - 18:00 | |||||
| 17:30 | Closing
| ||||||
| 18:00 | |||||||
| W.1 | 10:00 ~ 10:30 | 계속 걷는 연구자의 길 | 백성용 교수(한양대) |
| W.2 | 10:35 ~ 11:05 | Self-evolving Researcher: 정답 없는 시대의 연구 진로 설계 | 김현우 교수(KAIST) |
| W.3 | 11:10 ~ 12:00 | 대학원생의 정체성 | 오태현 교수(KAIST) |
| T.1 | 13:30 ~ 14:45 | Zeroth-Order Estimation을 활용한 VLM 토큰 압축 |
|
| T.2 | 15:00 ~ 16:15 | 스케일러블한 피드포워드 3차원 가우시안 스플래팅 | 박은병 교수 (연세대) |
| T.3 | 16:30 ~ 17:45 | Geometric Latent Diffusion | 김승룡 교수 (KAIST) |
| O1.1 | 10:00 ~ 10:15 | Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models / NeurIPS 2025 | 박경문 교수(고려대) |
| O1.2 | 10:15 ~ 10:30 | Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models / NeurIPS 2025 | 정희철 교수(경북대) |
| O1.3 | 10:30 ~ 10:45 | Revisiting Geometric Obfuscation with Dual Convergent Lines for Privacy-Preserving Image Queries in Visual Localization / CVPR 2026 | 홍제형 교수(한양대) |
| O1.4 | 10:45 ~ 11:00 | CLP: A Real-World Dataset of Contaminated Lens Protectors for Robust Semantic Segmentation / CVPR 2026 |
|
| Keynote 1 | 11:00 ~ 12:00 | When Should an AI Assistant Speak? Proactive and Communicative AI in Egocentric Video | Prof. Angela Yao (National Univ. of Singapore) |
| O2.1 | 13:30 ~ 13:45 | Reward Sharpness Aware Fine Tuning for Diffusion Models / CVPR 2026 | 김관영 교수(GIST) |
| O2.2 | 13:45 ~ 14:00 | FiDeSR: High-Fidelity and Detail-Preserving One-Step Diffusion Super-Resolution / CVPR 2026 | 박상효 교수(경북대) |
| O2.3 | 14:00 ~ 14:15 | SeaCache: Spectral-Evolution-Aware Cache for Accelerating Diffusion Models / CVPR 2026 | 허재필 교수(성균관대) |
| O2.4 | 14:15 ~ 14:30 | Semantic Alignment for Pose-Invariant Identity Preserving Diffusion / CVPR 2026 | 차은주 교수(숙명여대) |
| I1.1 | 14:30 ~ 14:45 | 데이터 플라이휠 기반 자율주행 소개 | 김하영 (42dot) |
| I1.2 | 14:45 ~ 15:00 |
스크린에서 캐빈으로: 범용 운전자 시선 지능 (Gaze Intelligence)의 진화
| 마노즈 판데이
(델타엑스)
|
| I1.3 | 15:00 ~ 15:15 |
문서 이해: 실제 환경에서 마주하는 비전-언어 과제
| 임비(로민) |
Poster Session 1
Poster No.
