E-raamat: Pattern Recognition and Computer Vision: 7th Chinese Conference, PRCV 2024, Urumqi, China, October 18-20, 2024, Proceedings, Part VI

Visual Harmony: LLM's Power in Crafting Coherent Indoor Scenes from
ImagesSuperpixel Cost Volume Excitation for Stereo MatchingMulti-view Depth
Estimation with Adaptive Feature Extraction and Region-Aware Depth
Prediction3D Data Augmentation for Driving Scenes on CameraA Pose-Aware
Auto-Augmentation Framework for 3D Human Pose and Shape Estimation from
Partial Point CloudsEfficient Emotional Talking Head Generation via Dynamic
3D Gaussian RenderingGeneralizable Geometry-aware Human Radiance Modeling
from Multi-view ImagesAG-NeRF: Attention-guided Neural Radiance Fields for
Multi-height Large-scale Outdoor Scene RenderingJPA: A Joint-Part Attention
for Mitigating Overfocusing on 3D Human Pose EstimationRealistic and
Visually-pleasing 3D Generation of Indoor Scenes from a Single
ImageAttenPoint: Exploring Point Cloud Segmentation through Attention-Based
ModulesMTFusion: Reconstructing Any 3D Object from Single Image Using
Multi-Word Textual InversionMulti-view 3D Reconstruction by Fusing
Polarization InformationQuat-DGNet: Enhancing 3D Dense Captioning with
Quaternion-Based Spatial Offsets and Dynamic Neighborhood GraphsDisparity
Refinement Based on Cross-Modal Feature Fusion and Global Hourglass
Aggregation for Robust Stereo Matching.- Trajectory-based Calibration for
Optical See-Through Head-Mounted Displays without Alignment.- Animatable
Human Rendering from Monocular Video via Pose-Independent Deformation.-
Maximum Spanning Tree for 3D Point Cloud RegistrationLearning the Dynamic
Spatio-Temporal Relationship Between Joints for 3D Human Pose Estimation.-
MaskEditor: Instruct 3D Object Editing with Learned MasksDyGASR: Dynamic
Generalized Gaussian Splatting with Surface Alignment for Accelerated 3D Mesh
Reconstruction.- MMIDM:Generating 3D Gesture from Multimodal Inputs with
Diffusion Models.- Discriminative-guided Diffusion-based Self-supervised
Monocular Depth Estimation.- Multiview Light Field Angular Super-Resolution
based on View Alignment and Frequency Attention.- MagicGS: Combining 2D and
3D Priors for Effective 3D Content Generation.- ESD-Pose: Enhanced Semantic
Discrimination for Generalizable 6D Pose EstimationTrans-DONeRF for
Transparent Object Rendering with Mixed Depth Prior.- SFDNeRF: A Semantic
Feature-Driven Few-Shot Neural Radiance Field Framework with Hybrid
Regularization.- TriEn-Net: Non-parametric Representation Learning for
Large-Scale Point Cloud Semantic Segmentation.- Decomposed Latent Diffusion
Model for 3D Point Cloud Generation.- Learning Multi-Branch Attention
Networks for 3D Face Reconstruction.- CP-VoteNet: Contrastive Prototypical
VoteNet for Few-Shot Point Cloud Object DetectionCross Modality Fusion
Network with Feature Alignment and Salient Object Exchange for Single Image
3D Shape Retrieval.- Enhanced Spatial Adaptive Fusion Network For Video
Super-ResolutionMulti-3D Occlusion Mask Learning for Flexible Occlusion
Removal in Neural Radiance Fields.- Sketch-Based 3D Shape Retrieval via
Cross-Modal Contrastive Learning and Difficulty-Aware Uncertainty
Regularization.- Residual Hybrid Attention Enhanced Video  Super-Resolution
with Cross Convolution.- SDFReg: Learning Signed Distance Functions for Point
Cloud Registration.- Unfolding Gradient Graph Regularization for Point Cloud
Color Denoising.- ER-SFM: EFFICIENT AND ROBUST CLUSTER-BASED STRUCTURE FROM
MOTION.- Multimodal Token Fusion and Optimization for 3D Human Mesh
Reconstruction with Transformers.