IVGT: 暗黙的視覚幾何トランスフォーマーによるニューラルシーン表現
IVGT: Implicit Visual Geometry Transformer for Neural Scene Representation
カメラポーズが未知の多視点画像から、連続的で一貫した3D幾何と外観を暗黙的にモデル化する手法を提案。SDFと色を予測する軽量デコーダを用いて、任意の3D位置での空間クエリを可能にし、メッシュ再構成や新規視点合成など多様なタスクで高い性能を示した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Yuqi Wu, Tianyu Hu, Wenzhao Zheng, Yuanhui Huang, Haowen Sun, Jie Zhou, Jiwen Lu
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Reconstructing coherent 3D geometry and appearance from unposed multi-view images is a fundamental yet challenging problem in computer vision. Most existing visual geometry foundation models predict explicit geometry by regressing pixel-aligned pointmaps, often suffering from redundancy and limited geometric continuity. We propose IVGT, an Implicit Visual Geometry Transformer that implicitly models continuous and coherent geometry from pose-free multi-view images. This formulation learns a continuous neural scene representation in a canonical coordinate system and supports continuous spatial queries at any 3D positions, retrieving local features to predict signed distance (SDF) values and colors using lightweight decoders. It allows direct extraction of continuous and coherent surface geometry, enabling rendering of RGB images, depth maps, and surface normal maps from arbitrary viewpoints. We train IVGT via multi-dataset joint optimization with 2D supervision and 3D geometric regularization. IVGT demonstrates generalization across scenes and achieves strong performance on various tasks, including mesh and point cloud reconstruction, novel view synthesis, depth and surface normal estimation, and camera pose estimation.