| Time | Paper Name | Advisor | Presenter |
1 | 15:15 ~ 16:45 | TRACE: Your Diffusion Model is Secretly an Instance Edge Detector / ICLR 2026 | 김경수 | 이지석 |
2 | Mark4D: Temporally-Consistent Watermarking for 4D Gaussian Splatting / CVPR 2025 | 김원화 | 이재진 | |
3 | Hear What Matters! Text-conditioned Selective Video-to-Audio Generation / CVPR2026 | 이지영 | 이지영 | |
4 | Training-free Mixed-Resolution Latent Upsampling for Spatially Accelerated Diffusion Transformers / CVPR 2026 | 전세영 | 이경렬 | |
5 | ConceptSplit: Decoupled Multi-Concept Personalization of Diffusion Models via Token-wise Adaptation and Attention Disentanglement / ICCV 2025 | 박경문 | 임하빈 | |
6 | Active Test-time Vision-Language Navigation / NeurIPS 2025 | 김상필 | 고희주 | |
7 | MatLat: Material Latent Space for PBR Texture Generation / CVPR 2026 | 성민혁 | 여경민 | |
8 | Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation / ICCV 2025 | 허재필 | 정지우 | |
9 | M3KG-RAG: Multi-hop Multimodal Knowledge Graph-enhanced Retrieval-Augmented Generation / CVPR 2026 | 김상필 | 박형철 | |
10 | WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning / CVPR 2026 | 황성주 | 여운경 | |
11 | Bidirectional Likelihood Estimation with Multi-Modal Large Language Models for Text-Video Retrieval /ICCV 2025 | 김현우 | 나지혜 | |
12 | Detecting Unknown Objects via Energy-based Separation for Open World Object Detection / CVPR 2026 | 박경문 | 허준우 | |
13 | Beyond the Ground Truth: Enhanced Supervision for Image Restoration / CVPR 2026 | 한보형 | 류동헌, 하인주 | |
14 | Token Warping Helps MLLMs Look from Nearby Viewpoints / CVPR 2026 | 성민혁 | 박찬호 | |
15 | Ψ-Sampler: Initial Particle Sampling for SMC-Based Inference-Time Reward Alignment in Score Models / NeurIPS 2025 | 성민혁 | 민윤홍 | |
16 | PHAC: Promptable Human Amodal Completion / CVPR 2026 | 장주용 | 노승영 | |
17 | Masking Matters: Unlocking the Spatial Reasoning Capabilities of LLMs for 3D Scene-Language Understanding / CVPR 2026 | 허재필 | 전예림 | |
18 | Open-ended Hierarchical Streaming Video Understanding with Vision Language Models / ICCV 2026 | 김선주 | 최예은 | |
19 | TripleSumm: Adaptive Triple-Modality Fusion for Video Summarization / ICLR 2026 | 이준석 | 김수민 | |
20 | Generate, Analyze, and Refine: Training-Free Sound Source Localization via MLLM Meta-Reasoning / CVPR 2026 | 김정욱 | 박수빈 | |
21 | PTC-Depth: Pose-Refined Monocular Depth Estimation with Temporal Consistency / CVPR 2026 | 김태현 | 김태현 | |
22 | Class-Wise Federated Averaging for Efficient Personalization / ICCV 2025 | 최대영 | 최대영 | |
23 | FaceShield: Defending Facial Image against Deepfake Threats / ICCV 2025 | 김상필 | 정재환 | |
24 | Syncphony: Synchronized Audio-to-Video Generation with Diffusion Transformers / ICLR 2026 | 어영정 | 송지빈 | |
25 |
Coupling Liquid Time-Constant Encoders with Modern Hopfield Memory / CVPR 2026
| 고재필 | Bishal Swain | |
26 | Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration / NeurIPS 2025 | 김호성 | 이융희 | |
27 | Pose-guided Enriched Feature Learning for Federated-by-camera Person Re-identification / CVPR 2026 | 심재영 | 오주형 | |
