English(EN)Enhancing 3D Semantic Scene Completion with a Refinement Module
新AI模型推动3D形状补全和深度估计发展
作者PulseAugur 编辑部·[7 个来源]·
研究人员推出了几款新的3D形状补全和深度估计模型。大型深度补全模型（LDCM）使用Transformer从稀疏观测生成密集深度图，性能优于现有方法。I2PRef提供了一种图像驱动的点云补全方法，从单个RGB图像重建完整的点云。DinoComplete利用来自DINO特征和状态空间模型的蒸馏语义先验，实现高效鲁棒的3D形状补全，在参数更少的情况下显示出更高的质量。此外，ESSC-RM是一个即插即用框架，可精炼现有的语义场景补全模型以提高预测性能。
AI
arXiv:2605.30115v1 Announce Type: new Abstract: This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without relying on complex architectural designs, LDCM generates…
This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without relying on complex architectural designs, LDCM generates metric-accurate dense depth maps using a transf…
arXiv:2605.26914v1 Announce Type: new Abstract: We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete…
arXiv cs.CV
TIER_1English(EN)·Furkan Mert Algan, Eckehard Steinbach·
arXiv:2605.26949v1 Announce Type: new Abstract: 3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insufficient for inferring missing structure. We present DinoComplete, a deterministic…
3D shape completion from partial scans remains challenging for unseen categories and noisy real-world observations, where geometry alone is often insufficient for inferring missing structure. We present DinoComplete, a deterministic and efficient shape completion framework that a…
We present an image-conditioned point cloud completion approach that treats images as the primary geometric source rather than a secondary guide. To this end, we introduce an Image-to-Point (I2P) module that can reconstruct complete point clouds directly from a single RGB image, …
arXiv cs.CV
TIER_1English(EN)·Dunxing Zhang (Technical University of Munich, Munich, Germany), Jiachen Lu (Technical University of Munich, Munich, Germany), Han Yang (National Science Center for Earthquake Engineering, Tianjin University, Tianjin, China, School of Civil Engineering, …·
arXiv:2512.18363v2 Announce Type: replace Abstract: We propose ESSC-RM, a plug-and-play Enhancing framework for Semantic Scene Completion with a Refinement Module, which can be seamlessly integrated into existing SSC models. ESSC-RM operates in two phases: a baseline SSC network …
