Computational Visual Media

This book constitutes the refereed proceedings of CVM 2025, the 13th International Conference on Computational Visual Media, held in Hong Kong SAR, China, in April 2025.

The 67 full papers were carefully reviewed and selected from 335 submissions. The papers are organized in topical sections as follows:

Part I: Medical Image Analysis, Detection and Recognition, Image Enhancement and Generation, Vision Modeling in Complex Scenarios

Part II: 3D Geometry and Rendering, Generation and Editing, Image Processing and Optimization

Part III: Image and Video Analysis, Multimodal Learning, Geometrical Processing, Applications

Inhalt

3D Geometry and Rendering

CMU-Flownet: Exploring Point Cloud Scene Flow Estimation in Occluded Scenario.- 3DFaceController: Region-Controllable Face Synthesis via Decomposed and Recomposed Neural Radiance Fields.- High-Quality and Efficient Inverse Rendering for Geometry, Material, and Illumination Reconstruction.- An efficient and robust tracing method based on matrix representation for surface-surface intersection.- Completing Dental Models While Preserving Crown Geometry and Meshing Topology.- TPD-NeRF: Temporally Progressive Reconstruction of Dynamic Neural Radiance Fields from Monocular Video.- Direct Extraction of High-Quality and Feature-Preserving Triangle Meshes from Signed Distance Functions.- MTScan: Material Transfer from Partial Scans to CAD models.- HR Human: Modeling Human Avatars with Triangular Mesh and High-Resolution Textures from Videos.- VGA: Reconstruction of Vivid Gaussian Avatar from Monocular Videos.- High-accuracy Fractured Object Reassembly under Arbitrary Poses.-

Generation and Editing

SingleDream: Attribute-Driven T2I Customization from a Single Reference Image.- Concept-Edge Fusion: Background Generation for Product Presentation Based on Text-to-Image Model.- Sketch-Guided Scene-level Image Editing with Diffusion Models.- Semantic-guided Coarse-to-Fine Diffusion Model for Self-supervised Image Shadow Removal.- Extreme Two-View Geometry From Object Poses with Diffusion Models.- TAD: A plug-and-play Task Arithmetic approach for augmenting Diffusion models.- DiffVecFont: Fusing Dual-Mode Reconstruct Vector Fonts via Masked Diffusion Transformers.-

Image Processing and Optimization

CosCAD: Cross-Modal CAD Model Retrieval and Pose Alignment from a Single Image.- TCDNet: Texture and Color Dynamic Network for Image Harmonization.- Unsupervised Monocular Depth Estimation for Foggy Images with Domain Separation and Self-depth Domain Conversion.- Unwarping Screen Content Images via Structure-texture Enhancement Network and Transformation Self-estimation.