28 | MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics / NeurIPS 2025 | 김태균 | 이창민 | |
29 | Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models / NeurIPS 2025 | 성민혁 | 황지성 | |
30 | AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models / NeurIPS 2025 | 함범섭 | 최정우 | |
31 | GeoAvatar: Adaptive Geometrical Gaussian Splatting for 3D Head Avatar / ICCV 2025 | 박경문 | 류하민 | |
32 | Diffusion Feature Field for Text-based 3D Editing with Gaussian Splatting / NeurIPS 2025 | 허재필 | 고은서 | |
33 | SEA: Evaluating Sketch Abstraction Efficiency via Element-level Commonsense Visual Question Answering / CVPR 2026 | 김지희 | 박지호 | |
34 | Follow the Saliency: Supervised Saliency for Retrieval-augmented Dense Video Captioning / CVPR 2026 | 김동진 | 최승희 | |
35 | Motion Prior Distillation in Time Reversal Sampling for Generative Inbetweening / ICLR 2026 | 전해곤 | 전우석 | |
36 | Foundation Encoders Are All You Need for Preference-Aware Personalization / CVPR 2026 | 서영덕 | 김형진 | |
37 | FEAT: Fashing Editing and Try-On from Any Design / CVPR 2026 | 이재구 | 권소예 | |
38 | Visual-RRT: Finding Paths toward Visual-Goals via Differentiable Rendering / CVPR 2026 | 윤성의 | 이세빈 | |
39 | Dataset Distillation of 3D Point Clouds via Distribution Matching / NeurIPS 2025 | 심재영 | 임재영 | |
40 | Parameterization-Based Dataset Distillation of 3D Point Clouds through Learnable Shape Morphing / ICLR 2026 | 심재영 | 임재영 | |
41 | Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs / ICLR 2026 | 한보형 | 김민지 | |
42 | BUFFER-X: Towards Zero-Shot Point Cloud Registration in Diverse Scenes / ICCV 2025 | 박재식 | 서민균 | |
43 | MDP-Omni: Parameter-free Multimodal Depth Prior-based Sampling for Omnidirectional Stereo Matching / ICCV 2025 | 이상준 | 손은진 | |
44 | Option-aware Temporally Abstracted Value for Offline Goal-Conditioned Reinforcement Learning / NeurIPS 2025 | 문태섭 | 한지수 | |
45 | Analyzing the Training Dynamics of Image Restoration Transformers: A Revisit to Layer Normalization / ICLR 2026 | 허재필 | 이민규 | |
46 | DeepVideo-R1: Video Reinforcement Fine-Tuning via Difficulty-aware Regressive GRPO / NeurIPS 2025 | 김현우 | 박진영 |
| D.1 | 16:45~16:55 | From Compression to Visual Intelligence: Codec-Aware Neural Representations for Efficient Visual Systems | |
| D.2 | 16:55~17:05 | Dataset Compression for Efficient AI | |
| D.3 | 17:05~17:15 | Frequency-Aware Representation Learning for Robust and Generalizable Image Analysis | |
| D.4 | 17:15~17:25 | Towards Trustworthy AI: Mitigating Unsafe Content and Privacy Leakage in Generative Models | 안재신 (경북대) |
| D.5 | 17:25~17:35 | Cross-Domain Generalizable Representation Learning for Face Anti-Spoofing | 정승진 (중앙대) |
| D.6 | 17:35~17:45 | See, Understand, and Act Through Adversity: Robust AI for Real World Deployment | 이소현 (POSTECH) |
| D.7 | 17:45~17:55 | From Visual Perception to Physical Intelligence: Reconstructing Human Expertise from Video | 신지수 (GIST) |
| D.8 | 17:55~18:05 | Embodied Vision for Real-World Perception and Action | 박충현 (POSTECH) |
