cvlab-kaist

Official implementation of "Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation"

[CVPR 2026] Official implementation of "VideoMaMa: Mask-Guided Video Matting via Generative Prior"

Official implementation of “GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting” by Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon...

Official Implementation of "CAT-Seg🐱: Cost Aggregation for Open-Vocabulary Semantic Segmentation"

Code for "Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting" by Jaewoo Jung, Jisang Han, Honggyu An, Jiwon Kang, Seonghoon Park, and Seungryong Kim

Official implementation of "Repurposing Geometric Foundation Models for Multi-view Diffusion"

Official implementation of "Text-Aware Image Restoration with Diffusion Models"

[ICML'25] Official Implementation of "PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting"

[CVPR'26] Official implementation of "Emergent Outlier View Rejection in Visual Geometry Grounded Transformers"

Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)

Official implementation of "Geometric Action Model for Robot Policy Learning"

[CVPR'26] Official implementation of "C3G: Learning Compact 3D Representations with 2K Gaussians"

Official implementation of "Diffusion Model for Dense Matching" (ICLR'24 Oral)

Code Implementation of "WorldCam: Interactive Autoregressive 3D Gaming Worlds with Camera Pose as a Unifying Geometric Representation"

Official Implementation of "MoDiTalker: Motion-Disentangled Diffusion Model for High-Fidelity Talking Head Generation" (AAAI 2025)

Official implementation of "DreamMatcher: Appearance Matching Self-Attention for Semantically-Consistent Text-to-Image Personalization" (CVPR 2024)

Official implementation of "VIRAL: Visual Representation Alignment for MLLMs".

[ICML 2026] Official implementation of "Deep Forcing: Training-Free Long Video Generation with Deep Sink and Participative Compression"

Official code implementation for TrackCraft3R: Repurposing Video Diffusion Transformers for Dense 3D Tracking

Official repository for LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data (CVPR 2023)

[CVPR 2024 (Highlight)] Unifying Correspondence, Pose and NeRF for Generalized Pose-Free Novel View Synthesis from Stereo Pairs

Official Implementation of WACV 2023 paper "3D GAN Inversion with Pose Optimization".

Official implementation of "WorldKV: Efficient World Memory with World Retrieval and Compression"

Official implementation of "Exploring Temporally-Aware Features for Point Tracking" (CVPR 2025)

[NeurIPS'25] Official implementation of "Emergent Temporal Correspondences from Video Diffusion Models"

Official Implementation of "Learning Temporally Aware Compact Gaussians for Feed-Forward 4D Reconstruction"

[NeurIPS'25] Official implementation of "D^2USt3R: Enhancing 3D Reconstruction with 4D Pointmaps for Dynamic Scenes"

Official implementation of "Seg4Diff: Unveiling Open-Vocabulary Segmentation in Text-to-Image Diffusion Transformers" (NeurIPS 2025)

Official code implementation of NeMF (NeurIPS'22)

Official implementation of "L3G-World: Real-Time Infinite World Generation with Latent 3D Gaussian Memory"

CVPR 2025 (Highlight) : Official implementation of "Cross-View Completion Models are Zero-shot Correspondence Estimators"

Official code implementation of MIDMs: Matching Interleaved Diffusion Models for Exemplar-based Image Translation (AAAI'23)

Official code implementation of "DäRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation"(NeurIPS 2023)

Official implementation of "Seurat: From Moving Points to Depth", CVPR 2025 Highlight

Official repository for InstaFormer: Instance-aware Image-to-Image Translation with Transformer (CVPR 2022)

Official implementation of "MV-TAP: Tracking Any Point in Multi-View Videos"

Official implementation of "CAMEO: Correspondence-Attention Alignment for Multi-View Diffusion Models"

Official implementation of "A Noise is Worth Diffusion Guidance", code and weights will be available soon.

Official implementation of "URECA : Unique Region Caption Anything"

Official Implementation of "Towards Open-Vocabulary Semantic Segmentation without Semantic Labels" (NeurIPS 2024)

Official implementation of "Retrieval-Augmented Score Distillation for Text-to-3D Generation"

Official implementation of "GARD: Geometry-Aware Representation Denoising for Robust Multi-view 3D Reconstruction"

Official Implementation of "Aligned Novel View Image and Geometry Synthesis via Cross-modal Attention Instillation"

Official implementation of "Repurposing Video Diffusion Transformers for Robust Point Tracking"

Official repository for CATs++: Boosting Cost Aggregation with Convolutions and Transformers (TPAMI'22)

Official implementation of "Visual Persona: Foundation Model for Full-Body Human Customization" (CVPR 2025)

[ICLR'26] Official implementation of "3D Scene Prompting for Scene-Consistent Camera-Controllable Video Generation"

Official implementation of "🍎APPLE: Attribute-Preserving Pseudo-Labeling for Diffusion-Based Face Swapping"