Poster Session: ,
| Board | # | Title |
|---|---|---|
| 118 | 1 | PointSeg: A Training-Free Paradigm for 3D Scene Segmentation via Foundation Models |
| 119 | 5 | Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation |
| 120 | 6 | Constructing a 3D Town from a Single Image |
| 121 | 7 | Semantic-Enhanced Monocular Depth Estimation via Fusion and Distillation of Foundation Models |
| 122 | 8 | Beyond the Frame: Generating 360° Panoramic Videos from Perspective Videos |
| 123 | 9 | STRIDE-QA: Visual Question Answering Dataset for Spatiotemporal Reasoning in Urban Driving Scenes |
| 124 | 12 | PaintScene4D: Consistent 4D Scene Generation from Text Prompts |
| 125 | 14 | Differentiable Room Acoustic Rendering with Multi-View Vision Priors |
| 126 | 15 | Total-Editing: Head Avatar with Editable Appearance, Motion, and Lighting |
| 127 | 16 | DAPS-AGF: Depth-Aware Perceptual Similarity with Adaptive Gradient Filtering for Enhanced Outdoor Scene Reconstruction |
| 178 | 17 | GeoCD: A Differential Local Approximation for Geodesic Chamfer Distance |
| 179 | 18 | Artist-Created Mesh Generation from Raw Observation |
| 180 | 19 | S2GO: Streaming Sparse Gaussian Occupancy Prediction |
| 181 | 21 | CIPHER: Culvert Inspection through Pairwise Frame Selection and High-Efficiency Reconstruction |
| 182 | 22 | UNet-Based Keypoint Regression for Real-Time Cone Localization in Autonomous Racing |
| 183 | 23 | Understanding multi-view transformers |
| 184 | 24 | PU-Gaussian: Point Cloud Upsampling using 3D Gaussian Representation |
| 185 | 25 | EVA-Gaussian: 3D Gaussian-based Real-time Human Novel View Synthesis under Diverse Multi-view Camera Settings |
| 186 | 26 | DeepCollide: Scalable Data-Driven High DoF Configuration Space Modeling using Implicit Neural Representations |
| 187 | 27 | CSG-Fusion: Consistent Sparse-View Gaussian Splatting via Matching-based Fusion |