| D.9 | 18:05~18:15 | Towards Generative Motion Modeling: From Language to Spatial Signals | 황인우 (서울대) |
| DP.1 | [Poster] [CV] | Drifting Field Policy: A One-Step Generative Policy via Wasserstein Gradient Flow | |
| DP.2 | [Poster] [CV] | Frequency-Aware Representation Learning for Robust and Generalizable Image Analysis | |
| DP.3 | [Poster] [CV] | Toward Real-World 3D Visual Perception | |
| DP.4 | [Poster] [CV] | Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models | 안재신 (경북대) |
| DP.5 | [Poster] [CV] | See, Understand, and Act Through Adversity: Robust AI for Real World Deployment | 이소현 (POSTECH) |
| DP.6 | [Poster] [CV] | State-Space Models for Visual Representation Learning | 이진성 (POSTECH) |
| DP.7 | [Poster] [CV] | From Compression to Visual Intelligence: Codec-Aware Neural Representations for Efficient Visual Systems | 한우경 (고려대) |
| DP.8 | [Poster] [CV] | Toward Motion Generative Modeling: From Language to Spatial Signals | 황인우 (서울대) |
| O3.1 | 09:00 ~ 09:15 | Hear you are: Teaching LLMs Spatial Reasoning with Vision and Spatial Sound / CVPR 2026 | 류형곤 교수(한국외대) |
| O3.2 | 09:15 ~ 09:30 | IVAAN: Instance-Level Vision-Language Alignment via Attribute-Guided Text Prompt Generation for Nuclei Analysis / CVPR 2026 | 박상현 교수(POSTECH) |
| O3.3 | 09:30 ~ 09:45 | ZOO-Prune: Training-Free Token Pruning via Zeroth-Order Gradient Estimation in Vision-Language Models / CVPR 2026 | 홍성은 교수(성균관대) |
| O3.4 | 09:45 ~ 10:00 | Zero-Shot Compositional Video Learning with Coding Rate Reduction / ICCV 2025 | 김은솔 교수 (한양대) |
| O4.1 | 10:00 ~ 10:15 | PR-MaGIC: Prompt Refinement Via Mask Decoder Gradient Flow For In-Context Segmentation / CVPR 2026 | 김원화 교수(POSTECH) |
| O4.2 | 10:15 ~ 10:30 | How Far Can We Go With Synthetic Data for Audio-Visual Sound Source Localization? / CVPR 2026 | 정준선 교수(KAIST) |
| O4.3 | 10:30 ~ 10:45 | Video Scene Segmentation with Genre and Duration Signals / ICLR 2026 | 전해곤 교수(연세대) |
| O4.4 | 10:45 ~ 11:00 | Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition / NeurIPS 2025 |
|
| Keynote 2 | 11:00 ~ 12:00 | Engineering Interpretable and Safe AI Systems | Prof. René Vidal (Univ. of Pennsylvania) |
| O5.1 | 13:30 ~ 13:45 | Learning from Oblivion: Predicting Knowledge-Overflowed Weights via Retrodiction of Forgetting / CVPR 2026 | 김정욱 교수(경희대) |
| O5.2 | 13:45 ~ 14:00 | Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity / NeurIPS 2025 | 손진희 교수(POSTECH) |
| O5.3 | 14:00 ~ 14:15 | Asymmetric Synthetic Data Update for Domain Incremental Dataset Distillation / ICLR 2026 | 심재영 교수(UNIST) |
| O5.4 | 14:15 ~ 14:30 | Anomaly as Non-Conformity via Training-Free Graph Laplacian Energy Minimization / CVPR 2026 | 백성용 교수(한양대) |
| I2.1 | 14:30 ~ 14:45 |
AI를 활용한 퍼포먼스 광고 최적화
| 한승현(몰로코) |
| I2.2 | 14:45 ~ 15:00 | 서울 월드 모델: 실제 도시 기반의 월드 시뮬레이션 모델 | 윤상두 (네이버) |
| I2.3 | 15:00 ~ 15:15 | 데이터 기반 인텔리전스: 피지컬 AI와 자율주행을 위한 고품질 AI 데이터 솔루션 | 유영준, 장욱(넥스데이타) |
| I2.4 | 15:15 ~ 15:30 | 인지-판단-제어까지: 산업 현장의 3D 비전과 도전과제 | 김수상(포스코DX) |
Poster No.
| Time | Paper Name | Advisor | Presenter |
1 | 15:30 ~ 17:00 | LIFT and PLACE: A Simple, Stable, and Effective Knowledge Distillation Framework for Lightweight Diffusion Models / CVPR 2026 | 유재준 | 여상엽 |
2 | Video Color Grading via Look-Up Table Generation / ICCV 2025 | 전해곤 | 신승현 | |
3 | ExploreGS: Explorable 3D Scene Reconstruction with Virtual Camera Samplings and Diffusion Priors / ICCV 2025 | 김선주 | 김민수 | |
4 | Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization / CVPR 2026 | 심현정 | 강인하 | |
5 | Visual Funnel: Resolving Contextual Blindness in Multimodal Large Language Models / CVPR 2026 | 김준영 | 전민규 | |
6 | HyCal: A Training-Free Prototype Calibration Method for Cross-Discipline Few-Shot Class-Incremental Learning / CVPR 2026 | 김영빈 | 이은주 | |
7 | Shape-of-You: Fused Gromov-Wasserstein Optimal Transport for Semantic Correspondence in-the-Wild / CVPR 2026
| 홍제형 | 임지인 | |
8 | R3-PCQA: Ray-Reprojection-Reinforcement for No-Reference 3D Point Cloud Quality Assessment / CVPR 2026 | 오희석 | 서상혁 | |
9 | MemoryTalker: Personalized Speech-Driven 3D Facial Animation via Audio-Guided Stylization / ICCV 2025 | 김학구 | 김학구 | |
10 | Emulating Self-attention with Convolution for Efficient Image Super-Resolution/ ICCV 2025 | 노영민 | 이동헌 | |
11 | MoE-GS: Mixture of Experts for Dynamic Gaussian Splatting / ICLR 2026 | 공경보 | 진인환 | |
12 | Automated Model Discovery via Multi-modal & Multi-step Pipeline / NeurIPS 2025 | 오태현 | 이정목 | |
13 | Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling / NeurIPS 2025 | 고종환 | 안재준 | |
14 | Interpreting vision transformers via residual replacement model / NeurIPS 2025 | 황성재 | 김준혁 | |
15 | An Efficient Post-hoc Framework for Reducing Task Discrepancy of Text Encoders for Composed Image Retrieval / ICCV 2025 | 문태섭 | 변재석 | |
16 | Understanding Flatness in Generative Models: Its Role and Benefits / ICCV 2025 | 유재준 | 서경국 | |
17 | Beyond Spatial Frequency: Pixel-wise Temporal Frequency-based Deepfake Video Detection / ICCV 2025 | 최종원 | 김태훈 | |
18 | Group-wise Scaling and Orthogonal Decomposition for Domain-Invariant Feature Extraction in Face Anti-Spoofing / ICCV 2025 | 최종원 | 정승진 | |
19 | HandVQA: Diagnosing and Improving Fine-Grained Spatial Reasoning about Hands in Vision-Language Models / CVPR 2026 | 백승렬 | 백승렬 | |
20 | ViKey: Enhancing Temporal Understanding in Videos via Visual Prompting / CVPR 2026 | 황성재 | 이연경 | |
21 | Image-Guided Geometric Stylization of 3D Meshes / CVPR 2026 | 김영민 | 최장운 | |
22 | AJAHR: Amputated Joint Aware 3D Human Mesh Recovery / ICCV2025 | 최종원 | 조현진, 최기윤 | |
23 | MVLM: Template-Free Tracking via Vision-Language Margin Confidence and Memory-Gated Tracking / CVPR26 | 배승환 | 박대현 | |
24 | Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding / CVPR 2026 | 이지형 | 정성준 | |
25 |
Stake the Points: Structure-Faithful Instance Unlearning / CVPR 2026
| 김은우 | 홍기성 | |
26 | FedMeNF: Privacy-Preserving Federated Meta-Learning for Neural Fields / ICCV 2025 | 김건희 | 윤준혁 | |
27 | Enhancing Multi-Image Understanding through Delimiter Token Scaling / ICLR 2026 | 최준석 | 이민영 | |
28 | ChartCap: Mitigating hallucination of dense chart captioning / ICCV 2025 | 김건희 | 임준영 | |
29 | Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span / NeurIPS 2025 | 김건희 | 임준영 | |
30 | Affostruction: 3D Affordance Grounding with Generative Reconstruction / CVPR 2026 | 조민수 | 박충현 | |
31 | Uncertainty-guided Compositional Alignment with Part-to-Whole Semantic Representativeness in Hyperbolic Vision-Language Models / CVPR 2026 | 전세영 | 장지하 | |
| 32 | Exploring State-Space Models for Data-Specific Neural Representations / ICLR 2026 | 곽수하 | 이진성 | |
33 | Relational Feature Caching for Accelerating Diffusion Transformers / ICLR 2026 | 함범섭 | 손병관 | |
34 | CLaD: Planning with Grounded Foresight via Cross-Modal Latent Dynamics / CVPR 2026 | 윤성의 | 정앤드류 | |
35 | GLINT: Modeling Scene-Scale Transparency via Gaussian Radiance Transport / CVPR 2026 | 연수용 | 나영주 | |
36 | GaRA-SAM: Robustifying Segment Anything Model with Gated-Rank Adaptation / NeurIPS 2025 | 곽수하 | 이소현 | |
37 | Robust Promptable Video Object Segmentation / CVPR 2026 | 곽수하 | 이소현 | |
38 |
See, Understand, and Act Through Adversity: Robust AI for Real World Deployment | 곽수하 | 이소현 | |
39 | From Compression to Visual Intelligence: Codec-Aware Neural Representations for Efficient Visual Systems | 진경환 | 한우경 | |
40 |
Dataset Compression for Efficient AI | 심재영 | 오민영 | |
41 | Frequency-Aware Representation Learning for Robust and Generalizable Image Analysis
| 이상철 | 남주현 | |
42 |
Towards Trustworthy AI: Mitigating Unsafe Content and Privacy Leakage in Generative Models | 정희철 | 안재신 | |
43 |
Cross-Domain Generalizable Representation Learning for Face Anti-Spoofing | 최종원 | 정승진 | |
44 |
From Visual Perception to Physical Intelligence: Reconstructing Human Expertise from Video | 전해곤 | 신지수 | |
45 | Toward Real-World 3D Visual Perception | 조민수 | 박충현 | |
46 | Towards Generative Motion Modeling: From Language to Spatial Signals | 김영민 | 황인우 |
| O6.1 | 10:00 ~ 10:15 | Combinative Matching for Geometric Shape Assembly / ICCV 2025 | 조민수 교수(POSTECH) |
| O6.2 | 10:15 ~ 10:30 | From Corners to Fiducial Tags: Revisiting Checkerboard Calibration for Event Cameras / CVPR 2026 | 주경돈 교수(UNIST) |
| O6.3 | 10:30 ~ 10:45 | Dexterous World Models / CVPR 2026 | 주한별 교수(서울대) |
| O6.4 | 10:45 ~ 11:00 | Emergent Temporal Correspondences from Video Diffusion Transformers / NeurIPS 2025 |
|
| Keynote 3 | 11:00 ~ 12:00 | World Models: Connecting the Digital and Physical World | Prof. Matthias Nießner (Tech. Univ. of Munich) |
| Invited Talk | 12:00 ~ 12:30 | Building Interactable 3D Spaces from Imperfect Observations | Prof. Angela Dai (Tech. Univ. of Munich) |
| O7.1 | 14:00 ~ 14:15 | Event-Driven Storytelling with Multiple Lifelike Humans in a 3D scene / ICCV 2025 | 김영민 교수(서울대) |
| O7.2 | 14:15 ~ 14:30 | MoRel: Long-Range Flicker-Free 4D Motion Modeling Anchor Relay-based Bidirectional Blending via with Hierarchical Densification / CVPR 2026 | 오지형 교수(중앙대) |
| O7.3 | 14:30 ~ 14:45 | Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning / CVPR 2026 | 조재원 교수(건국대) |
| O7.4 | 14:45 ~ 15:00 | Multi-view Pyramid Transformer: Look Coarser to See Broader / CVPR 2026 | 박은병 교수 (연세대) |
| O8.1 | 15:00 ~ 15:15 | CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting / ICLR 2026 | 김상필 교수(고려대) |
| O8.2 | 15:15 ~ 15:30 | Radiometrically Consistent Gaussian Surfels for Inverse Rendering / ICLR 2026 | 윤성의 교수(KAIST) |
| O8.3 | 15:30 ~ 15:45 | InsideOut: Integrated RGB-Radiative Gaussian Splatting for Comprehensive 3D Object Representation / ICCV 2025 | 최종원 교수 (중앙대) |
| O8.4 | 15:45 ~ 16:00 | OpenBox: Annotate Any Bounding Boxes in 3D / NeurIPS 2025 | 박재식 교수 (서울대) |
Poster No.
| Time | Paper Name | Advisor | Presenter |
1 | 16:00 ~ 17:30 | CHROMA: Consistent Harmonization of Multi-View Appearance via Bilateral Grid Prediction / ICLR 2026 | 전해곤 | 신지수 |
2 | Selectively Extracting and Injecting Visual Attributes into Text-to-Image Models / CVPR 2026 | 주재걸 | 최승환 | |
3 | TAS-LoRA: Transformer Architecture Search with Mixture-of-LoRA Experts / CVPR 2026 | 함범섭 | 전제민 | |
4 | Planning in 8 Tokens: A Compact Discrete Tokenizer for Latent World Model / CVPR 2026 | 곽수하 | 김동원 | |
5 | ESSENTIAL: Episodic and Semantic Memory Integration for Video Class-Incremental Learning / ICCV 2025 | 최진우 | 이종서 | |
6 | A Semantically Disentangled Unified Model for Multi-category 3D Anomaly Detection/ CVPR 2026 | 조명아 | 김수연 | |
7 | Learning 3D Object Spatial Relationships from Pre-trained 2D Diffusion Models / ICCV 2025 | 주한별 | 백상원 | |
8 | DextER: Language-driven Dexterous Grasp Generation with Embodied Reasoning / CVPR 2026 | 조민수 | 박은하 | |
9 | CLAY: Conditional Visual Similarity Modulation in Vision-Language Embedding Space / CVPR 2026 | 오태현 | 임소휘 | |
10 | M2SFormer: Multi-Spectral and Multi-Scale Attention with Edge-Aware Difficulty Guidance for Image Forgery Localization / ICCV 2025 | 이상철 | 남주현 | |
11 | Identity-aware Language Gaussian Splatting for Open-vocabulary 3D Semantic Segmentation / ICCV 2025 | 김원준 | 류건 | |
12 | FRAMER: Frequency-Aligned Self-Distillation with Adaptive Modulation Leveraging Diffusion Priors for Real-World Image Super-Resolution / CVPR 2026 | 오지형 | 최승호 | |
13 | FLAIR: Frequency- and Locality-Aware Implicit Neural Representations / CVPRF 2026 | 오지형 | 고석훈 | |
14 | Human Interaction-Aware 3D Reconstruction from a Single Image / CVPR 2026 | 전세영 | 전서윤 | |
15 | Space-Time Forecasting of Dynamic Scenes with Motion-aware Gaussian Grouping / CVPR 2026 | 조민수 | 이준명 | |
16 | SGSoft: Learning Fused Semantic-Geometric Features for 3D Shape Correspondence via Template-Guided Soft Signals / CVPR 2026 | 심현정 | 윤소연 | |
17 | Axis-level Symmetry Detection with Group-Equivariant Representation / ICCV 2025 | 조민수 | 유원균 | |
18 | Decoupled Generative Modeling for Human-Object Interaction Synthesis / CVPR 2026 | 김상필 | 정환희 | |
19 | CRIT: Graph-Based Automatic Data Synthesis to Enhance Cross-Modal Multi-Hop Reasoning / CVPR 2026 | 서홍석 | 유승우 | |
20 | Stay in your Lane: Role Specific Queries with Overlap Suppression Loss for Dense Video Captioning / CVPR 2026 | 조재원 | 백승협, 이지민 | |
21 | DeepProtect: Proactive Face-Swapping Defense using Identity Blending and Attribute Distortion / CVPR 2026 | 유석봉 | 백승혁 | |
22 | Shift-and-Sum Quantization for Visual Autoregressive Models / ICLR 2026 | 함범섭 | 문재현 | |
23 | Learning Compact 3D Representations from Feed-Forward Novel View Synthesis / CVPR 2026 | 김승룡 | 안홍규 | |
24 | Low-Resolution Editing is All You Need for High-Resolution Editing / CVPR 2026 | 한보형 | 이현수 | |
25 |
Towards Robust Vision Transformers: Path Dependency Analysis and a Simple Two-Stage Adversarial Training / CVPR 2026
| 송병철 | 홍정우 | |
26 | MonoSAOD: Monocular 3D Object Detection with Sparsely Annotated Label / CVPR 2026 | 김정욱 | 정준영 | |
27 | ELITE: Efficient Gaussian Head Avatar from a Monocular Video via Learned Initialization and Test-time Generative Adaptation / CVPR 2026 | 오태현 | 김유왕 | |
28 | MV-TAP: Tracking Any Point in Multi-View Videos / CVPR 2026 | 김승룡 | 구자혁 | |
29 | Dual-Path TempOral Decoder for End-to-End Multi-Object Tracking / NeurIPS 2025 | 고영준 | 김현섭 | |
30 | ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion / NeurIPS 2025 | 김동진 | 고성호 | |
31 | JPEG Processing Neural Operator for Backward-Compatible Coding / ICCV 2025 | 진경환 | 한우경 | |
32 | Motion Synthesis with Sparse and Flexible Keyjoint Control / ICCV 2025 | 김영민 | 임동근, 황인우 | |
33 | LightSplat: Fast and Memory-Efficient Open-Vocabulary 3D Scene Understanding in Five Seconds / CVPR 2026 | 주경돈 | 방재훈, 김민지 | |
34 | CVA: Context-aware Video-text Alignment for Video Temporal Grounding / CVPR 2026 | 임성훈 | 문성호 | |
35 | Cross-Modal Emotion Transfer for Emotion Editing in Talking Face Video / CVPR 2026 | 김태환 | 최찬혁 | |
36 | AgilePruner: An Empirical Study of Attention and Diversity for Adaptive Visual Token Pruning in Large Vision-Language Models / ICLR 2026 | 공경보 | 백창우 | |
37 | Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers / NeurIPS 2025 | 김승룡 | 김채현 | |
38 | OVS Meets Continual Learning: Towards Sustainable Open-Vocabulary Segmentation / NeurIPS 2025 | 최준석 | 황동준 | |
39 | FEAST: Fully Connected Expressive Attention for Spatial Transcriptomics / CVPR 2026 | 황성재 | 정태진 | |
40 | Correspondence-Attention Alignment for Multi-View Diffusion Models / CVPR 2026 | 김승룡 | 권민경 | |
41 | DialNav: Multi-turn Dialog Navigation with a Remote Guide / ICCV 2025 | 서홍석 | 한리경 | |
42 | DiffPS: Leveraging Prior Knowledge of Diffusion Model for Person Search/ ICCV 2025 | 엄찬호 | 김기열 | |
43 | MSQ: Memory-Efficient Bit Sparsification Quantization/ ICCV 2025 | 고종환 | 한석호 | |
44 | PhysGaia: A Physics-Aware Benchmark of Multi-Body Interactions for Dynamic Novel View Synthesis / CVPR 2026 | 한보형 | 김미정 | |
45 | Seeing Through Touch:Tactile-Driven Visual Localization of Material Regions / CVPR 2026 | Arda Senocak | 김선규 | |
46 | PARTE: Part-Guided Texturing for 3D Human Reconstruction from a Single Image / ICCV 2025 | 문경식 | 김동환 |